Skip to main content

For coding agents: the Studio guide

Synced from bicycle-studio-api

This index and the chapters below are generated by yarn sync:studio from origin/platform at 1afd83f, synced 2026-09-28. Do not edit them here; change the source and run the sync again.

These pages are the exact texts Bicycle Studio serves to coding agents: the studio_guide MCP tool returns them as the landing guide, and GET /api/studio/v1/guide returns the same text over HTTP. They are synced from the Studio repository, not edited here, so what you read on this site is what an agent connected to the Studio MCP reads.

Read Working with the person first, then the chapters in order. Each chapter is one studio_guide(topic) answer; the parts produced from code (the manifest fields, the bda.fn SDK, the function handler reference) are inside the chapter that uses them.

ChapterWhat it covers
Working with the personHow to work with the person: questions first, confirmed numbers, person-only steps.
Start here: building on Bicycle StudioWhat to build, the order of work, the rules.
Connecting to the Studio MCPURLs, OAuth vs token, scopes, and why some tools may be missing.
Data appsCompose vs hand-build, bda.manifest.json, bda.fn, upload and publish.
Functions: a guide for coding agentsKinds, function.json, tests and fixtures, the code sandbox, calling a function.
AgentsAgent functions: the spec, connections, limits, the queue.
WorkflowsThe create, try and publish loop, steps, sends, triggers, calling by ref.
Runs: invocations and tracesOne inv_ record per run: status, events, trace, debugging.
Detect and Explain: a guide for coding agentsWhat changed, and why: Detect and Explain on an app's model.
Limits and person-only stepsEvery step only a person may take, and the limits.
Porting a data story or notebook into a workflowPorting a notebook into a workflow: what maps to which step.
Example: a KPI function and a hand-built app that shows itA KPI code function and a hand-built app that shows it.
Example: an Ask AI function that summarises a small tableAn llm function that summarises a table.
Example: a classify function that sorts support ticketsA classify function that sorts tickets.
Example: an agent function, and the code function it will callAn agent function with one function tool.
Example: weekly bookings digest by emailA weekly workflow whose email a person approves.
Example: train a model, then predict with itTrain, then predict, with workflow blobs.
Example: a backtest mapped over originsA backtest mapped over partitions.
Example: hand a publish to a personA token builds an app version; a person publishes it.