crewaiinc

CrewAI architecture decisions and project scaffolding. Use when starting a new crewAI project, choosing between LLM.call() vs Agent.kickoff() vs Crew.kickoff() vs Flow, scaffolding with 'crewai create flow', setting up YAML config (agents.yaml, tasks.yaml), wiring @CrewBase crew.py, writing Flow main.py with @start/@listen, building experimental conversational Flows with handleturn()/chat(), or using {variable} interpolation.

CrewAI agent design and configuration. Use when creating, configuring, or debugging crewAI agents — choosing role/goal/backstory, selecting LLMs, assigning tools, tuning maxiter/maxrpm/maxexecutiontime, enabling planning/delegation, setting up knowledge sources, using guardrails, or configuring agents in YAML vs code.

Query the official CrewAI documentation for answers. Use when the user has a CrewAI question that isn't fully covered by the getting-started, design-agent, design-task skills — e.g., specific API details, configuration options, advanced features, troubleshooting errors, enterprise features, tool references, or anything where the latest docs are the best source of truth.

CrewAI task design and configuration. Use when creating, configuring, or debugging crewAI tasks — writing descriptions and expectedoutput, setting up task dependencies with context, configuring output formats (outputpydantic, outputjson, outputfile), using guardrails for validation, enabling humaninput, async execution, markdown formatting, or debugging task execution issues.

Building CrewAI Flows on crewai 1.15.x: structured (Pydantic) vs dict state and state.id, @start/@listen/@router wiring, or/and semantics, router labels vs method names, @persist (correct import, where it stores state, restorefromstateid), checkpointing with CheckpointConfig, @humanfeedback and HumanFeedbackResult.feedback, plot(), calling crews and agents from flow methods, kickoff inputs, and the crewai create flow scaffold. Use when writing or debugging a Flow subclass or main.py with from crewai.flow import ..., when a listener never fires or fires twice, or when you see errors like "listen condition 'x' references the handler name 'x'", "cannot import name 'persist'", "'StateWithId' object is not subscriptable", "Flow state model must have an 'id' field", "--inputs requires a declarative flow definition", "invoked synchronously from within a running event loop", or HumanFeedbackCollapseError.

Current crewai 1.15.x API versus the 0.x API that coding assistants remember: imports, Agent/Task/Crew parameters and defaults, kickoff variants, CrewOutput fields, LLM model strings and provider extras, structured output (outputpydantic, responsemodel, responseformat), guardrails, unified Memory, knowledge embedders, the crewai create crew wizard vs --classic, reset-memories flags, and removed features. Use when writing, reviewing, or debugging any crewai code, before trusting remembered crewai syntax, or when a user pastes errors like cannot import name 'BaseTool' from 'crewaitools', cannot import name 'persist', ShortTermMemory, Anthropic native provider not available, LiteLLM fallback package is not installed, got an unexpected keyword argument 'responseformat', OPENAIAPIKEY is required, If return type is annotated, it must be Tuple[bool, Any], or result.pydantic is None.

Giving crewAI agents tools and MCP servers on crewai 1.15.x: custom BaseTool with argsschema and @tool, which crewaitools names really exist, tool caching, maxusagecount, ToolFailure, Agent(mcps=[...]) string and MCPServerStdio/HTTP/SSE forms, rewritten MCP tool names, MCPServerAdapter, timeouts, and what works on a hosted deployment. Use when writing or debugging a tool or MCP connection, when you see 'cannot import name BaseTool from crewaitools', 'You are missing the mcp package', 'MCPConnectionError', 'Operation timed out after 30 seconds', 'reached its usage limit', 'Invalid MCP reference', 'Anthropic function name ... must start with a letter', an agent that never calls an MCP tool, mcps=[...] that yields no tools (for example an https:// string under akickoff or on CrewAI AMP), or a stdio MCP server that works locally but not after deploy.

Deterministic, offline testing of CrewAI crews and flows with pytest: a stub BaseLLM (shipped in references/stubllm.py) that drives text, structured output and tool calls with no API key, asserting on the prompts crewai built, testing guardrails and flow routing, what crewai test really does, event listeners for debugging, and the exact tracing/telemetry env var values. Use when writing tests for a crewai project, mocking or stubbing the LLM, writing a custom BaseLLM, seeing TypeError: ... call() got an unexpected keyword argument 'fromtask', ValueError: OPENAIAPIKEY is required in CI, TraceGrantError in pytest, running crewai test, adding a BaseEventListener, or setting CREWAITRACINGENABLED / CREWAIDISABLETELEMETRY / OTELSDKDISABLED.

Calling a crew or flow deployed on CrewAI AMP over HTTP: the bearer token and deployment URL, GET /inputs, POST /kickoff with the {"inputs": {...}} body, which input keys are required ({placeholder} tokens), polling GET /status/{kickoffid} with a deadline and backoff, terminal states and where the result lives, webhooks, POST /resume, slow first calls, and writing crews that stay correct when they are kicked off repeatedly or concurrently. Use when writing a client, script, backend or frontend that calls a deployed crew, when a kickoff returns 422 "Missing inputs: ...", when a status poll never ends, says "NOT FOUND" or the result field is empty, when /resume returns 422 for executionId, when a run's prompt shows another run's data, or when the user pastes a kickoffid, a /kickoff curl, or 'Template variable ... not found in inputs dictionary'.

Getting a CrewAI crew or flow onto CrewAI AMP: the project shape the build expects (uv.lock, [tool.crewai] type, src/ / entry points, a real Flow subclass, absolute imports, a self-contained root), crewai deploy validate, the three deploy paths (CLI create/push, GitHub, ZIP upload) and what each one actually uploads, env vars per deployment and what the CLI re-sends from .env, provider keys and extras, and machine-wide org selection. Use when running crewai deploy create / crewai deploy push / crewai deploy validate, when a deploy says Online but runs old code, old env values or lost a key, or when pasting errors like missinglockfile, Crew class annotated with @CrewBase not found, No Flow subclass found, Expected to find at least one of these files: uv.lock or poetry.lock, OPENAIAPIKEY is required, Anthropic native provider not available, deploymentnotfound, gitclonefailure, Automation error, fix the code and deploy again, or pyproject.toml not fou