lowercase g in goose (#4832)

2025-09-26 23:44:38 -05:00
parent bb1b73d634
commit 2032c7099c
120 changed files with 669 additions and 651 deletions
@@ -11,21 +11,21 @@ authors:

 I'm a developer at heart, so when I'm working on a personal project, the hardest part isn't writing code—it's making design decisions. I recently built a calendar user interface. I wanted to enhance its visual appeal, so I researched UI design trends like "glassmorphism" and "claymorphism."

-However, I didn't want to spend hours implementing the CSS for each design trend, so I developed a faster approach: screenshot-driven development. I used an open source developer agent called [Goose](https://github.com/block/goose) to transform my user interfaces quickly.
+However, I didn't want to spend hours implementing the CSS for each design trend, so I developed a faster approach: screenshot-driven development. I used an open source developer agent called [goose](https://github.com/block/goose) to transform my user interfaces quickly.

 <!-- truncate -->

-:::warning Goose Beta Version
-This post was written about a beta version of Goose and the commands and flow may have changed.
+:::warning goose Beta Version
+This post was written about a beta version of goose and the commands and flow may have changed.
 :::

 ### My original calendar:
 ![calendar](screenshot-calendar-og.png)

-### Goose prototyped the designs below: 
-![Goose prototypes](goose-prototypes-calendar.png)
+### goose prototyped the designs below: 
+![goose prototypes](goose-prototypes-calendar.png)

-In this blog post, I'll show you how to quickly prototype design styles by letting Goose handle the CSS for you.
+In this blog post, I'll show you how to quickly prototype design styles by letting goose handle the CSS for you.
 >💡 Note: Your results might look different from my examples - that's part of the fun of generative AI! Each run can produce unique variations of these design trends.

 ## Get Started with Screenshot-Driven Development
@@ -180,7 +180,7 @@ Let's create a basic UI to experiment with. Create an index.html file with the c

 Once saved, open the file in your browser. You should see a calendar!

-### Step 2: Install Goose
+### Step 2: Install goose

 ```bash
 brew install pipx
@@ -196,7 +196,7 @@ goose session start

 #### Bring your own LLM

->Goose will prompt you to set up your API key when you first run this command. You can use various LLM providers like OpenAI or Anthropic
+>goose will prompt you to set up your API key when you first run this command. You can use various LLM providers like OpenAI or Anthropic

 ```bash
 export OPENAI_API_KEY=your_api_key
@@ -205,9 +205,9 @@ export ANTHROPIC_API_KEY=your_api_key
 ```

 ### Step 4: Enable the Screen toolkit
-Goose uses [toolkits](https://block.github.io/goose/plugins/plugins.html) to extend its capabilities. The [screen](https://block.github.io/goose/plugins/available-toolkits.html#6-screen-toolkit) toolkit lets Goose take and analyze screenshots.
+goose uses [toolkits](https://block.github.io/goose/plugins/plugins.html) to extend its capabilities. The [screen](https://block.github.io/goose/plugins/available-toolkits.html#6-screen-toolkit) toolkit lets goose take and analyze screenshots.

-To enable the Screen toolkit, add it to your Goose profile at ~/.config/goose/profiles.yaml.
+To enable the Screen toolkit, add it to your goose profile at ~/.config/goose/profiles.yaml.

 > Your configuration might look slightly different depending on your LLM provider preferences.

@@ -225,8 +225,8 @@ default:
    requires: {}
 ```

-### Step 5: Prompt Goose to screenshot your UI
-Goose analyzes your UI through screenshots to understand its structure and elements. In your Gooses session, prompt Goose to take a screenshot by specifying which display your UI is on:
+### Step 5: Prompt goose to screenshot your UI
+goose analyzes your UI through screenshots to understand its structure and elements. In your gooses session, prompt goose to take a screenshot by specifying which display your UI is on:

 ```bash
 Take a screenshot of display(1)  
@@ -234,11 +234,11 @@ Take a screenshot of display(1)

 > The display number is required - use display(1) for your main monitor or display(2) for a secondary monitor.

-Upon success, Goose will run a `screencapture` command and save it as a temporary file.
+Upon success, goose will run a `screencapture` command and save it as a temporary file.

-### Step 6: Prompt Goose to transform your UI
+### Step 6: Prompt goose to transform your UI

-Now, you can ask Goose to apply different design styles. Here are some of the prompts I gave Goose and the results it produced:
+Now, you can ask goose to apply different design styles. Here are some of the prompts I gave goose and the results it produced:

 #### Glassmorphism

@@ -277,11 +277,11 @@ Apply a brutalist effect please

 ## Learn More

-Developing user interfaces is a blend of creativity and problem-solving. And I love that using Goose gives me more time to focus on creativity rather than wrestling with CSS for hours. 
+Developing user interfaces is a blend of creativity and problem-solving. And I love that using goose gives me more time to focus on creativity rather than wrestling with CSS for hours. 

-Beyond prototyping, Goose's ability to analyze screenshots can help developers identify and resolve UI bugs.
+Beyond prototyping, goose's ability to analyze screenshots can help developers identify and resolve UI bugs.

-If you're interested in learning more, check out the [Goose repo](https://github.com/block/goose) and join our [Discord community](https://discord.gg/block-opensource).
+If you're interested in learning more, check out the [goose repo](https://github.com/block/goose) and join our [Discord community](https://discord.gg/block-opensource).

 <head>
    <meta property="og:title" content="Screenshot-Driven Development" />
@@ -1,53 +1,53 @@
 ---
 draft: false
-title: "Previewing Goose v1.0 Beta"
-description: "Goose v1.0 Beta is here! Learn about the latest features and improvements."
+title: "Previewing goose v1.0 Beta"
+description: "goose v1.0 Beta is here! Learn about the latest features and improvements."
 date: 2024-12-06
 authors:
  - adewale
 ---

-![Goose v1.0 Beta](goose-v1.0-beta.png)
-We are excited to share a preview of the new updates coming to Goose with Goose v1.0 Beta!
+![goose v1.0 Beta](goose-v1.0-beta.png)
+We are excited to share a preview of the new updates coming to goose with goose v1.0 Beta!

-This major update comes with a bunch of new features and improvements that make Goose more powerful and user-friendly. Here are some of the key highlights.
+This major update comes with a bunch of new features and improvements that make goose more powerful and user-friendly. Here are some of the key highlights.

 <!-- truncate -->


-## Exciting Features of Goose 1.0 Beta
+## Exciting Features of goose 1.0 Beta

 ### 1. Transition to Rust

-The core of Goose has been rewritten in Rust. Why does this matter? Rust allows for a more portable and stable experience. This change means that Goose can run smoothly on different systems without the need for Python to be installed, making it easier for anyone to start using it.
+The core of goose has been rewritten in Rust. Why does this matter? Rust allows for a more portable and stable experience. This change means that goose can run smoothly on different systems without the need for Python to be installed, making it easier for anyone to start using it.

 ### 2. Contextual Memory

-Goose will remember previous interactions to better understand ongoing projects. This means you won’t have to keep repeating yourself. Imagine having a conversation with someone who remembers every detail—this is the kind of support Goose aims to offer.
+goose will remember previous interactions to better understand ongoing projects. This means you won’t have to keep repeating yourself. Imagine having a conversation with someone who remembers every detail—this is the kind of support goose aims to offer.

 ### 3. Improved Plugin System

-In Goose v1.0, the Goose toolkit system is being replaced with Extensions. Extensions are modular daemons that Goose can interact with dynamically. As a result, Goose will be able to support more complex plugins and integrations. This will make it easier to extend Goose with new features and functionality.
+In goose v1.0, the goose toolkit system is being replaced with Extensions. Extensions are modular daemons that goose can interact with dynamically. As a result, goose will be able to support more complex plugins and integrations. This will make it easier to extend goose with new features and functionality.

 ### 4. Headless mode

-You can now run Goose in headless mode - this is useful for running Goose on servers or in environments where a graphical interface is not available.
+You can now run goose in headless mode - this is useful for running goose on servers or in environments where a graphical interface is not available.

