Step 1
Route your alerts to SHIP
Connect the error tracker or the alert channel your team already watches. Choose which alerts open a mission and which only get a note.
Incident response
Early accessTurn a production alert into a tested pull request
When an alert fires, SHIP reads the error, finds the cause in your code and proposes a fix. The fix arrives as a pull request that passed your CI and a test.
- For
- Engineers on call for a production web app.
- Instead of
- Reading a stack trace in the middle of the night to find the line that broke.
Runs today: When an alert opens an issue in Linear, assign it to SHIP, or comment @SHIP on it in GitHub Issues, and get the fix back as a pull request.
Answer 4 questions. SHIP emails you when it opens to you.
How it works
Connect your alerts once, then read fixes
Step 2
Read the investigation first
The agent reads the stack trace, the recent changes and the code around them, and writes up the cause it found on the issue. With a checkpoint on, the mission waits for your approval before any code changes.
Step 3
Approve the fix
The fix lands as a pull request that passed your CI, a code review and a test on a preview your own pipeline deploys. Nothing reaches production until someone on your team merges it.
Capabilities
Keep a person in charge of production
Hold the mission before any code changes
A checkpoint stops the mission after the investigation, so someone approves the approach before the Builder starts.
Test the fix on a preview
The Tester exercises the failing path on a preview your own pipeline deploys and attaches the browser trace as proof.
Run on your own models and keys
Every agent runs on the credentials you connect, and your provider bills inference at your own rates.
See what every incident cost
Each mission reports what it cost and how long it took, priced on the model that served it.
Comparison
Compare SHIP with Devin and Factory
| Factory |
|
|---|---|
| Devin |
|
| SHIP | In early access
|
FAQ
Frequently asked questions
Is alert-driven incident response available today?
Not yet: reading alerts straight from an error tracker or alert channel is in early access. Today, when an alert opens an issue in Linear, assign it to SHIP, or comment @SHIP on it in GitHub Issues, and the agents investigate and return the fix as a pull request.
Does SHIP deploy the fix to production?
No, SHIP does not deploy to production. The fix waits as a pull request until someone on your team merges it, and your own pipeline deploys it from there. Auto-merge stays off unless you turn it on.
When is Devin or Factory the better fit?
Factory fits a team that wants Sentry, Datadog or PagerDuty alerts investigated as they fire today, through the Alert Responder its automations page describes. Devin fits a team that wants alerts and backlog items triaged and categorized with suggested approaches. SHIP fits when every fix should arrive as a pull request that passed your CI, a code review and a test, on the harness and model you choose.
What does it cost to hand SHIP an alert?
Each alert issue you hand over is one mission: one credit covers up to 3 agent-hours, and each further 3 agent-hours or part of them uses one more. Credits come back when a mission ends in failure or needs attention with no pull request, and your own provider bills model usage.
Start answering alerts with pull requests
Join the early-access list, and assign alert issues to SHIP in the meantime.
Join the early-access list
Answer 4 questions. SHIP emails you when it opens to you.