On-call incident digests

The on-call handover written by something that was actually awake: every incident, its suspected cause, and the commits that moved - in one digest with links.

Talk to us Read the docs

The brief

Written like you’d brief a person.

This is the whole setup - a procedure in plain language, with tools and specialist agents referenced inline. When it runs is not written here: that’s the trigger, configured beside it.

For every open incident in #yekar.pagerduty.get-incident, pull recent changes with #yekar.github.list-commits, link the affected issues, and post a suspected cause to the on-call channel with #yekar.slack.send-message.

How it runs

From trigger to logged outcome.

Trigger

Schedule - A morning sweep of overnight incidents, before standup

GitHub events can also wake it the moment changes land.

Collect the incidents
Gathers what fired overnight and how it resolved.
Correlate the changes
Pulls the commits and issues that moved in the window.
Suggest a cause
Posts a suspected cause with its evidence - clearly marked as a lead, not a verdict.
Write the handover
One digest, owners named, everything linked.

Where people stay in control

Nothing consequential runs on its own.

The agent never acks, resolves, or reassigns an incident - it reports; people decide.

Tools it uses

Runs on accounts you already have.

PagerDuty
GitHub
Linear
Slack

Connected once, governed per agent - this use case gets only the tools listed here.

Illustrative savings

$800–$2,000 / month

Assumes 30–100 incidents a month and a daily handover that takes an engineer 20–30 minutes.

Illustrative monthly savings, estimated from typical handling time at public salary benchmarks, reviewed August 2026. Not a promise or a guarantee - your numbers depend on volume and process.

What makes this dependable

Operate and improveBring operating risks to the team Put it to workStart agents from connected events Operate and improveTrace every trigger attempt

All use cases →