 ```sh
 cargo run --bin goose -- run -i instructions.md
 ```

-### 5. Goose now has a GUI
+### 5. goose now has a GUI

-Goose now has an electron-based GUI macOS application that provides and alternative to the CLI to interact with Goose and manage your projects.
+goose now has an electron-based GUI macOS application that provides and alternative to the CLI to interact with goose and manage your projects.

-![Goose GUI](goose-gui.png)
+![goose GUI](goose-gui.png)

-### 6. Goose alignment with open protocols
+### 6. goose alignment with open protocols

-Goose v1.0 Beta now uses a custom protocol, that is designed in parallel with [Anthropic’s Model Context Protocol](https://www.anthropic.com/news/model-context-protocol) (MCP) to communicate with Systems. This makes it possible for developers to create their own systems (e.g Jira, ) that Goose can integrate with. 
+goose v1.0 Beta now uses a custom protocol, that is designed in parallel with [Anthropic’s Model Context Protocol](https://www.anthropic.com/news/model-context-protocol) (MCP) to communicate with Systems. This makes it possible for developers to create their own systems (e.g Jira, ) that Goose can integrate with. 

-Excited for many more feature updates and improvements? Stay tuned for more updates on Goose! Check out the [Goose repo](https://github.com/block/goose) and join our [Discord community](https://discord.gg/block-opensource).
+Excited for many more feature updates and improvements? Stay tuned for more updates on Goose! Check out the [goose repo](https://github.com/block/goose) and join our [Discord community](https://discord.gg/block-opensource).


 <head>
@@ -19,30 +19,30 @@ We're in the early days of a new era in tech, one where companies are innovating

 Anthropic is leading the charge with the [Model Context Protocol (MCP)](https://modelcontextprotocol.io), an open standard that enables large language model (LLM) applications to connect with external systems, providing the necessary context for more informed and relevant AI interactions. 

-This is a game changer for AI agents such as [Goose](https://block.github.io/goose/), which can perform tasks autonomously - a significant leap beyond chatbots that only provide step-by-step instructions. However, to unlock the full potential of these AI agents, we need a standard method for connecting them to external data sources. MCP provides this foundation.
+This is a game changer for AI agents such as [goose](https://block.github.io/goose/), which can perform tasks autonomously - a significant leap beyond chatbots that only provide step-by-step instructions. However, to unlock the full potential of these AI agents, we need a standard method for connecting them to external data sources. MCP provides this foundation.

-With MCP's standardized APIs and endpoints, Goose can integrate seamlessly into your systems, enhancing its ability to perform complex tasks like debugging, writing code, and running commands directly in your environment. 
+With MCP's standardized APIs and endpoints, goose can integrate seamlessly into your systems, enhancing its ability to perform complex tasks like debugging, writing code, and running commands directly in your environment. 

-![Goose Framework](goose-framework-1.0.png)
+![goose Framework](goose-framework-1.0.png)

 ### What's Possible

-Without MCP, every [Goose toolkit](https://block.github.io/goose/plugins/using-toolkits.html) developer would need to implement bespoke integrations with every system they need to connect to. Not only is this tedious and repetitive, but it delays the fun stuff.
+Without MCP, every [goose toolkit](https://block.github.io/goose/plugins/using-toolkits.html) developer would need to implement bespoke integrations with every system they need to connect to. Not only is this tedious and repetitive, but it delays the fun stuff.

-Let's take a simple GitHub workflow, for example. Goose interacts directly with the GitHub API using custom scripts or configurations. Developers must configure Goose to authenticate with GitHub and specify endpoints for actions like fetching open pull requests or adding comments. Each integration requires manual setup and custom coding to handle authentication tokens, error handling, and API updates.
+Let's take a simple GitHub workflow, for example. goose interacts directly with the GitHub API using custom scripts or configurations. Developers must configure goose to authenticate with GitHub and specify endpoints for actions like fetching open pull requests or adding comments. Each integration requires manual setup and custom coding to handle authentication tokens, error handling, and API updates.

-MCP simplifies the process by providing a standardized interface for accessing GitHub as a resource. Goose, acting as an [MCP client](https://modelcontextprotocol.io/clients), requests the necessary information (e.g., list of open pull requests) from an [MCP server](https://modelcontextprotocol.io/quickstart#general-architecture) configured to expose GitHub's capabilities. The MCP server handles authentication and communication with GitHub, abstracting away the complexity of API interactions. Goose can then focus on tasks like providing a detailed review comment or suggesting code changes.
+MCP simplifies the process by providing a standardized interface for accessing GitHub as a resource. goose, acting as an [MCP client](https://modelcontextprotocol.io/clients), requests the necessary information (e.g., list of open pull requests) from an [MCP server](https://modelcontextprotocol.io/quickstart#general-architecture) configured to expose GitHub's capabilities. The MCP server handles authentication and communication with GitHub, abstracting away the complexity of API interactions. goose can then focus on tasks like providing a detailed review comment or suggesting code changes.

 ### Join the Ecosystem

-As MCP adoption expands, so does Goose’s potential to deliver even more powerful solutions for your organization. By [integrating Goose](https://block.github.io/goose/) into your workflows and [embracing MCP](https://modelcontextprotocol.io/introduction), you’re not just enhancing your own systems, you’re contributing to the growth of an ecosystem that makes AI tools more interoperable, efficient, and impactful.
+As MCP adoption expands, so does goose’s potential to deliver even more powerful solutions for your organization. By [integrating goose](https://block.github.io/goose/) into your workflows and [embracing MCP](https://modelcontextprotocol.io/introduction), you’re not just enhancing your own systems, you’re contributing to the growth of an ecosystem that makes AI tools more interoperable, efficient, and impactful.



 <head>
  <meta charset="UTF-8" />
  <title>Connecting AI Agents to Your Systems with MCP</title>
-  <meta name="description" content="Goose" />
+  <meta name="description" content="goose" />
  <meta name="keywords" content="MCP, Anthropic, AI Open Standards" />


@@ -1,7 +1,7 @@
 ---
 draft: false
-title: "Resolving CI Issues with Goose: A Practical Walkthrough"
-description: "Leverage Goose to simplify your CI debugging process, fetch detailed information about failed CI runs & annotations directly from GitHub, and even apply fixes directly."
+title: "Resolving CI Issues with goose: A Practical Walkthrough"
+description: "Leverage goose to simplify your CI debugging process, fetch detailed information about failed CI runs & annotations directly from GitHub, and even apply fixes directly."
 date: 2024-12-11
 authors:
  - dalton
@@ -9,12 +9,12 @@ authors:

 ![CI](goose-github-ci.png)

-Running into Continuous Integration (CI) failures in pull requests can be quite frustrating but they happen very often. In this post, we leverage the GitHub CLI (`gh`) using Goose to simplify your CI debugging process, fetch detailed information about failed CI runs and annotations directly from GitHub, and even apply fixes directly.
+Running into Continuous Integration (CI) failures in pull requests can be quite frustrating but they happen very often. In this post, we leverage the GitHub CLI (`gh`) using goose to simplify your CI debugging process, fetch detailed information about failed CI runs and annotations directly from GitHub, and even apply fixes directly.

 <!-- truncate -->

-:::warning Goose Beta Version
-This post was written about a beta version of Goose and the commands and flow may have changed.
+:::warning goose Beta Version
+This post was written about a beta version of goose and the commands and flow may have changed.
 :::


@@ -24,7 +24,7 @@ Before diving in, ensure you have the necessary tools set up.

 ### 1. Install and Authenticate GitHub CLI (`gh`)

-You'll need the [GitHub CLI](https://cli.github.com/) `gh` to enable Goose's access to CI check run details.  
+You'll need the [GitHub CLI](https://cli.github.com/) `gh` to enable goose's access to CI check run details.  

 ```bash
 brew install gh
@@ -34,8 +34,8 @@ gh auth login
 Follow the prompts to authenticate your account.


-### 2. Configure Goose
-Ensure Goose is configured and ready to interact with your repository and local tools. Specifically, you will need to configure a goose profile with the GitHub toolkit.
+### 2. Configure goose
+Ensure goose is configured and ready to interact with your repository and local tools. Specifically, you will need to configure a goose profile with the GitHub toolkit.

 Update your `profiles.yaml` file in `~/.config/goose` with the necessary toolkits:

@@ -56,13 +56,13 @@ Start a session with the profile:
 ```bash
 goose session start --profile my-profile
 ```
-If the profile’s toolkits are not correctly configured, Goose might fail to access `gh` commands.
+If the profile’s toolkits are not correctly configured, goose might fail to access `gh` commands.

-## Resolving CI Failures with Goose
-Once everything is set up, we can now use Goose to tackle CI issues with the following steps:
+## Resolving CI Failures with goose
+Once everything is set up, we can now use goose to tackle CI issues with the following steps:

 ### Step 1: Fetch CI Failure Details
-Ask Goose to retrieve information about the CI failures for a specific PR.
+Ask goose to retrieve information about the CI failures for a specific PR.

 **Example Request:**

@@ -73,20 +73,20 @@ Can you tell me about the CI failures on PR #11111 in the organization/repo repo

 You can access a check run ID by clicking on a PR’s checks tab and selecting a failure. The ID will be available in the URL.

-**Goose's Workflow:**
+**goose's Workflow:**

-Goose will use the `gh` CLI to check run information and provide a detailed summary of the issues. Goose uses the GitHub CLI to:
+goose will use the `gh` CLI to check run information and provide a detailed summary of the issues. goose uses the GitHub CLI to:

 - Fetch details about failed CI runs, including logs and annotations.
 - Provide a clear and actionable summary of issues.

-**Example Command Goose Runs:**
+**Example Command goose Runs:**

 ```curl
 gh api -H "Accept: application/vnd.github+json" /repos/<owner>/<repo>/check-runs/<check-run-id>/annotations
 ```

-**Example Goose Output:**
+**Example goose Output:**
 ```mathematica
 Here are the details for Check Run ID 123456:

@@ -110,8 +110,8 @@ Here are the details for Check Run ID 123456:
   Line: 98  
   Error: Type mismatch in returned value. Expected 'String', found 'Int'.  
 ```
-### Step 2: Request Fixes from Goose
-Once Goose provides the failure details, ask it to resolve the issues directly.
+### Step 2: Request Fixes from goose
+Once goose provides the failure details, ask it to resolve the issues directly.

 Example Request:

@@ -119,13 +119,13 @@ Example Request:
 Can you fix these issues and stage the changes so I can review them? Do not add unnecessary code comments.
 ```

-**What Goose Does:**
+**What goose Does:**

 - Applies fixes based on error messages.
 - Stages changes for review.


-**Example Goose Response:**
+**Example goose Response:**
 ```markdown
 I have fixed the following files and staged them:

@@ -148,26 +148,26 @@ Carefully review the staged changes to ensure they address the issues correctly

 If needed, clean up or re-stage the changes before committing.

-## Benefits of Using Goose
-Using Goose to resolve CI issues streamlines your workflow by:
+## Benefits of Using goose
+Using goose to resolve CI issues streamlines your workflow by:

 - identifying issues and applying fixes with minimal manual effort.
 - integrating with tools like the GitHub CLI to validate changes.
 - handling repetitive CI debugging tasks while you focus on code quality.

-Goose allows you to resolve CI failures efficiently, ensuring confidence in your workflow while reducing the effort required for debugging and testing.
+goose allows you to resolve CI failures efficiently, ensuring confidence in your workflow while reducing the effort required for debugging and testing.

-Try it out, and let Goose handle the heavy lifting of CI debugging for you!
+Try it out, and let goose handle the heavy lifting of CI debugging for you!

 <head>
-  <meta property="og:title" content="Resolving CI Issues with Goose: A Practical Walkthrough" />
+  <meta property="og:title" content="Resolving CI Issues with goose: A Practical Walkthrough" />
  <meta property="og:type" content="article" />
  <meta property="og:url" content="https://block.github.io/goose/blog/2024/12/11/resolving-ci-issues-with-goose-a-practical-walkthrough" />
-  <meta property="og:description" content="Leverage Goose to simplify your CI debugging process, fetch detailed information about failed CI runs & annotations directly from GitHub, and even apply fixes directly." />
+  <meta property="og:description" content="Leverage goose to simplify your CI debugging process, fetch detailed information about failed CI runs & annotations directly from GitHub, and even apply fixes directly." />
  <meta property="og:image" content="https://block.github.io/goose/assets/images/goose-github-ci-30930008ab57b0aebae15a03c73a12b5.png" />
  <meta name="twitter:card" content="summary_large_image" />
  <meta property="twitter:domain" content="block.github.io/goose" />
-  <meta name="twitter:title" content="Resolving CI Issues with Goose: A Practical Walkthrough" />
-  <meta name="twitter:description" content="Leverage Goose to simplify your CI debugging process, fetch detailed information about failed CI runs & annotations directly from GitHub, and even apply fixes directly." />
+  <meta name="twitter:title" content="Resolving CI Issues with goose: A Practical Walkthrough" />
+  <meta name="twitter:description" content="Leverage goose to simplify your CI debugging process, fetch detailed information about failed CI runs & annotations directly from GitHub, and even apply fixes directly." />
  <meta name="twitter:image" content="https://block.github.io/goose/assets/images/goose-github-ci-30930008ab57b0aebae15a03c73a12b5.png" />
 </head>
@@ -9,29 +9,29 @@ authors:

 We are thrilled to announce **codename goose**, your on-machine, open source AI agent built to automate your tasks. 

-Powered by your choice of [large language models (LLMs)](/docs/getting-started/providers), a user-friendly desktop interface and CLI, and [extensions](/docs/getting-started/using-extensions) that integrate with your existing tools and applications, Goose is designed to enhance your productivity and workflow.
+Powered by your choice of [large language models (LLMs)](/docs/getting-started/providers), a user-friendly desktop interface and CLI, and [extensions](/docs/getting-started/using-extensions) that integrate with your existing tools and applications, goose is designed to enhance your productivity and workflow.

 <!--truncate-->


-You can think of Goose as an assistant that is ready to take your instructions, and do the work for you.
+You can think of goose as an assistant that is ready to take your instructions, and do the work for you.

-While Goose's first use cases are engineering focused, the community has been exploring other non-engineering use cases for Goose as well. And it goes without saying, Goose is [open source](https://github.com/block/goose) 🎉.
+While goose's first use cases are engineering focused, the community has been exploring other non-engineering use cases for goose as well. And it goes without saying, goose is [open source](https://github.com/block/goose) 🎉.


