Incident command
The timeline built live from alerts, deploys and chat, the right people paged, and a postmortem drafted when it is over.
Chat
Connected apps.
Connect each one once. You sign in on the app's own screen, and you can disconnect any time.
PagerDuty
Datadog
Sentry
GitHub
Slack
Notion
An example run.
What the agent does, step by step, after you ask. This is an illustration; your results depend on your own data.
Incident command
pagerduty.get_incidentOpened at 02:14: checkout error rate above 5 percentDonedatadog.query_metricsErrors began at 02:10, latency doubled at 02:12Donegithub.list_deploysA deploy of the payments service went out at 02:08Donesentry.list_issuesNew error: timeout calling the card processorDoneslack.create_channelIncident channel opened with the contextWaits for youpagerduty.page_userPayments on-call and the incident lead pagedWaits for younotion.create_pagePostmortem drafted with the timeline, ready to editDone
You stay in control.
Looking things up is automatic. Anything that changes something waits for you, and every step is logged.
Runs on its own
- Opened at 02:14: checkout error rate above 5 percent
- Errors began at 02:10, latency doubled at 02:12
- A deploy of the payments service went out at 02:08
- New error: timeout calling the card processor
- Postmortem drafted with the timeline, ready to edit
Waits for your approval
- Incident channel opened with the context
- Payments on-call and the incident lead paged
How it works.
Connect your apps
PagerDuty, Datadog, Sentry, GitHub, Slack, Notion. Setu keeps the sign-in secure and never shows your passwords to the agent.
Ask, or set a trigger
Run it when an incident opens. You describe the job in your own words.
You stay in control
Reading is quick. Anything that writes or deletes can wait for your approval, and every step is logged.
More for engineering.
-
Engineering
Triage pull requests
“Triage the new pull requests.”
Each pull request labelled, linked to its ticket, checked against recent errors and sent to the right reviewer.
When a pull request opens
-
Engineering
Weekly engineering summary
“Summarise what shipped this week, what slipped and why.”
A readable summary for people who weren't in the standup, with risks and what's next, drawn from code, tickets and incidents.
Every Friday at 16:00
-
Engineering
Fix vulnerable dependencies
“Deal with this week's dependency security alerts.”
Alerts reviewed, the real risks separated out, fixes opened as pull requests and tickets created for the rest.
Every Tuesday at 9:00
Give your agent real hands.
Connect an app, hand your agent the tools, and watch it finish the job.