CHATBOTS

Error-Budget Brief for the Incoming On-Call

At rotation boundary, this bot pairs unresolved Sentry issues with PagerDuty incident history to brief the incoming engineer on which services are burning error budget and most…

CategoryChatbots
Enginesim
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerPagerDuty handoff eventPagerDutyPagerDuty
  • ActionPull unresolved Sentry issues by volumeSentrySentry
  • ActionFetch trailing page count per servicePagerDutyPagerDuty
  • LogicJoin sources; score paging likelihood into tiers
  • OutputPost risk brief with Sentry deep links to SlackSlack

What it does

This bot gives the incoming on-call a risk-forward briefing instead of a backward-looking incident dump. It correlates unresolved Sentry issues with recent PagerDuty page frequency to surface which services are degrading and likely to alert during the upcoming shift, so the engineer knows where to keep an eye before anything pages.

When to use it

Use this when your team wants handoffs to be predictive rather than reactive — especially when certain services have been flaky and you want the next engineer primed on the highest-risk areas rather than reading raw alert lists.

How it works

  1. 1PagerDuty fires the on-call handoff event at the rotation boundary.
  2. 2The bot pulls unresolved Sentry issues ranked by event volume and regression status.
  3. 3It fetches the trailing page count per service from PagerDuty incident history.
  4. 4A logic step joins the two sources and scores each service's likelihood of paging this shift.
  5. 5Services are sorted into a 'watch closely' tier and an 'informational' tier.
  6. 6The risk brief is posted to the incoming engineer in Slack with deep links to each Sentry issue.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect PagerDutyIncidents, on-call, escalations.
  2. 2
    Connect SentryErrors, performance, releases.
  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.