-## How Goose Works
+## How goose Works

-Goose operates as an intelligent, autonomous agent capable of handling complex tasks through a well-orchestrated coordination of its core features:
+goose operates as an intelligent, autonomous agent capable of handling complex tasks through a well-orchestrated coordination of its core features:
  
- **Using Extensions**: [Extensions](/docs/getting-started/using-extensions) are key to Goose’s adaptability, providing you the ability to connect with applications and tools that you already use. Whether it’s connecting to GitHub, accessing Google Drive or integrating with JetBrains IDEs, the possibilities are extensive. Some of these extensions have been curated in the [extensions][extensions-directory] directory. Goose extensions are built on the [Model Context Protocol (MCP)](https://www.anthropic.com/news/model-context-protocol) - enabling you to build or bring your own custom integrations to Goose. 
+- **Using Extensions**: [Extensions](/docs/getting-started/using-extensions) are key to goose’s adaptability, providing you the ability to connect with applications and tools that you already use. Whether it’s connecting to GitHub, accessing Google Drive or integrating with JetBrains IDEs, the possibilities are extensive. Some of these extensions have been curated in the [extensions][extensions-directory] directory. goose extensions are built on the [Model Context Protocol (MCP)](https://www.anthropic.com/news/model-context-protocol) - enabling you to build or bring your own custom integrations to goose. 

- **LLM Providers**: Goose is compatible with a wide range of [LLM providers](/docs/getting-started/providers), allowing you to choose and integrate your preferred model. 
+- **LLM Providers**: goose is compatible with a wide range of [LLM providers](/docs/getting-started/providers), allowing you to choose and integrate your preferred model. 

- **CLI and Desktop Support**: You can run Goose as a desktop app or through the command-line interface (CLI) using the same configurations across both.
+- **CLI and Desktop Support**: You can run goose as a desktop app or through the command-line interface (CLI) using the same configurations across both.

-## Goose in Action
+## goose in Action

-Goose is able to handle a wide range of tasks, from simple to complex, across various engineering domains. Here are some examples of tasks that Goose has helped people with:
+goose is able to handle a wide range of tasks, from simple to complex, across various engineering domains. Here are some examples of tasks that goose has helped people with:

 - Conduct code migrations such as Ember to React, Ruby to Kotlin, Prefect-1 to Prefect-2 etc. 
 - Dive into a new project in an unfamiliar coding language
@@ -45,10 +45,10 @@ Goose is able to handle a wide range of tasks, from simple to complex, across va

 ## Getting Started

-You can get started using Goose right away! Check out our [Quickstart](/docs/quickstart).
+You can get started using goose right away! Check out our [Quickstart](/docs/quickstart).


-## Join the Goose Community
+## Join the goose Community

 Excited for upcoming features and events? Be sure to connect with us!

@@ -116,21 +116,21 @@ Without tool calling, LLMs would only guess answers based on their training data

 It's worth noting that not all agents are the same when it comes to tool access. Most proprietary agents are tightly scoped to a specific LLM and a predefined set of tools, as companies build agents tailored for their own applications.

-Other agents, like Goose, are more extensible, allowing users to configure it with the LLM of their choice, as well as add tools for various APIs, databases, and even [local environments like IDEs](/docs/mcp/jetbrains-mcp). However, for agents to scale across different tools and systems without requiring custom integrations for each one, they need a standardized way to discover, call, and manage tools. This is exactly what the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) provides.
+Other agents, like goose, are more extensible, allowing users to configure it with the LLM of their choice, as well as add tools for various APIs, databases, and even [local environments like IDEs](/docs/mcp/jetbrains-mcp). However, for agents to scale across different tools and systems without requiring custom integrations for each one, they need a standardized way to discover, call, and manage tools. This is exactly what the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) provides.

 ## MCP Ecosystem

 Traditional AI integrations require custom API calls for every system, making scaling difficult. MCP solves this by providing an open, universal protocol for agents to communicate with external systems dynamically.

-With MCP, an agent like Goose can:
+With MCP, an agent like goose can:

 * connect to any API without a developer writing manual integration code
 * integrate with cloud services, dev tools, databases, and enterprise systems
 * retrieve and store context to enhance reasoning

-At the time of this writing, there are more than [1000 MCP servers](https://www.pulsemcp.com/servers) (systems that expose tools) that any MCP-enabled AI agent like Goose can connect to! These MCP servers act as bridges between agents and external systems, enabling access to APIs, databases, and development environments. Some were developed by the official API providers, while the vast majority were developed by community members. Because MCP is an open standard, anyone can build an MCP server for any resource. This greatly increases the possibilities of AI agents!
+At the time of this writing, there are more than [1000 MCP servers](https://www.pulsemcp.com/servers) (systems that expose tools) that any MCP-enabled AI agent like goose can connect to! These MCP servers act as bridges between agents and external systems, enabling access to APIs, databases, and development environments. Some were developed by the official API providers, while the vast majority were developed by community members. Because MCP is an open standard, anyone can build an MCP server for any resource. This greatly increases the possibilities of AI agents!

-For example, let's say I want Goose to develop a new web app for me in my WebStorm IDE based on a Figma design and then commit the code to a new repo in GitHub. I can add the following MCP Servers as Goose extensions to give it all of these capabilities:
+For example, let's say I want goose to develop a new web app for me in my WebStorm IDE based on a Figma design and then commit the code to a new repo in GitHub. I can add the following MCP Servers as goose extensions to give it all of these capabilities:

 * [Figma](/docs/mcp/figma-mcp)
 * [JetBrains](/docs/mcp/jetbrains-mcp)
@@ -143,7 +143,7 @@ With this, I can prompt my AI agent in natural language and it'll take care of t
 Pretty powerful, right?! 

 ## Get Started with AI Agents
-Hopefully this has provided clear insight into what are AI agents, how they work, and what they can enable for you. [Goose](/docs/getting-started/installation) is free and open source and you can add as many [extensions](/docs/getting-started/using-extensions#adding-extensions) as you desire. This is a great way to get started with AI agents and see how they can automate tasks in your workflow to make you more efficient.
+Hopefully this has provided clear insight into what are AI agents, how they work, and what they can enable for you. [goose](/docs/getting-started/installation) is free and open source and you can add as many [extensions](/docs/getting-started/using-extensions#adding-extensions) as you desire. This is a great way to get started with AI agents and see how they can automate tasks in your workflow to make you more efficient.


 <head>
@@ -1,45 +1,45 @@
 ---
 title: Let A Team of AI Agents Do It For You
-description: Community Spotlight on Cliff Hall's GooseTeam MCP server.
+description: Community Spotlight on Cliff Hall's gooseTeam MCP server.
 authors: 
    - tania
 ---

 ![blog banner](gooseteam-mcp.png)

-During our [previous livestream](https://youtu.be/9tq-QUnE29U), Aaron Goldsmith, Infrastructure Operations Engineer at Cash App, showed a team of Goose AI agents collaborating in real time to create a website. Our community loved it so much, Cliff Hall was inspired to iterate on that idea and create a GooseTeam MCP server.
+During our [previous livestream](https://youtu.be/9tq-QUnE29U), Aaron Goldsmith, Infrastructure Operations Engineer at Cash App, showed a team of goose AI agents collaborating in real time to create a website. Our community loved it so much, Cliff Hall was inspired to iterate on that idea and create a gooseTeam MCP server.

 <!--truncate-->

 ## The Original Protocol

-Aaron Goldsmith made an AI agent team consisting of multiple Goose instances a reality with his lightweight [Agent Communication Protocol](https://gist.github.com/AaronGoldsmith/114c439ae67e4f4c47cc33e829c82fac). With it, each Goose agent enters the chat, gets assigned a role (e.g. Project Coordinator, Researcher, Web Developer), and works on its part of a given task. The protocol specifies instructions guiding how the agents should talk and behave, allowing multiple Goose agents to collaborate. It also specifies that communication between the agents should be done via a Python-based websocket server with text/markdown . 
+Aaron Goldsmith made an AI agent team consisting of multiple goose instances a reality with his lightweight [Agent Communication Protocol](https://gist.github.com/AaronGoldsmith/114c439ae67e4f4c47cc33e829c82fac). With it, each goose agent enters the chat, gets assigned a role (e.g. Project Coordinator, Researcher, Web Developer), and works on its part of a given task. The protocol specifies instructions guiding how the agents should talk and behave, allowing multiple goose agents to collaborate. It also specifies that communication between the agents should be done via a Python-based websocket server with text/markdown . 

-## GooseTeam MCP Server
+## gooseTeam MCP Server

-Introducing [GooseTeam](https://github.com/cliffhall/GooseTeam), created by Software Architect and community member, Cliff Hall. GooseTeam takes Aaron's protocol and iterates on it into an MCP server and collaboration protocol for Goose Agents. With features like task management, message storage, and agent waiting, you can have an entire team of Goose agents work together on a task or project for you.
+Introducing [gooseTeam](https://github.com/cliffhall/gooseTeam), created by Software Architect and community member, Cliff Hall. gooseTeam takes Aaron's protocol and iterates on it into an MCP server and collaboration protocol for goose Agents. With features like task management, message storage, and agent waiting, you can have an entire team of goose agents work together on a task or project for you.

-A Goose agent with the Project Coordinator role will assign roles to other agents, your connected agents will send messages that can retrieved at any time, and your team of agents will connect to the same MCP server to collaborate together.
+A goose agent with the Project Coordinator role will assign roles to other agents, your connected agents will send messages that can retrieved at any time, and your team of agents will connect to the same MCP server to collaborate together.

-![Goose Agents](gooseteam-agents.png)
+![goose Agents](gooseteam-agents.png)

-## A New Way to Goose
+## A New Way to goose

-Working with a team of AI agents on a task is a game changer. Instead of getting confused as to how to improve your prompt engineering on your own or work across sessions manually, tools like Cliff's GooseTeam or Aaron's Agent Communication Protocol help us make sure AI agents like Goose are doing the work for us as efficiently as possible. The possibilities feel endless!
+Working with a team of AI agents on a task is a game changer. Instead of getting confused as to how to improve your prompt engineering on your own or work across sessions manually, tools like Cliff's gooseTeam or Aaron's Agent Communication Protocol help us make sure AI agents like goose are doing the work for us as efficiently as possible. The possibilities feel endless!

 ## Get Your Contribution Featured
-Hopefully this contribution inspired you as much as it inspired our community. If you have a Goose contribution or project you'd like to share with our community, join our [Discord](https://discord.gg/block-opensource) and share your work in the **#share-your-work** channel. You may just be featured on our livestream or get a cool prize. 👀 You can also star Goose on GitHub or follow us on social media so you never miss an update from us. Until next time!
+Hopefully this contribution inspired you as much as it inspired our community. If you have a goose contribution or project you'd like to share with our community, join our [Discord](https://discord.gg/block-opensource) and share your work in the **#share-your-work** channel. You may just be featured on our livestream or get a cool prize. 👀 You can also star goose on GitHub or follow us on social media so you never miss an update from us. Until next time!


