# Turn recurring engineering work into agent workflows (https://www.shipfox.io/docs)

Description: Shipfox runs your recurring engineering work with coding agents and returns it ready for your team.

A big part of your team's week goes to recurring work: small tickets,
dependency updates, failing checks, alerts, release chores. Coding agents made
each engineer faster, but the work is still manual, one task at a time. And the
more your agents produce, the more piles up for a human to review.

Shipfox turns this work into workflows that start on their own and come back
ready for a human. One opens a pull request, small and with your checks already
passing. One triages dependency updates and merges the safe ones under your
rules. One investigates an alert and suggests a fix. You set the rules: which
model runs each step, what each agent can touch, and where a person signs off.
Only the work that needs judgment reaches your team.

And the factory improves itself. Run workflows that watch your other runs, find
what is slow or failing, and suggest changes.

## Run coding agents like CI pipelines [#run-coding-agents-like-ci-pipelines]

How a Shipfox workflow runs:

1. Triggers: Linear, GitHub, Slack, Jira, Sentry, PostHog, Notion, ClickUp, a schedule, or a webhook start the workflow, from a ticket, a pull request, an alert, a check, or a schedule.
2. Agent workflow: defined in `.shipfox/workflows/implement-issue.yml` and run on an isolated, ephemeral runner.
   - Triage: agent step on GLM 5.3, reads Linear, costs about $0.01.
   - Mark in progress: tool step, writes Linear.
   - Fix issues: agent step on GPT-6 Sol, edits code, costs about $0.12.
   - npm test: run step. If it fails, the workflow goes back to Fix issues.
   - Open PR: agent step on Claude Sonnet, writes GitHub, costs about $0.03.
   - Example run #128 succeeded in 4m 12s, cost about $0.16, and recorded logs, the agent session, and metrics.
3. Your team: The Open PR step sends the result to your team. A comment on it, even days later, resumes the Fix issues step with full context. Your team gets a pull request marked ready, with tests passing, a summary of changes, and a small, focused change ready for review. Other workflows return a diagnosis or a suggested improvement instead.

1. An event starts a workflow. A ticket, a new pull request, an alert, a failed
   check, or a schedule.
2. The workflow does the work. It mixes AI agents with the exact commands you
   choose, in an isolated environment with a full log and the cost of every run
   visible.
3. The result reaches your team. A pull request, a diagnosis, or a suggested
   improvement, ready to approve. Leave a comment and the workflow continues.

Workflows live as YAML in your repo, and you review them like any other code.
Any model per step, any stack. Open source.

Coding agents make each engineer faster. Shipfox gives your whole team a
software factory that builds, checks, and improves itself.

### [Get started with Shipfox](https://app.shipfox.io)

Complete onboarding in Shipfox and start building workflows.

### [Example workflows](https://www.shipfox.io/docs/examples)

See how teams set up recurring work and where people participate.

### [How Shipfox works](https://www.shipfox.io/docs/understand)

Take a closer look at workflows, runs, and integrations.

### [Compare approaches](https://www.shipfox.io/docs/compare-approaches)

See how Shipfox differs from local coding agents, agent automations, and CI platforms.