# Frequently Asked Questions

Common questions about CrewWork, how it works, and how it fits into your development workflow.

## General

## What is CrewWork?

CrewWork is a self-hosted development platform for building features, repairing errors, and improving code quality. It connects work requests and findings to autonomous execution, independent validation, and human review. Follow progress, inspect the changes and evidence, and decide what merges.

## Can I use CrewWork today?

CrewWork is unreleased and in active development. Contact team@crewwork.ai to discuss current capabilities, access, licensing, and your deployment needs.

## Is my code safe?

Proposed changes are prepared in isolated workspaces with scoped writes and configurable execution limits. Project fixes land on separate local delivery branches, with push disabled by default. Platform Self-Repair prepares draft pull requests. Review the changes and validation evidence before deciding what merges.

## How does CrewWork handle interrupted work?

Run and queue state is saved in Postgres, with checkpoints supporting recovery after interruptions. Workspace locks coordinate repository writes. Configured time, token, and iteration budgets bound execution; repeated identical failures stop after three consecutive occurrences by default, with the count preserved across restarts.

## What programming languages are supported?

Code intelligence supports Python, JavaScript, TypeScript/TSX, Go, Rust, Java, and C/C++. The code reader, diffs, and logs work with other project languages too. The test engine supports Python, JS/TS, Go, Rust, Ruby, PHP, .NET, JVM projects, and C/C++. Measured coverage is available for Python and JS/TS; support differs by capability.

## Technical

## How are automated repairs triggered?

Automatic error-repair triggers are opt-in and off by default. Set event thresholds, cooldowns, and daily repair budgets per project. Integration health is visible, and a circuit breaker halts ingestion after repeated webhook failures. You can also start work from a specific error or finding.

## What AI models does CrewWork use?

The default generative model is Qwen3.8 27B, used for planning, coding, review, structured extraction, and chat through configured model endpoints. Semantic search uses a separate embedding model. Local hosting is the default; other OpenAI-compatible endpoints can be configured, with public model endpoints requiring explicit opt-in.

## What do I need to self-host?

The application runs as a Docker Compose stack on one host, including its data services, workers, and observability tools. Model-serving hardware is configured separately. The current development setup uses two generative model hosts and runs embeddings alongside one of them; this is not a minimum hardware specification. Plan for model capacity, repository storage, backups, and service administration. The Compare page explains the deployment model.

## Does CrewWork produce compliance or audit evidence?

Projects can generate evidence reports covering scans, quality results, releases, and audit history, organized into PCI DSS-oriented and OWASP ASVS-oriented views. These reports organize evidence and do not certify compliance. Project members with read access can inspect them.

## Can I use CrewWork with Claude Desktop, Cursor, or other AI tools?

CrewMate exposes an MCP server with six read-only tools. External MCP clients can read files, search code, and inspect Git status for a connected project using a scoped API key.

## Workflow

## What counts as completion?

Completion requires admissible evidence from validation the platform ran itself. A model’s own success report cannot satisfy that requirement. Required checks vary with the work and its validation contract; a completed run does not imply that every possible check was run or that every defect has been found.

## What happens if Sentry webhooks fail verification or go stale?

Integration health and failure reasons are surfaced for inspection. Repeated webhook failures trip a circuit breaker, so ingestion stops until the connection is recovered.

## What happens if something goes wrong?

Failed or missing required evidence prevents successful completion. The run records its status and diagnostics, while repair attempts remain bounded by configured limits. Proposed changes stay separate from the target branch so you can inspect what happened before deciding on the next step.

## Still have questions?

Discuss your use case and deployment questions with the team, or read the technical details.

[Discuss your project](https://crewwork.ai/about/#access)

[Read the White Paper](https://crewwork.ai/architecture/white-paper/)

---

Canonical page: https://crewwork.ai/faq/