Prerequisites
Before searching docs, check if node_modules/ai/docs/ exists. If it is absent, inspect the project package manager and state the exact dependency change. Install ai only when the user's request already authorizes dependency changes or after explicit confirmation.
Do not install other packages at this stage. Provider packages (e.g., @ai-sdk/openai) and client packages (e.g., @ai-sdk/react) should be installed later when needed based on user requirements.
Critical: Do Not Trust Internal Knowledge
Everything you know about the AI SDK is outdated or wrong. Your training data contains obsolete APIs, deprecated patterns, and incorrect usage.
When working with the AI SDK:
- Inspect the installed
aiversion and local docs first; add the package only under the prerequisite rule above - Search
node_modules/ai/docs/andnode_modules/ai/src/for current APIs - If not found locally, search ai-sdk.dev documentation (instructions below)
- Never rely on memory - always verify against source code or docs
useChathas changed significantly - check Common Errors before writing client code- Preserve the provider already used by the project. If none is configured, ask for requirements or present provider-neutral options; do not default to a gateway or vendor. Use AI Gateway Reference only when the project or user chooses Vercel AI Gateway.
- Verify model IDs at implementation time. Read the installed provider package docs, the configured provider catalog, or current official provider documentation. Never infer freshness from a larger-looking version number and never change providers merely to obtain a newer model.
- Run typecheck after changes to ensure code is correct
- Be minimal - Only specify options that differ from defaults. When unsure of defaults, check docs or source rather than guessing or over-specifying.
If you cannot find documentation to support your answer, state that explicitly.
Finding Documentation
Installed package
Search bundled docs and source in node_modules/ai/:
- Docs:
grep "query" node_modules/ai/docs/ - Source:
grep "query" node_modules/ai/src/
Provider packages include docs at node_modules/@ai-sdk/<provider>/docs/.
When local documentation is unavailable
- Search:
https://ai-sdk.dev/api/search-docs?q=your_query - Fetch
.mdURLs from results (e.g.,https://ai-sdk.dev/docs/agents/building-agents.md)
When Typecheck Fails
Before searching source code, grep Common Errors for the failing property or function name. Many type errors are caused by deprecated APIs documented there.
If not found in common-errors.md:
- Search
node_modules/ai/src/andnode_modules/ai/docs/ - Search ai-sdk.dev (for earlier versions or if not found locally)
Building and Consuming Agents
Creating Agents
Use the agent API documented by the installed package. Use ToolLoopAgent only when that symbol exists in the installed version and matches the task; otherwise follow the current documented agent or generateText/streamText pattern.
File conventions: See type-safe-agents.md for where to save agents and tools.
Type Safety: When consuming agents with useChat, always use InferAgentUIMessage<typeof agent> for type-safe tool results. See reference.
Consuming Agents (Framework-Specific)
Before implementing agent consumption:
- Check
package.jsonto detect the project's framework/stack - Search documentation for the framework's quickstart guide
- Follow the framework-specific patterns for streaming, API routes, and client integration
References
- Common Errors - Renamed parameters reference (parameters → inputSchema, etc.)
- AI Gateway - Optional gateway setup when explicitly selected
- Type-Safe Agents with useChat - End-to-end type safety with InferAgentUIMessage
- DevTools - Set up local debugging and observability (development only)