Recipes

The configuration chapters say what every field does. These recipes show how the pieces fit together in a real service — each one is a pattern running in production in Kaboo, written so you can lift it into your own project.

Recipe	Reach for it when
Serve on AgentCore in production	You deploy behind AWS AgentCore Runtime, or any host with response caps and idle reaping
Compose a workflow per run	One service runs many workflows — per tenant, per project, per admin-authored row
Skills	Agents need reusable instructions, loaded only when a task calls for them
Call MCP tools as the signed-in user	Tools behind a gateway must act with the caller's permissions
Tools that need run context	A tool keeps state per conversation or must act once per turn
Guard hooks for every agent	Runs should survive malformed transcripts, retry loops and expired sign-ins
Ask the user, and request inputs	An agent needs an answer, a file or a data source mid-run
Shared state	The person and every agent should see what the conversation built, without looking it up
Generative UI from any agent	Answers should come as surfaces, visuals or partner apps in the chat
Structured outputs a UI can render	An agent's result should arrive as typed data for a card, not prose
Images and file attachments	Users attach files, or tools return images
Sub-agents in a chat UI	Users should see which agent is working on what, in words
Cost and context control	Long, tool-heavy runs cost too much or outgrow the context window

Testing your workflows covers proving any of these with a scripted model, and Best practices collects the rules of thumb behind them.