Runtime Kit gives AI agents three public moves: read named data, send an action request, and edit things-to-store-and-run.json without importing private implementation code.
What this is
This page is for founders and developers who ask an AI agent to build with Bitfield.An AI agent needs rails. Without rails, it will choose the fastest-looking direct dependency: import unpublished code, parse files in UI code, wire features directly together, or create a second data path. That can work for one screen and punish you later.Runtime Kit gives the agent a better instruction set:The instruction to give your AI agent
Paste this into your AI coding session before asking it to build a Bitfield feature:The public work split
Give an AI agent one of these jobs at a time:This split matters because AI agents are good at adding code quickly. Runtime Kit makes the fast path the safer path.
Good request examples
Ask for one concrete change at a time:Prompt packs
Use these when you want the agent to build one specific Runtime Kit shape.First feature prompt
React read prompt
Target request prompt
Package file prompt
Placeable surface prompt
Troubleshooting prompt
Bad request examples
These requests invite tangled code:The better request names the screen, data name, action name, and files an AI agent may touch.
Bad output and corrected output
Direct package parsing
Wrong shape
Public read
Unpublished Runtime Kit import
Wrong shape
Public import
Missing UI states
Wrong shape
Full render path
Uncontracted reply parsing
Wrong shape
Declared reply shape
Local-state hand edit
Wrong shape
Repair the source
Review checklist for generated code
Before you accept AI output, check these exact things:If any row fails, reject the change and make an AI agent repair that exact file, name, or action first.
Full Runtime Kit review map
Make an AI agent fill this out before you accept the work:If any row is blank, an AI agent has not described the concrete public files and names clearly enough.
What an AI agent should explain back
Ask an AI agent to summarize the chain it used:Common mistakes
Letting an AI agent invent a new public APIIf an AI agent adds a new hook, provider, context, or subscription import, stop it. The current public imports are one request function and one React read hook.Letting an AI agent move package setup into ReactReact renders named data. Package admission belongs in Runtime Kit, not app components.Letting an AI agent make action names too implementation-specificUse stable product names likeproduct.search or welcome.suggest. Do not expose the private runner, file name, or implementation choice in the action name.Letting an AI agent ignore empty and error statesAI often writes the happy path only. Runtime Kit components should render loading, error, empty, and success states every time.