CHATBOTS

On-Call Handoff Digest at Rotation Boundary

When a PagerDuty on-call rotation changes hands, this bot assembles every open incident, active alert, and unresolved Slack thread into a single handoff digest and posts it…

CategoryChatbots
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerPagerDuty on-call handoff eventPagerDutyPagerDuty
  • ActionFetch open + acknowledged incidentsPagerDutyPagerDuty
  • ActionQuery firing Datadog monitors for owned servicesDatadogDatadog
  • ActionScan channel for unresolved threadsSlack
  • LogicBranch on whether anything is open vs clean handoff
  • OutputPost handoff digest to incoming on-callSlack

What it does

At the moment a PagerDuty schedule rotates, this bot gathers the full operational state the outgoing engineer was holding and hands it to the incoming one. No more 'so, anything I should know?' over a hurried Slack DM. The digest lists open incidents with current status, firing Datadog monitors, and any Slack threads still waiting on a human reply.

When to use it

Run this on any team with a recurring on-call rotation where context regularly gets dropped at handoff. It is most valuable for teams whose pages span multiple services and where a single Slack channel accumulates half-finished investigation threads.

How it works

  1. 1PagerDuty fires its `on_call_handoff` event when the schedule boundary is reached.
  2. 2The bot pulls all open and acknowledged incidents for the affected escalation policy from PagerDuty.
  3. 3It queries Datadog for monitors currently in Alert or Warn state on the owned services.
  4. 4It scans the incident channel for threads with no reply in the last interval, flagging them as unresolved.
  5. 5A branch checks whether anything is actually open; if all clear, it posts a short 'clean handoff' note instead.
  6. 6The assembled digest is delivered as a direct message and channel post to the incoming on-call engineer.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect PagerDutyIncidents, on-call, escalations.
  2. 2
    Connect DatadogMetrics, traces, log search.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.