 <head>
  <meta property="og:title" content="Let A Team of AI Agents Do It For You" />
  <meta property="og:type" content="article" />
  <meta property="og:url" content="https://block.github.io/goose/blog/2025/02/17/gooseteam-mcp" />
-  <meta property="og:description" content="Community Spotlight on Cliff Hall's GooseTeam MCP server." />
+  <meta property="og:description" content="Community Spotlight on Cliff Hall's gooseTeam MCP server." />
  <meta property="og:image" content="https://block.github.io/goose/assets/images/gooseteam-mcp-082fa2890c313519c2a1637ca979c219.png" />
  <meta name="twitter:card" content="summary_large_image" />
  <meta property="twitter:domain" content="block.github.io/goose" />
  <meta name="twitter:title" content="Let A Team of AI Agents Do It For You" />
-  <meta name="twitter:description" content="Community Spotlight on Cliff Hall's GooseTeam MCP server." />
+  <meta name="twitter:description" content="Community Spotlight on Cliff Hall's gooseTeam MCP server." />
  <meta name="twitter:image" content="https://block.github.io/goose/assets/images/gooseteam-mcp-082fa2890c313519c2a1637ca979c219.png" />
 </head>
@@ -1,44 +1,44 @@
 ---
-title: 6 Essential Tips for Working with Goose
-description: Practical tips to help you use Goose more effectively and efficiently.
+title: 6 Essential Tips for Working with goose
+description: Practical tips to help you use goose more effectively and efficiently.
 authors: 
    - angie
 ---

 ![goose tips](goose-tips.png)

-Working with AI agents can sometimes feel unpredictable. After using Goose extensively for the last few months, I've compiled a few key tips that will help you get the most out of this tool. No matter your workflow, these guidelines will help you work more efficiently with Goose.
+Working with AI agents can sometimes feel unpredictable. After using goose extensively for the last few months, I've compiled a few key tips that will help you get the most out of this tool. No matter your workflow, these guidelines will help you work more efficiently with goose.


 <!--truncate-->

 ## 1. Keep Sessions Focused and Short

-One of the most common mistakes users make is trying to accomplish too much in a single session. While it might seem efficient to keep the conversation going, longer sessions can actually hinder Goose's performance. 
+One of the most common mistakes users make is trying to accomplish too much in a single session. While it might seem efficient to keep the conversation going, longer sessions can actually hinder goose's performance. 

-Every message adds to the context window, which is the amount of conversation history Goose can retain at any given time. This history is made up of tokens, the individual pieces of text (words or even parts of words) that Goose processes to generate responses. More tokens don’t just increase processing time, they also contribute to LLM usage costs. And once the context window fills up, older messages get pushed out, which can lead to loss of important details or unexpected behavior.
+Every message adds to the context window, which is the amount of conversation history goose can retain at any given time. This history is made up of tokens, the individual pieces of text (words or even parts of words) that goose processes to generate responses. More tokens don’t just increase processing time, they also contribute to LLM usage costs. And once the context window fills up, older messages get pushed out, which can lead to loss of important details or unexpected behavior.

 Think of it like keeping too many browser tabs open. Eventually, it impacts performance. Instead, start fresh sessions for distinct tasks. Don't worry about losing context; that's exactly what the [Memory extension](/docs/mcp/memory-mcp) is for. Keeping sessions focused and concise ensures more accurate, relevant responses while also keeping your LLM costs under control.


 ## 2. Minimize Active Extensions

-When it comes to Goose extensions, less is often more. It's tempting to enable [every available extension](https://www.pulsemcp.com/servers) just in case (I'm guilty of this!), but this approach can be counterproductive. Each active extension adds to the system prompt, increasing complexity and making Goose work harder to decide which tools to use.
+When it comes to goose extensions, less is often more. It's tempting to enable [every available extension](https://www.pulsemcp.com/servers) just in case (I'm guilty of this!), but this approach can be counterproductive. Each active extension adds to the system prompt, increasing complexity and making goose work harder to decide which tools to use.

 Consider this: if you're cooking in a kitchen, having every possible utensil and appliance out on the counter doesn't make you a better chef. It just creates clutter and confusion. The same principle applies here. 

 Go ahead and install any extensions that interest you, but [keep them disabled](/docs/getting-started/using-extensions#enablingdisabling-extensions) until you need them. Start with the built-in [Developer extension](/docs/mcp/developer-mcp) enabled, which is surprisingly powerful on its own, and only enable others when you need their specific capabilities. This leads to faster responses, lower token usage, and often more focused solutions.

 :::tip Bonus Tip
-Before starting a complex task, ask Goose about its current capabilities. A simple prompt like "Do you have tools available to work with [specific technology/service]?" can save time and prevent false starts. Goose can tell you whether it has the necessary tools for your task, and if not, suggest which extensions you might need to enable. This quick check ensures you have the right tools ready before diving in too deep.
+Before starting a complex task, ask goose about its current capabilities. A simple prompt like "Do you have tools available to work with [specific technology/service]?" can save time and prevent false starts. goose can tell you whether it has the necessary tools for your task, and if not, suggest which extensions you might need to enable. This quick check ensures you have the right tools ready before diving in too deep.
 :::

-## 3. Teach Goose with .goosehints Files
+## 3. Teach goose with .goosehints Files


-One of Goose's most powerful features is its ability to understand context through [.goosehints](/docs/guides/using-goosehints) files, acting like a "README for AI". These hints can be set at both the project and global levels to guide Goose’s responses.
+One of goose's most powerful features is its ability to understand context through [.goosehints](/docs/guides/using-goosehints) files, acting like a "README for AI". These hints can be set at both the project and global levels to guide goose’s responses.

-At the project level, placing .goosehints files in your directory helps Goose understand your structure, conventions, and special considerations. You can even use multiple files - one at the root for overall guidance and others in specific directories for more granular instructions (e.g., frontend styling conventions).
+At the project level, placing .goosehints files in your directory helps goose understand your structure, conventions, and special considerations. You can even use multiple files - one at the root for overall guidance and others in specific directories for more granular instructions (e.g., frontend styling conventions).

 Beyond projects, global .goosehints files (`~/.config/goose/.goosehints`) apply across all sessions, making them perfect for things like:

@@ -50,29 +50,29 @@ Beyond projects, global .goosehints files (`~/.config/goose/.goosehints`) apply

 ## 4. Choose the Right Mode for Your Workflow

-Goose offers [different modes](/docs/guides/goose-permissions) that determine how much autonomy it has when modifying files, using extensions, and performing automated actions. 
+goose offers [different modes](/docs/guides/goose-permissions) that determine how much autonomy it has when modifying files, using extensions, and performing automated actions. 

-* ⚡️ **Auto Mode (Default):** Goose can modify, create, and delete files, as well as use extensions, without requiring approval. Best for users who want seamless automation.
+* ⚡️ **Auto Mode (Default):** goose can modify, create, and delete files, as well as use extensions, without requiring approval. Best for users who want seamless automation.

-* ✅ **Approve Mode:** Goose asks for confirmation before making changes. With [Smart Approve](/docs/guides/goose-permissions#permission-modes) enabled, it evaluates risk levels and prompts for high-risk actions while executing safe ones automatically.
+* ✅ **Approve Mode:** goose asks for confirmation before making changes. With [Smart Approve](/docs/guides/goose-permissions#permission-modes) enabled, it evaluates risk levels and prompts for high-risk actions while executing safe ones automatically.

-* 💬 **Chat Mode:** Goose operates in chat-only mode, without modifying files or using extensions. Ideal for users who want AI assistance without automation.
+* 💬 **Chat Mode:** goose operates in chat-only mode, without modifying files or using extensions. Ideal for users who want AI assistance without automation.

-If you’re new to Goose or working on a critical project, Approve Mode offers a great balance of automation and oversight. For hands-free workflows, Auto Mode keeps things moving, while Chat Mode is perfect for brainstorming and general AI assistance.
+If you’re new to goose or working on a critical project, Approve Mode offers a great balance of automation and oversight. For hands-free workflows, Auto Mode keeps things moving, while Chat Mode is perfect for brainstorming and general AI assistance.

-## 5. Guide Goose with Step-by-Step Execution
+## 5. Guide goose with Step-by-Step Execution

-Complex tasks are best handled in stages, and Goose excels when you allow it to break problems into manageable steps. Instead of expecting an instant solution, ask Goose to generate a step-by-step plan first. Review the plan to ensure it aligns with your goals, then let Goose execute each step in sequence.
+Complex tasks are best handled in stages, and goose excels when you allow it to break problems into manageable steps. Instead of expecting an instant solution, ask goose to generate a step-by-step plan first. Review the plan to ensure it aligns with your goals, then let goose execute each step in sequence.

 This structured approach not only improves accuracy but also gives you more control over the process. You can pause, adjust, or refine each step as needed, giving you more control while ensuring better results.

 ## 6. Refine and Iterate for Better Responses

-Goose is powerful, but like any AI, it sometimes needs a second pass to get things right. If you don’t get the response you need, try refining your prompt or asking Goose to adjust its answer.
+goose is powerful, but like any AI, it sometimes needs a second pass to get things right. If you don’t get the response you need, try refining your prompt or asking goose to adjust its answer.

 Good iteration techniques include:

-* Asking Goose to explain its reasoning before taking action
+* Asking goose to explain its reasoning before taking action
 * Requesting alternative solutions to compare different approaches
 * Asking for a step-by-step breakdown of its thought process
 * Rewording prompts to add more detail or constraints
@@ -81,17 +81,17 @@ For example, instead of asking, "Help me debug this error," try, "I’m getting

 ---

-By following these tips, you'll be able to work more effectively with Goose, getting better results while using fewer resources. Remember, the goal is to solve problems efficiently and effectively. Whether you're writing code, automating tasks, or managing complex projects, these guidelines will help you make the most of what Goose has to offer.
+By following these tips, you'll be able to work more effectively with goose, getting better results while using fewer resources. Remember, the goal is to solve problems efficiently and effectively. Whether you're writing code, automating tasks, or managing complex projects, these guidelines will help you make the most of what goose has to offer.

 <head>
-  <meta property="og:title" content="6 Essential Tips for Working with Goose" />
+  <meta property="og:title" content="6 Essential Tips for Working with goose" />
  <meta property="og:type" content="article" />
  <meta property="og:url" content="https://block.github.io/goose/blog/2025/03/06/goose-tips" />
-  <meta property="og:description" content="Practical tips to help you use Goose more effectively and efficiently." />
+  <meta property="og:description" content="Practical tips to help you use goose more effectively and efficiently." />
  <meta property="og:image" content="https://block.github.io/goose/assets/images/goose-tips-4add28cc7201737dfb468ad11980f070.png" />
  <meta name="twitter:card" content="summary_large_image" />
  <meta property="twitter:domain" content="block.github.io/goose" />
-  <meta name="twitter:title" content="6 Essential Tips for Working with Goose" />
-  <meta name="twitter:description" content="Practical tips to help you use Goose more effectively and efficiently." />
+  <meta name="twitter:title" content="6 Essential Tips for Working with goose" />
+  <meta name="twitter:description" content="Practical tips to help you use goose more effectively and efficiently." />
  <meta name="twitter:image" content="https://block.github.io/goose/assets/images/goose-tips-4add28cc7201737dfb468ad11980f070.png" />
 </head>
@@ -1,6 +1,6 @@
 ---
-title: "Automating Phone Calls with Goose"
-description: Practical tips to help you use Goose more effectively and efficiently.
+title: "Automating Phone Calls with goose"
+description: Practical tips to help you use goose more effectively and efficiently.
 authors: 
    - angie
 ---
@@ -11,19 +11,19 @@ authors:

 </div>

-In the latest episode of [Wild Goose Case](https://www.youtube.com/playlist?list=PLyMFt_U2IX4uMW9kpE1FENQUyIgLuUnWD), hosts [Ebony Louis](https://www.linkedin.com/in/ebonylouis/) and [Ace Abati](https://www.linkedin.com/in/acekyd/) explored a fascinating new way to extend Goose’s automation capabilities by integrating with [VOYP](https://voyp.app/), an AI-powered system that makes phone calls. Their guest, [Paulo Taylor](https://www.linkedin.com/in/paulotaylor/), a technology veteran with over 35 years of experience, walked through how developers can use Goose to trigger and manage phone-based interactions through VOYP.
+In the latest episode of [Wild goose Case](https://www.youtube.com/playlist?list=PLyMFt_U2IX4uMW9kpE1FENQUyIgLuUnWD), hosts [Ebony Louis](https://www.linkedin.com/in/ebonylouis/) and [Ace Abati](https://www.linkedin.com/in/acekyd/) explored a fascinating new way to extend goose’s automation capabilities by integrating with [VOYP](https://voyp.app/), an AI-powered system that makes phone calls. Their guest, [Paulo Taylor](https://www.linkedin.com/in/paulotaylor/), a technology veteran with over 35 years of experience, walked through how developers can use goose to trigger and manage phone-based interactions through VOYP.

