> ## Documentation Index
> Fetch the complete documentation index at: https://docs.crewship.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# When not to use Crewship

> Recognize the jobs Crewship is not designed for, including low-latency services, unreviewed production changes, and work with missing context or credentials.

# When not to use Crewship

Crewship is an orchestration and governance layer for bounded agent work. It is a poor fit when the orchestration cost or uncertainty is greater than the task.

| If your requirement sounds like…                                                 | Prefer this instead                                                                  | Why Crewship is the wrong first tool                                                                            |
| -------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------- |
| “Return a fraud decision inside the request's tail-latency budget.”              | A conventional service with a deterministic model and an explicit SLO.               | Crewship runs are asynchronous; model, container, and approval latency are variable.                            |
| “Reformat every row in this ten-million-row table exactly the same way.”         | A SQL/data pipeline or a one-off program with a checkpointed batch.                  | An agent adds token cost and variance where there is no judgment to supply.                                     |
| “Push this production migration automatically and roll it back if health drops.” | A deployment system with tested rollout and rollback semantics.                      | Crewship can prepare a change and pause at a waitpoint, but it is not your production controller.               |
| “Review this repository, but the crew cannot read the repository or its tests.”  | Grant the workspace or attach the repository first, then reassess.                   | A better prompt cannot create missing files, permissions, acceptance criteria, or domain context.               |
| “Give the agent our regulated customer export because it might help.”            | Keep the data in the approved system and use a purpose-built, audited integration.   | Credential injection governs delivery; it does not make an unapproved data boundary acceptable.                 |
| “Keep an autonomous process alive forever and let it decide what to do next.”    | An event-driven service or scheduler with explicit state transitions and owners.     | Crewship is queue-and-trigger based; routines finish, fail, or pause at durable waitpoints.                     |
| “Have the agent change a security chokepoint without a test or reviewer.”        | A controlled engineering change with red-test-first review and protected deployment. | Crewship can coordinate the work, but an agent run is not evidence that a security-sensitive change is correct. |

Two product examples make the boundary concrete:

* A dependency-upgrade routine is a good fit when it opens a bounded issue, runs the repository checks, and stops for a major-version decision. It is a poor fit when you want it to merge arbitrary upgrades directly to production with no branch protection.
* A credential-aware integration task is a good fit when the agent needs a narrowly assigned token for one run and a human can approve escalation. It is a poor fit when the requirement is to copy a long-lived secret into chat history or a shared repository.

Use Crewship when an agent can make progress in a bounded workspace, the outcome can be checked, and a human or policy can own the decision when the work crosses a trust boundary. Start with [First projects](/guides/first-projects) and stop after the rung that proves your use case.