AI AGENTS
On-Call Agent: PagerDuty Incident Triage with Approval-Gated Remediation
When PagerDuty pages, an agent pulls the firing service's Datadog metrics and recent deploys, writes a plain-English diagnosis.
How it runs
The automated pipeline, trigger to output.
- TriggerPagerDuty incident firesPagerDuty
- ActionPull service metrics from DatadogDatadog
- ActionFetch recent deploys and commits from GitHubGitHub
- LogicRank likely causes and map to runbook fixes
- OutputPost diagnosis with approval-gated steps to SlackSlack
What it does
Turns a raw PagerDuty page into a triaged incident brief. The agent gathers signal from Datadog and GitHub, reasons about the likely cause, and proposes concrete fixes — but never acts on its own. A human approves in Slack first.
When to use it
Use it when your on-call rotation gets paged faster than humans can context-switch, and you want the first five minutes of investigation done before anyone opens a laptop. Best for teams that want speed without handing an agent unattended write access to production.
How it works
- 1A PagerDuty incident fires the workflow with the affected service and severity.
- 2The agent queries Datadog for that service's error rate, latency, and saturation over the last hour.
- 3It pulls the service's recent merged commits and deploys from GitHub to spot suspicious changes.
- 4Logic ranks candidate causes and matches each to a runbook remediation (rollback, scale up, restart, feature-flag off).
- 5The agent posts a diagnosis plus an ordered list of proposed steps to the incident's Slack channel, each behind an Approve button — nothing executes until a responder clicks.
Set it up
What you configure once, before turning it on.
- 1Connect PagerDutyIncidents, on-call, escalations.
- 2Connect DatadogMetrics, traces, log search.
- 3Connect GitHubRepos, issues, pull requests, actions.
- 4Connect SlackChannels, DMs, threads, mentions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI Agents workflows
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.

Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.