 <!--truncate-->

-# Expanding Goose’s Reach with AI-Powered Calls
+# Expanding goose’s Reach with AI-Powered Calls

-Goose is already known for automating tasks, but you can extend that automation beyond the screen. With the [VOYP Goose Extension](goose://extension?cmd=npx&arg=-y&arg=voyp-mcp&id=voyp&name=VOYP&description=Automated%20Phone%20Calling&env=VOYP_API_KEY%3DVOYP%20API%20key), you can automate phone calls to retrieve information, handle customer interactions, or even assist with accessibility needs.
+goose is already known for automating tasks, but you can extend that automation beyond the screen. With the [VOYP Goose Extension](goose://extension?cmd=npx&arg=-y&arg=voyp-mcp&id=voyp&name=VOYP&description=Automated%20Phone%20Calling&env=VOYP_API_KEY%3DVOYP%20API%20key), you can automate phone calls to retrieve information, handle customer interactions, or even assist with accessibility needs.

-VOYP functions as an AI call agent, using LLMs and Text-to-Speech (TTS) technology to conduct conversations over the phone. This means you can trigger phone interactions directly from Goose sessions, enabling real-world automation beyond traditional interfaces.
+VOYP functions as an AI call agent, using LLMs and Text-to-Speech (TTS) technology to conduct conversations over the phone. This means you can trigger phone interactions directly from goose sessions, enabling real-world automation beyond traditional interfaces.

 # How It Works

-Under the hood, VOYP utilizes multiple telecom providers to optimize call costs. It supports various LLMs and TTS providers, giving users flexibility in how they configure their AI caller. The integration with Goose is made possible through the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/), which allows Goose to communicate seamlessly with VOYP and other AI-driven tools.
+Under the hood, VOYP utilizes multiple telecom providers to optimize call costs. It supports various LLMs and TTS providers, giving users flexibility in how they configure their AI caller. The integration with goose is made possible through the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/), which allows goose to communicate seamlessly with VOYP and other AI-driven tools.

 # Live Demo: AI Calls in Action
 During the livestream, Paulo demonstrated VOYP’s capabilities with a series of engaging examples. One highlight was a playful experiment where the AI made a phone call to tell a goose-themed joke. 
@@ -32,18 +32,18 @@ During the livestream, Paulo demonstrated VOYP’s capabilities with a series of

 In [another demo](https://www.youtube.com/live/g_F1u6aqohk?t=1515), Paulo had VOYP engage in a conversation with ChatGPT’s phone service about time travel, showing how fluid and adaptable the AI’s responses can be. He also walked through VOYP's real-time conversation monitoring dashboard, which provides a transparent look at how the AI processes and responds during calls.

-# Getting Started with Goose and VOYP
-For those eager to experiment with [VOYP](https://github.com/paulotaylor/voyp-mcp), sign up on the [VOYP website](https://voyp.app/) to create an account and obtain an API key. While calls require credits, new users receive 20 free credits for testing. The cost per call varies by region, with U.S.-based calls being the most affordable at approximately five credits per minute. To integrate VOYP with Goose, [install the VOYP extension](goose://extension?cmd=npx&arg=-y&arg=voyp-mcp&id=voyp&name=VOYP&description=Automated%20Phone%20Calling&env=VOYP_API_KEY%3DVOYP%20API%20key).
+# Getting Started with goose and VOYP
+For those eager to experiment with [VOYP](https://github.com/paulotaylor/voyp-mcp), sign up on the [VOYP website](https://voyp.app/) to create an account and obtain an API key. While calls require credits, new users receive 20 free credits for testing. The cost per call varies by region, with U.S.-based calls being the most affordable at approximately five credits per minute. To integrate VOYP with goose, [install the VOYP extension](goose://extension?cmd=npx&arg=-y&arg=voyp-mcp&id=voyp&name=VOYP&description=Automated%20Phone%20Calling&env=VOYP_API_KEY%3DVOYP%20API%20key).

 <head>
-  <meta property="og:title" content="Wild Goose Case: Automating Phone Calls with Goose and VOYP" />
+  <meta property="og:title" content="Wild goose Case: Automating Phone Calls with goose and VOYP" />
  <meta property="og:type" content="article" />
  <meta property="og:url" content="https://block.github.io/goose/blog/2025/03/06/goose-tips" />
-  <meta property="og:description" content="Give Goose the ability to make phone calls with the VOYP extension." />
+  <meta property="og:description" content="Give goose the ability to make phone calls with the VOYP extension." />
  <meta property="og:image" content="https://block.github.io/goose/assets/images/goose-voyp-215f3391cfbe2132542a2be63db84999.png" />
  <meta name="twitter:card" content="summary_large_image" />
  <meta property="twitter:domain" content="block.github.io/goose" />
-  <meta name="twitter:title" content="Wild Goose Case: Automating Phone Calls with Goose and VOYP" />
-  <meta name="twitter:description" content="Give Goose the ability to make phone calls with the VOYP extension." />
+  <meta name="twitter:title" content="Wild goose Case: Automating Phone Calls with goose and VOYP" />
+  <meta name="twitter:description" content="Give goose the ability to make phone calls with the VOYP extension." />
  <meta name="twitter:image" content="https://block.github.io/goose/assets/images/goose-voyp-215f3391cfbe2132542a2be63db84999.png" />
 </head>
@@ -1,45 +1,45 @@
 ---
-title: "Turn Figma Designs Into Code With Goose"
-description: Give Goose the ability to turn Figma designs into code with the Figma extension.
+title: "Turn Figma Designs Into Code With goose"
+description: Give goose the ability to turn Figma designs into code with the Figma extension.
 authors: 
    - tania
 ---

 ![blog cover](goosefigma.png)

-In our previous episode of [Goose Flight School](https://www.youtube.com/playlist?list=PLyMFt_U2IX4s1pMaidir5P4lSfjUK6Nzm), our host [Adewale Abati](https://www.linkedin.com/in/acekyd/) showed us how to use Goose to take a Figma design and transform it into a functional Nuxt application. In this stream he covered the entire process, from initial setup to final implementation, highlighting how Goose can help developers bridge the gap between design and development.
+In our previous episode of [goose Flight School](https://www.youtube.com/playlist?list=PLyMFt_U2IX4s1pMaidir5P4lSfjUK6Nzm), our host [Adewale Abati](https://www.linkedin.com/in/acekyd/) showed us how to use goose to take a Figma design and transform it into a functional Nuxt application. In this stream he covered the entire process, from initial setup to final implementation, highlighting how goose can help developers bridge the gap between design and development.

 <!--truncate-->

 # How It Works
-[Extensions](https://block.github.io/goose/docs/getting-started/using-extensions) enhance Goose's functionality by connecting with your existing tools and workflows. They add new features, access external data resources, and integrate with other systems. Learn how multiple extensions, including Figma and Developer, worked together seamlessly to dramatically accelerate development.
+[Extensions](https://block.github.io/goose/docs/getting-started/using-extensions) enhance goose's functionality by connecting with your existing tools and workflows. They add new features, access external data resources, and integrate with other systems. Learn how multiple extensions, including Figma and Developer, worked together seamlessly to dramatically accelerate development.

-# Live Tutorial: Goose Builds Live
-During the livestream, Adewale demonstrated step-by-step how Goose handled each development phase, from creating the basic application structure to generating responsive layouts using Tailwind CSS. Adewale also highlighted how Goose addresses potential limitations as you go, showcasing the powerful balance between the Goose's automation and developer control.
+# Live Tutorial: goose Builds Live
+During the livestream, Adewale demonstrated step-by-step how goose handled each development phase, from creating the basic application structure to generating responsive layouts using Tailwind CSS. Adewale also highlighted how goose addresses potential limitations as you go, showcasing the powerful balance between the goose's automation and developer control.

 <iframe class="aspect-ratio" src="https://www.youtube.com/embed/_9t_N9zKwKM?si=r3e1MkrjS-f2AvkI" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>

-Throughout the stream, Adewale shared valuable tips to prepare your design for Goose. His key recommendations include: 
+Throughout the stream, Adewale shared valuable tips to prepare your design for goose. His key recommendations include: 

 * start with a well-structured Figma design
-* use Goose to make targeted improvements after the initial generation
+* use goose to make targeted improvements after the initial generation
 * fine-tune specific elements as needed
 * make sure you thoroughly test for functionality and responsiveness

-# Getting Started with Goose and Figma
-Whether you're a designer wanting to rapidly turn concepts into working code or a developer curious about streamlining design implementation, you can download Goose with its built-in [Developer extension](https://block.github.io/goose/docs/getting-started/installation) and add the [Figma extension](https://block.github.io/goose/v1/extensions/). 
+# Getting Started with goose and Figma
+Whether you're a designer wanting to rapidly turn concepts into working code or a developer curious about streamlining design implementation, you can download goose with its built-in [Developer extension](https://block.github.io/goose/docs/getting-started/installation) and add the [Figma extension](https://block.github.io/goose/v1/extensions/). 

 For step-by-step instructions, check out the [Figma tutorial](/docs/mcp/figma-mcp).

 <head>
-  <meta property="og:title" content="Goose Flight School: Turn Figma Designs Into Code With Goose" />
+  <meta property="og:title" content="goose Flight School: Turn Figma Designs Into Code With goose" />
  <meta property="og:type" content="article" />
  <meta property="og:url" content="https://block.github.io/goose/blog/2025/03/12/goose-figma-mcp" />
-  <meta property="og:description" content="Give Goose the ability to turn Figma designs into code with the Figma extension." />
+  <meta property="og:description" content="Give goose the ability to turn Figma designs into code with the Figma extension." />
  <meta property="og:image" content="http://block.github.io/goose/assets/images/goosefigma-e6f84a734bd56cb431bb02452331a5d5.png" />
  <meta name="twitter:card" content="summary_large_image" />
  <meta property="twitter:domain" content="block.github.io/goose" />
-  <meta name="twitter:title" content="Goose Flight School: Turn Figma Designs Into Code With Goose" />
-  <meta name="twitter:description" content="Give Goose the ability to turn Figma designs into code with the Figma extension." />
+  <meta name="twitter:title" content="goose Flight School: Turn Figma Designs Into Code With goose" />
+  <meta name="twitter:description" content="Give goose the ability to turn Figma designs into code with the Figma extension." />
  <meta name="twitter:image" content="http://block.github.io/goose/assets/images/goosefigma-e6f84a734bd56cb431bb02452331a5d5.png" />
 </head>
@@ -1,23 +1,23 @@
 ---
-title: "AI, But Make It Local With Goose and Ollama"
-description: Integrate Goose with Ollama for a fully local experience.
+title: "AI, But Make It Local With goose and Ollama"
+description: Integrate goose with Ollama for a fully local experience.
 authors: 
    - tania
 ---

 ![blog cover](gooseollama.png)

-On the [Goosing Around](https://youtube.com/playlist?list=PLyMFt_U2IX4uFFhd_2TD9-tlJkgHMMb6F&feature=shared) stream series, host [Rizel Scarlett](https://www.linkedin.com/in/rizel-bobb-semple/) [demonstrated how to use Goose locally with Ollama](https://youtube.com/watch?v=WG10r2N0IwM?feature=share) for a fully local experience on your device. Her guest, [Parth Sareen](https://www.linkedin.com/in/parthsareen/), an experienced software engineer with a focus on building frameworks and systems for AI/ML, showed us the magic of structured outputs and how Goose and Ollama work together under the hood.
+On the [Goosing Around](https://youtube.com/playlist?list=PLyMFt_U2IX4uFFhd_2TD9-tlJkgHMMb6F&feature=shared) stream series, host [Rizel Scarlett](https://www.linkedin.com/in/rizel-bobb-semple/) [demonstrated how to use goose locally with Ollama](https://youtube.com/watch?v=WG10r2N0IwM?feature=share) for a fully local experience on your device. Her guest, [Parth Sareen](https://www.linkedin.com/in/parthsareen/), an experienced software engineer with a focus on building frameworks and systems for AI/ML, showed us the magic of structured outputs and how goose and Ollama work together under the hood.

