W Ian Douglas

You've been using goose for weeks, maybe months. You have dozens of successful sessions where you asked for help with blog posts, code reviews, documentation, or data analysis. Each time you think "Didn't I already do this?" but never get around to checking. Sound familiar?

I myself had over a hundred goose sessions and as many megabytes of conversation data. I was sitting on a goldmine of potential automation. A coworker suggested something brilliant: "What if goose could analyze your sessions and build recipes automatically?" Wait, wait, wait!! Create a personalized cookbook based on my own session history? Yes, please! Let's build a "cookbook generator" recipe!

When you're working on complex projects with goose, you'll often need to break work into multiple tasks and run them with AI agents. Goose gives you two powerful ways to do this: subagents and subrecipes. Both can run multiple AI instances in parallel, but they work differently. Picking which one to use can be confusing, so we're going to guide you to a decision.

I've been using both approaches, and the choice between them depends on what you're trying to accomplish. Let me break down when to use each method and show you real examples.

Remember when you first learned to cook? You probably started with simple recipes like scrambled eggs or toast. But eventually you wanted to make something more complex, like a full dinner with multiple dishes. That's how subrecipes work in goose: each recipe can run stand-alone for a dedicated task, and a main recipe can orchestrate how they run.

Let's explore goose subrecipes together! You're about to learn know how to orchestrate multiple AI models, coordinate tasks, and build workflows that will turn you into a "head chef" user with goose.

Remember when people shared recipes by passing handwritten cards between neighbors? You trusted Grandma's apple pie recipe because you knew Grandma. But what happens when strangers start sharing recipes online? You need someone to taste-test them first.

That's exactly the challenge we face with Goose recipes. We're building a community cookbook where you can try Goose recipes from other users with confidence that they're safe. But we needed a way to make sure every recipe was safe to run.

As Goose users, we have two main ways to provide persistent context to our AI assistant: the .goosehints file and the Memory Extension MCP server. Today, I'll share what's in my .goosehints file, why some of it should probably move to the Memory Extension, and how you can make that choice.

I taught Goose how to drive (a rover)​

Goose has no hands, no eyes, and no spatial awareness, but it can drive a rover!

I came across a demo video from Deemkeen, where he used Goose to control a Makeblock mbot2 rover using natural language commands like "drive forward/backward," "beep," and "turn left/right" powered by a Java-based MCP server and MQTT.

Inspired and excited to take it further, I taught the rover to spin, blink colorful lights, and help me take over the world!

Development teams can operate like sports teams. Each member has a role and a shared playbook helps coordinate efforts. Let's explore how AI-driven "plays" can form a starter "playbook" for your dev team, helping with common technical tasks. You can use recipes with Goose to leverage the Model Context Protocol (MCP) to make you more productive.

As developers, we're always looking for ways to build more efficient, scalable, and intelligent applications. For years, RESTful APIs have been our go-to for connecting services. Here are some ways you can integrate AI agents and MCP into your existing API infrastructure to make it smarter, more efficient, and easier to maintain.