 <!--truncate-->

-Goose serves as an on-machine AI agent that can interact with your applications and tools through extensions, providing the framework and interface for AI-powered workflows. Ollama enables running large language models locally with a simple API, handling the optimization of models to run efficiently on consumer hardware.
+goose serves as an on-machine AI agent that can interact with your applications and tools through extensions, providing the framework and interface for AI-powered workflows. Ollama enables running large language models locally with a simple API, handling the optimization of models to run efficiently on consumer hardware.

 Together, they create a self-contained AI agent workflow that puts advanced capabilities directly in the hands of developers.

 # Getting Started

-Before diving deep into various capabilities, Rizel walked us through how to set yourself up for success by integrating Goose with Ollama. To follow along, you can download Goose [here](https://block.github.io/goose/) and follow a step-by-step walk through in the [Configure LLM Provider](https://block.github.io/goose/docs/getting-started/providers) guide.
+Before diving deep into various capabilities, Rizel walked us through how to set yourself up for success by integrating goose with Ollama. To follow along, you can download goose [here](https://block.github.io/goose/) and follow a step-by-step walk through in the [Configure LLM Provider](https://block.github.io/goose/docs/getting-started/providers) guide.

 If you have any questions or get stuck, feel free to chat with us on [Discord](https://discord.gg/block-opensource) or post an issue/discussion on [GitHub](https://github.com/block/goose/). Thanks for reading!

@@ -28,7 +28,7 @@ Using cloud-based LLMs and providers make it so you don't need substantial compu
 - **Offline capability** transforms when and where you can use AI. "I use Ollama all the time on planes—it's a lot of fun!" Parth shared, highlighting how local models free you from the constraints of internet connectivity.
 - **Direct control over model behavior** means you can fine-tune parameters without subscription fees or API limits. Open source models allow you to get a closer look at what's happening behind the scenes.

-Personal use cases like development assistance, personal knowledge management, education, and content management are but some examples that can benefit from working locally and offline. You can keep research and sensitive data private, and utilize Goose when you have limited connectivity.
+Personal use cases like development assistance, personal knowledge management, education, and content management are but some examples that can benefit from working locally and offline. You can keep research and sensitive data private, and utilize goose when you have limited connectivity.

 # Can My Machine Handle This?
 This question came up repeatedly, and the answer is more encouraging than you think. As Parth pointed out, "You don't need to run the largest models to get excellent results." The requirements you'll want to look out for on your device boils down to this:
@@ -83,17 +83,17 @@ As Parth walked through these examples, he shared key practices to ensure you ge
 # It's About The Freedom To Choose
 While there are trade-offs in terms of raw processing power when you go local vs cloud, you don't have to choose one over the other. As Parth summarized during the livestream: "Local AI isn't about replacing cloud options—it's about having the freedom to choose the right approach for your specific needs."

-The benefits of owning your AI experience can be compelling for a variety of use cases. Whether you're a developer building tools, a writer working with confidential material, or simply someone who values privacy and control, I hope the Goose-Ollama integration offers a glimpse into how a local experience can benefit you, and explore a future where sophisticated AI is as personal and private as the data on your hard drive. Thanks for reading!
+The benefits of owning your AI experience can be compelling for a variety of use cases. Whether you're a developer building tools, a writer working with confidential material, or simply someone who values privacy and control, I hope the goose-Ollama integration offers a glimpse into how a local experience can benefit you, and explore a future where sophisticated AI is as personal and private as the data on your hard drive. Thanks for reading!

 <head>
-  <meta property="og:title" content="Goosing Around: AI, But Make It Local With Goose and Ollama" />
+  <meta property="og:title" content="Goosing Around: AI, But Make It Local With goose and Ollama" />
  <meta property="og:type" content="article" />
  <meta property="og:url" content="https://block.github.io/goose/blog/2025/03/13/goose-ollama-local" />
-  <meta property="og:description" content="Integrate Goose with Ollama for a fully local experience." />
+  <meta property="og:description" content="Integrate goose with Ollama for a fully local experience." />
  <meta property="og:image" content="http://block.github.io/goose/assets/images/gooseollama-fbb2cb67117c81eaa189a6b6174e6c6c.png" />
  <meta name="twitter:card" content="summary_large_image" />
  <meta property="twitter:domain" content="block.github.io/goose" />
-  <meta name="twitter:title" content="Goosing Around: AI, But Make It Local With Goose and Ollama" />
-  <meta name="twitter:description" content="Integrate Goose with Ollama for a fully local experience." />
+  <meta name="twitter:title" content="Goosing Around: AI, But Make It Local With goose and Ollama" />
+  <meta name="twitter:description" content="Integrate goose with Ollama for a fully local experience." />
  <meta name="twitter:image" content="http://block.github.io/goose/assets/images/gooseollama-fbb2cb67117c81eaa189a6b6174e6c6c.png" />
 </head>
@@ -1,64 +1,64 @@
 ---
-title: "How Goose Catches AI Errors with Langfuse"
-description: Get detailed insights into Goose's behavior with Langfuse's observability tools.
+title: "How goose Catches AI Errors with Langfuse"
+description: Get detailed insights into goose's behavior with Langfuse's observability tools.
 authors: 
    - tania
 ---

 ![blog cover](goose_aierrors.png)

-How do we debug AI agents like Goose? In the [Goosing Around](https://youtube.com/playlist?list=PLyMFt_U2IX4uFFhd_2TD9-tlJkgHMMb6F&feature=shared) stream series, host [Rizel Scarlett](https://www.linkedin.com/in/rizel-bobb-semple/) invited [Marc Klingen](https://www.linkedin.com/in/marcklingen/), Co-Founder at Langfuse, and [Alice Hau](https://www.linkedin.com/in/alice-hau/), Machine Learning Engineer at Block, to demo how Langfuse enables observability into Goose's actions, letting you trace LLM behavior and catch errors.
+How do we debug AI agents like goose? In the [Goosing Around](https://youtube.com/playlist?list=PLyMFt_U2IX4uFFhd_2TD9-tlJkgHMMb6F&feature=shared) stream series, host [Rizel Scarlett](https://www.linkedin.com/in/rizel-bobb-semple/) invited [Marc Klingen](https://www.linkedin.com/in/marcklingen/), Co-Founder at Langfuse, and [Alice Hau](https://www.linkedin.com/in/alice-hau/), Machine Learning Engineer at Block, to demo how Langfuse enables observability into goose's actions, letting you trace LLM behavior and catch errors.

 <!--truncate-->

 ## What is Langfuse

-[Langfuse](https://langfuse.com/) is an open source observability platform specifically designed for LLM-powered apps. Mark revealed during stream that Langfuse wasn't originally an observability platform, it was born from early attempts to build an AI agent like Goose. 
+[Langfuse](https://langfuse.com/) is an open source observability platform specifically designed for LLM-powered apps. Mark revealed during stream that Langfuse wasn't originally an observability platform, it was born from early attempts to build an AI agent like goose. 

 While they were limited by the available models at the time, especially with multi-file edits, the team discovered the tooling they had built for debugging and monitoring their agent was more valuable to them than their agent.

-## How Langfuse Works With Goose
-Since traditional observability tools don't quite cut it when it comes to AI agents. Langfuse introduces 3 core concepts to make Goose's behavior more observable, and create logs that are easier to parse:
+## How Langfuse Works With goose
+Since traditional observability tools don't quite cut it when it comes to AI agents. Langfuse introduces 3 core concepts to make goose's behavior more observable, and create logs that are easier to parse:

 ### Traces

-Each interaction with Goose creates a trace to capture the full story of what happened. These traces include key information, from the initial prompt and user messages to tool calls and their responses. They also store valuable metadata about model outputs and timing information, giving developers a complete picture of each interaction.
+Each interaction with goose creates a trace to capture the full story of what happened. These traces include key information, from the initial prompt and user messages to tool calls and their responses. They also store valuable metadata about model outputs and timing information, giving developers a complete picture of each interaction.

 ### Timeline View
-The timeline view takes these complex interactions and transforms it into a digestible format. Developers can see parallel task execution in real-time, understand the dependencies between different actions, and measure the actual duration of each opersation. This can be super helpful when debugging a complex sequence of actions taken by Goose, or to help optimize performance.
+The timeline view takes these complex interactions and transforms it into a digestible format. Developers can see parallel task execution in real-time, understand the dependencies between different actions, and measure the actual duration of each opersation. This can be super helpful when debugging a complex sequence of actions taken by goose, or to help optimize performance.

 ### Structured Data
-Alice explained, "Goose sessions can be really long... we have log files, but you'll just see a massive log of JSON."
+Alice explained, "goose sessions can be really long... we have log files, but you'll just see a massive log of JSON."

 Rather than rangle raw JSON log, Langfuse helps organize this data to help make navigating longer sessions and their data more straightforward. This approach can help developers easily analyze tool usage patterns, monitor token consumption, and quickly identify any performance bottlenecks and where they may happen.

-With this integration, you can instead better understand the sequence of actions taken by Goose, and analyze track token usage and model behavior across LLMs.
+With this integration, you can instead better understand the sequence of actions taken by goose, and analyze track token usage and model behavior across LLMs.

 ## Practical Benefits
-The observability the Goose and Langfuse integration brings is great for anyone who wants clear insight into what Goose is doing behind the scenes. Alice and Marc discussed the different ways this integration can help you debug faster.
+The observability the goose and Langfuse integration brings is great for anyone who wants clear insight into what goose is doing behind the scenes. Alice and Marc discussed the different ways this integration can help you debug faster.

-Developers can dive deeper into detailed session logs and identify the root cause to a reported issue and ensure Goose is operating as efficiently as possible. Like checking why certain commands may not be working as expected, or seeing exactly how Goose is processing information for a given task with a specific LLM. 
+Developers can dive deeper into detailed session logs and identify the root cause to a reported issue and ensure goose is operating as efficiently as possible. Like checking why certain commands may not be working as expected, or seeing exactly how goose is processing information for a given task with a specific LLM. 

 As developers focus on operational efficiency, researchers can use the analytical capabilities of this integration to better understand which models best suit their needs. Through comprehensive model evaluations, they can analyze how different models handle tool calling, understand decision-making patterns across LLMs, and establish a systematic approach to understanding and improving AI systems.

 # The Future of AI Observability
-These powerful debugging and analysis capabilities are only the beginning. This integration between Goose and Langfuse represents a significant step forward in making AI agents as transparent and debuggable as traditional code.
+These powerful debugging and analysis capabilities are only the beginning. This integration between goose and Langfuse represents a significant step forward in making AI agents as transparent and debuggable as traditional code.

-To keep up with the exciting developments as they release, you can check out both of the [Goose](https://github.com/block/goose) and [Langfuse](https://github.com/langfuse/langfuse) repositories on GitHub. 
+To keep up with the exciting developments as they release, you can check out both of the [goose](https://github.com/block/goose) and [Langfuse](https://github.com/langfuse/langfuse) repositories on GitHub. 

-You can also watch the [livestream discussing the Goose and Langfuse integration](https://www.youtube.com/live/W39BQjsTS9E?feature=shared), and follow the [tutorial showing you how to integrate Langfuse with Goose](/docs/tutorials/langfuse).
+You can also watch the [livestream discussing the goose and Langfuse integration](https://www.youtube.com/live/W39BQjsTS9E?feature=shared), and follow the [tutorial showing you how to integrate Langfuse with goose](/docs/tutorials/langfuse).

 Also, be sure to subscribe to our [events calendar](https://calget.com/c/t7jszrie) to catch upcoming events.

 <head>
-  <meta property="og:title" content="How Goose Catches AI Errors with Langfuse" />
+  <meta property="og:title" content="How goose Catches AI Errors with Langfuse" />
  <meta property="og:type" content="article" />
  <meta property="og:url" content="https://block.github.io/goose/blog/2025/03/18/goose-langfuse" />
-  <meta property="og:description" content="Get detailed insights into Goose's behavior with Langfuse's observability tools." />
+  <meta property="og:description" content="Get detailed insights into goose's behavior with Langfuse's observability tools." />
  <meta property="og:image" content="http://block.github.io/goose/assets/images/goose_aierrors-22154af884db86789ce1a12a72897e8e.png" />
  <meta name="twitter:card" content="summary_large_image" />
  <meta property="twitter:domain" content="block.github.io/goose" />
-  <meta name="twitter:title" content="How Goose Catches AI Errors with Langfuse" />
-  <meta name="twitter:description" content="Get detailed insights into Goose's behavior with Langfuse's observability tools." />
+  <meta name="twitter:title" content="How goose Catches AI Errors with Langfuse" />
+  <meta name="twitter:description" content="Get detailed insights into goose's behavior with Langfuse's observability tools." />
  <meta name="twitter:image" content="http://block.github.io/goose/assets/images/goose_aierrors-22154af884db86789ce1a12a72897e8e.png" />
 </head>
@@ -8,144 +8,144 @@ authors:

 Remember that saying, "it’s not what you ask, but **how you ask**"?

-When I first started working with Goose as an AI agent, I was convinced there had to be one ‘best' prompting style. I spent so much time trying to figure out which one was superior, but the more I used Goose, the more I realized that couldn't be further from the truth. There isn’t one _right_  way to prompt AI, but there are better approaches depending on what your end goal is.
+When I first started working with goose as an AI agent, I was convinced there had to be one ‘best' prompting style. I spent so much time trying to figure out which one was superior, but the more I used goose, the more I realized that couldn't be further from the truth. There isn’t one _right_  way to prompt AI, but there are better approaches depending on what your end goal is.

-So, let’s go through **which prompt style works best for your specific needs**, and how you can use them to vibe code a little better with Goose.
+So, let’s go through **which prompt style works best for your specific needs**, and how you can use them to vibe code a little better with goose.

 <!--truncate-->

 ## Instruction-Based Prompting

-If you’re not a developer or you're just new to Goose, this is a great place to start. The best way to get good responses is to be as clear and direct as possible. Goose works best when given specific instructions, so tell it exactly what you need and include all of the important details. If you’re too vague, you might end up with an overly technical or even a possibly incomplete answer that doesn’t actually help you.
+If you’re not a developer or you're just new to goose, this is a great place to start. The best way to get good responses is to be as clear and direct as possible. goose works best when given specific instructions, so tell it exactly what you need and include all of the important details. If you’re too vague, you might end up with an overly technical or even a possibly incomplete answer that doesn’t actually help you.


 For example, instead of saying:

 ❌ Okay Prompt: 

->_**Goose, what’s a pull request?**_ 
+>_**goose, what’s a pull request?**_ 

 This might give you a super technical definition that assumes you already know the basics. 

 So, you could say:

 ✅ Better Prompt:
->_**Goose, explain how GitHub pull requests work like I’m new to coding**_ 
+>_**goose, explain how GitHub pull requests work like I’m new to coding**_ 

-This tells Goose exactly what you need and at what level. 
+This tells goose exactly what you need and at what level. 


 :::tip pro tip
-If you want Goose to remember your preferences, you can say, 
+If you want goose to remember your preferences, you can say, 

->_**Goose, remember I’m not a developer. Explain things at a high level unless I ask for technical details**_
+>_**goose, remember I’m not a developer. Explain things at a high level unless I ask for technical details**_

-If you have the [Memory Extension](/docs/mcp/memory-mcp) enabled, Goose will save this preference so you won’t have to remind it every time. 
+If you have the [Memory Extension](/docs/mcp/memory-mcp) enabled, goose will save this preference so you won’t have to remind it every time. 
 :::

 ## Chain-of-Thought Prompting

-Sometimes a topic or task can just be too much to tackle all at once, and that’s where Chain-of-Thought Prompting comes in. Instead of getting this enormous and complicated response back, you can guide Goose to break things down step by step so it’s easier to follow.
+Sometimes a topic or task can just be too much to tackle all at once, and that’s where Chain-of-Thought Prompting comes in. Instead of getting this enormous and complicated response back, you can guide goose to break things down step by step so it’s easier to follow.


 For example, instead of saying:

 ❌ Okay Prompt: 

->_**Goose, what are Model Context Protocol Servers, and how are they used in goose?**_
+>_**goose, what are Model Context Protocol Servers, and how are they used in goose?**_

 which might get you a response that's hard to follow, you could say:

 ✅ Better Prompt:
 
->_**Goose, walk me through what MCPs are and how they're used in gosoe, step by step**_ 
+>_**goose, walk me through what MCPs are and how they're used in gosoe, step by step**_ 

-This forces Goose to slow down and explain each part clearly, making it easier to understand.
+This forces goose to slow down and explain each part clearly, making it easier to understand.

-Now, if you want to take it a step further and make sure Goose understands the exact style of responses you're expecting, that’s when Few-Shot Prompting is the way to go.
+Now, if you want to take it a step further and make sure goose understands the exact style of responses you're expecting, that’s when Few-Shot Prompting is the way to go.

 ## Few-Shot Prompting

-If you need Goose to match a specific style or format, the best way to get there is by showing it what you want. I use this all the time! Since AI models learn patterns from examples, giving Goose a reference helps it skip the guesswork and just get straight to the point.
+If you need goose to match a specific style or format, the best way to get there is by showing it what you want. I use this all the time! Since AI models learn patterns from examples, giving goose a reference helps it skip the guesswork and just get straight to the point.

 For example, instead of saying: 

 ❌ Okay Prompt: 

->_**Goose, summarize this report**_ 
+>_**goose, summarize this report**_ 

 you could say: 

 ✅ Better Prompt:

->_**Goose, here’s how I usually summarize reports: (example summary). Can you summarize this new report the same way?**_
+>_**goose, here’s how I usually summarize reports: (example summary). Can you summarize this new report the same way?**_
 
-By providing an example, you’re guiding Goose to the answer that you actually want.
+By providing an example, you’re guiding goose to the answer that you actually want.

-Now, what if you've given Goose an example and it’s first response isn’t quite right? There's no need to end the session and start over, that’s when Iterative Refinement Prompting is useful.
+Now, what if you've given goose an example and it’s first response isn’t quite right? There's no need to end the session and start over, that’s when Iterative Refinement Prompting is useful.

 ## Iterative Refinement Prompting

-Let’s be real, Goose just like any AI agent isn’t always going to get it 'right' on the first try. Sometimes, it gives you a response that's way too technical, other times, it might completely miss the mark or even worse, hallucinate its way into a weird, made-up answer, that kind of sounds true. But instead of giving up and starting over, you can steer the conversation by giving feedback on what needs to change.
+Let’s be real, goose just like any AI agent isn’t always going to get it 'right' on the first try. Sometimes, it gives you a response that's way too technical, other times, it might completely miss the mark or even worse, hallucinate its way into a weird, made-up answer, that kind of sounds true. But instead of giving up and starting over, you can steer the conversation by giving feedback on what needs to change.

-Since Goose allows you to bring your own LLM, the way it responds depends a lot on which model you’re using. Some LLMs need a little extra guidance, while others might require a few rounds of refinement before they get things right. The good news? You can shape the response without completely starting over.
+Since goose allows you to bring your own LLM, the way it responds depends a lot on which model you’re using. Some LLMs need a little extra guidance, while others might require a few rounds of refinement before they get things right. The good news? You can shape the response without completely starting over.

-For example, if Goose spits out something overly complicated, don’t just accept it, you can push back! Try saying:
+For example, if goose spits out something overly complicated, don’t just accept it, you can push back! Try saying:

->_**Goose, this response is too technical. Can you simplify it?**_ 
+>_**goose, this response is too technical. Can you simplify it?**_ 

 Or if something sounds off and you want to do a fact check:

->_**Goose, where did you get that information? How do you know it's accurate?**_ 
+>_**goose, where did you get that information? How do you know it's accurate?**_ 

-Think of working with Goose like pair programming or collaborating with a coworker. Sometimes, you need to clarify what you want or redirect the conversation to get make sure you're both on the same page.
+Think of working with goose like pair programming or collaborating with a coworker. Sometimes, you need to clarify what you want or redirect the conversation to get make sure you're both on the same page.

-But what if you don’t have a clear example or specific instructions to guide Goose? That’s when I would use Zero-Shot Prompting.
+But what if you don’t have a clear example or specific instructions to guide goose? That’s when I would use Zero-Shot Prompting.

 ## Zero-Shot Prompting

-Sometimes, you just want Goose to take a wild guess, get a little creative, and run with it. That’s exactly what Zero-Shot Prompting is for, it lets Goose figure things out on its own, without any examples or extra guidance from you.
+Sometimes, you just want goose to take a wild guess, get a little creative, and run with it. That’s exactly what Zero-Shot Prompting is for, it lets goose figure things out on its own, without any examples or extra guidance from you.

 For example, you might say:

->_**Goose, write me a project update for my team**_ 
+>_**goose, write me a project update for my team**_ 

 or: 

->_**Goose, I want to build a cool prompt directory**_ 
+>_**goose, I want to build a cool prompt directory**_ 

-I love using this approach when I have a rough idea but no real clear direction. It’s like brainstorming but with AI, Goose will throw out ideas, suggest next steps, and sometimes even point out things I would’ve never even thought of. More often than not, my original idea ends up 10x better just by letting Goose take the lead.
+I love using this approach when I have a rough idea but no real clear direction. It’s like brainstorming but with AI, goose will throw out ideas, suggest next steps, and sometimes even point out things I would’ve never even thought of. More often than not, my original idea ends up 10x better just by letting goose take the lead.

-Now, if you want Goose to not just come up with amazing ideas but also be funny, helpful, and maybe even a little nicer to you, that’s when you need to put those manners you learned in elementary school to use.
+Now, if you want goose to not just come up with amazing ideas but also be funny, helpful, and maybe even a little nicer to you, that’s when you need to put those manners you learned in elementary school to use.

 ## Politeness-Based Prompting

-Believe it or not, being polite actually makes AI responses better! Even though Goose isn’t self-aware……yet…… 👀, AI models tend to generate more thoughtful, structured, and sometimes even friendlier replies when asked nicely. So yes, saying “please” and “thank you” actually makes a difference.
+Believe it or not, being polite actually makes AI responses better! Even though goose isn’t self-aware……yet…… 👀, AI models tend to generate more thoughtful, structured, and sometimes even friendlier replies when asked nicely. So yes, saying “please” and “thank you” actually makes a difference.

 For example, instead of saying:

 ❌ Okay Prompt:

->_**Goose, generate a project update**_ 
+>_**goose, generate a project update**_ 

 you could say:

 ✅ Better Prompt:

->_**Goose, could you generate a project update for me, please? Thanks!**_ 
+>_**goose, could you generate a project update for me, please? Thanks!**_ 

-Goose will respond either way, but **trust me**, polite prompts tend to get you better answers. One of our users once got the sweetest response from Goose at the end of a project, like it was genuinely grateful for the collaboration and even wished them sweet dreams. It was adorable!!
+goose will respond either way, but **trust me**, polite prompts tend to get you better answers. One of our users once got the sweetest response from goose at the end of a project, like it was genuinely grateful for the collaboration and even wished them sweet dreams. It was adorable!!

 ![goose response](politenessprompt.png)
->_Here’s the actual response, Goose is really out here making people’s day._
+>_Here’s the actual response, goose is really out here making people’s day._

-And the best part? This works with any prompting style. So, if you want Goose to be helpful, clear, and maybe even a little extra nice to you, be good to Goose and Goose will be good to you.
+And the best part? This works with any prompting style. So, if you want goose to be helpful, clear, and maybe even a little extra nice to you, be good to goose and goose will be good to you.

 ## The Best Prompts Feel Natural

 At the end of the day, all these prompting styles are just tools, at your disposal. The most important thing is to keep your prompts clear and natural. You don’t have to overthink it, but adding a little structure can make a huge difference in getting the responses you actually want.

-Goose is here to make your life easier, so the next time you open up a session, just keep your goal in mind, experiment with different prompting styles, and see what works best for you.
+goose is here to make your life easier, so the next time you open up a session, just keep your goal in mind, experiment with different prompting styles, and see what works best for you.

 <head>
  <meta property="og:title" content="AI Prompting 101: How to Get the Best Responses from Your AI Agent" />
@@ -1,5 +1,5 @@
 ---
-title: "How I Use Goose to Plan My Week with Asana and Google Calendar MCPs"
+title: "How I Use goose to Plan My Week with Asana and Google Calendar MCPs"
 description: Use MCPs with Goose to automate task management and enhance productivity.
 authors: 
    - angie
@@ -7,11 +7,11 @@ authors:

 ![blog cover](mcp-planner.png)

-Mondays are overwhelming. A pile of unfinished tasks from last week, new priorities rolling in, and meetings scattered across the calendar. It’s a lot 😩. Instead of manually sorting through my todos and figuring out where everything fits, I use a couple of handy MCP servers with Goose and let it figure out my week.
+Mondays are overwhelming. A pile of unfinished tasks from last week, new priorities rolling in, and meetings scattered across the calendar. It’s a lot 😩. Instead of manually sorting through my todos and figuring out where everything fits, I use a couple of handy MCP servers with goose and let it figure out my week.

 <!--truncate-->

-There's so many amazing MCP servers out there to make my work life better, including [Asana](https://github.com/roychri/mcp-server-asana) and [Google Calendar](https://www.pulsemcp.com/servers?q=google+calendar). I added these as Goose extensions, which means Goose can now can pull in my tasks, analyze them, and schedule them, all with one simple prompt:
+There's so many amazing MCP servers out there to make my work life better, including [Asana](https://github.com/roychri/mcp-server-asana) and [Google Calendar](https://www.pulsemcp.com/servers?q=google+calendar). I added these as goose extensions, which means Goose can now can pull in my tasks, analyze them, and schedule them, all with one simple prompt:

 > _**Goose, pull all uncompleted tasks assigned to me in Asana. Group them by type of work to reduce context switching. Estimate how long each task will take. Then, schedule each task accordingly in my Google Calendar.  Make sure not to double book or overload any single day.**_

@@ -264,7 +264,7 @@ This blog post included just a few of the ways I use Goose. If you're curious ab

 What are 5 useful things you can help me with today?

-Let Goose surprise you. ✨
+Let goose surprise you. ✨


 <head>
@@ -7,7 +7,7 @@ authors:

 ![blog cover](bestcodes.png)

-The only way to discover how much of an impact your contributions can make is to submit them and hope for the best. Sometimes, what feels like "just a small fix" can end up reshaping an open source project or inspiring a brand new feature. Here's how one of our top contributors turned a small build fix into important improvements for the Goose experience.
+The only way to discover how much of an impact your contributions can make is to submit them and hope for the best. Sometimes, what feels like "just a small fix" can end up reshaping an open source project or inspiring a brand new feature. Here's how one of our top contributors turned a small build fix into important improvements for the goose experience.

 <!--truncate-->

@@ -1,13 +1,13 @@
 ---
 unlisted: true
 ---
-# Writing Blog Posts for Goose
+# Writing Blog Posts for goose

-This guide explains how to write and structure blog posts for the Goose documentation site.
+This guide explains how to write and structure blog posts for the goose documentation site.

 ## Getting Started

-1. Clone the Goose repository:
+1. Clone the goose repository:
 ```bash
 git clone https://github.com/block/goose.git
 cd goose
@@ -14,35 +14,35 @@ import WindowsDesktopInstallButtons from '@site/src/components/WindowsDesktopIns
 import LinuxDesktopInstallButtons from '@site/src/components/LinuxDesktopInstallButtons';
 import { PanelLeft } from 'lucide-react';

-# Goose in 5 minutes
+# goose in 5 minutes

-Goose is an extensible open source AI agent that enhances your software development by automating coding tasks. 
+goose is an extensible open source AI agent that enhances your software development by automating coding tasks. 

 This quick tutorial will guide you through:

- ✅ Installing Goose
+- ✅ Installing goose
 - ✅ Configuring your LLM
 - ✅ Building a small app
 - ✅ Adding an MCP server

 Let's begin 🚀

-## Install Goose
+## Install goose

 <Tabs>
  <TabItem value="mac" label="macOS" default>
-    Choose to install the Desktop and/or CLI version of Goose:
+    Choose to install the Desktop and/or CLI version of goose:

    <Tabs groupId="interface">
-      <TabItem value="ui" label="Goose Desktop" default>
+      <TabItem value="ui" label="goose Desktop" default>
        <MacDesktopInstallButtons/>
        <div style={{ marginTop: '1rem' }}>
          1. Unzip the downloaded zip file.
-          2. Run the executable file to launch the Goose Desktop application.
+          2. Run the executable file to launch the goose Desktop application.
        </div>
      </TabItem>
-      <TabItem value="cli" label="Goose CLI">
-        Run the following command to install Goose:
+      <TabItem value="cli" label="goose CLI">
+        Run the following command to install goose:

        ```sh
        curl -fsSL https://github.com/block/goose/releases/download/stable/download_cli.sh | bash
@@ -52,22 +52,22 @@ Let's begin 🚀
  </TabItem>

  <TabItem value="linux" label="Linux">
-    Choose to install the Desktop and/or CLI version of Goose:
+    Choose to install the Desktop and/or CLI version of goose:

    <Tabs groupId="interface">
-      <TabItem value="ui" label="Goose Desktop" default>
+      <TabItem value="ui" label="goose Desktop" default>
        <LinuxDesktopInstallButtons/>
        <div style={{ marginTop: '1rem' }}>
          **For Debian/Ubuntu-based distributions:**
          1. Download the DEB file
          2. Navigate to the directory where it is saved in a terminal
          3. Run `sudo dpkg -i (filename).deb`
-          4. Launch Goose from the app menu
+          4. Launch goose from the app menu

        </div>
      </TabItem>
-      <TabItem value="cli" label="Goose CLI">
-        Run the following command to install the Goose CLI on Linux:
+      <TabItem value="cli" label="goose CLI">
+        Run the following command to install the goose CLI on Linux:

        ```sh
        curl -fsSL https://github.com/block/goose/releases/download/stable/download_cli.sh | bash
@@ -77,19 +77,19 @@ Let's begin 🚀
  </TabItem>

  <TabItem value="windows" label="Windows">
-    Choose to install the Desktop and/or CLI version of Goose:
+    Choose to install the Desktop and/or CLI version of goose:

    <Tabs groupId="interface">
-      <TabItem value="ui" label="Goose Desktop" default>
+      <TabItem value="ui" label="goose Desktop" default>
        <WindowsDesktopInstallButtons/>
        <div style={{ marginTop: '1rem' }}>
          1. Unzip the downloaded zip file.
-          2. Run the executable file to launch the Goose Desktop application.
+          2. Run the executable file to launch the goose Desktop application.
        </div>
      </TabItem>
-      <TabItem value="cli" label="Goose CLI">
+      <TabItem value="cli" label="goose CLI">
        
-        Run the following command in **Git Bash**, **MSYS2**, or **PowerShell** to install the Goose CLI natively on Windows:
+        Run the following command in **Git Bash**, **MSYS2**, or **PowerShell** to install the goose CLI natively on Windows:

        ```bash
        curl -fsSL https://github.com/block/goose/releases/download/stable/download_cli.sh | bash
@@ -378,7 +378,7 @@ const config: Config = {
          title: "Quick Links",
          items: [
            {
-              label: "Install Goose",
+              label: "Install goose",
              to: "docs/getting-started/installation",
            },
            {
@@ -460,7 +460,7 @@ const config: Config = {
            },
          },
        ],
-        quickQuestions: ["What is Goose?"],
+        quickQuestions: ["What is goose?"],
      },
    },
    announcementBar: {
@@ -8,13 +8,13 @@ const DesktopInstallButtons = () => {
      <div className="pill-button">
        <Link
          className="button button--primary button--lg"
-          to="https://github.com/block/goose/releases/download/stable/Goose.zip"
+          to="https://github.com/block/goose/releases/download/stable/goose.zip"
        >
          <IconDownload /> macOS Silicon
        </Link>
        <Link
          className="button button--primary button--lg"
-          to="https://github.com/block/goose/releases/download/stable/Goose_intel_mac.zip"
+          to="https://github.com/block/goose/releases/download/stable/goose_intel_mac.zip"
        >
          <IconDownload /> macOS Intel
        </Link>
@@ -8,7 +8,7 @@ const WindowsDesktopInstallButtons = () => {
      <div className="pill-button">
        <Link
          className="button button--primary button--lg"
-          to="https://github.com/block/goose/releases/download/stable/Goose-win32-x64.zip"
+          to="https://github.com/block/goose/releases/download/stable/goose-win32-x64.zip"
        >
          <IconDownload /> Windows
        </Link>