CHATBOTS

PagerDuty Incident Explainer for Datadog Alerts

When a Datadog alert escalates into a PagerDuty incident, the bot DMs the assigned responder a plain-English explanation of the firing monitor plus the dashboards and deploys…

CategoryChatbots
Enginepaperclip
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerPagerDuty incident assigned to responderPagerDutyPagerDuty
  • ActionFetch monitor query, state, and dashboardsDatadogDatadog
  • ActionPull recent deploys and commit historyGitHubGitHub
  • LogicAdjust brief depth by incident severity
  • OutputDM the assigned responder the incident briefSlack

What it does

Bridges the gap between a paged incident and understanding it. When PagerDuty assigns a Datadog-sourced incident to a responder, this workflow proactively messages that person with everything they need to start investigating, before they even open a laptop.

When to use it

Use it for high-severity rotations where the assigned engineer may be woken up and needs instant orientation. Ideal when Datadog feeds PagerDuty and you want the responder briefed the second they are paged.

How it works

A PagerDuty incident-triggered event starts the flow with the linked Datadog monitor reference. The workflow pulls the monitor query, state, and linked dashboards from Datadog, then fetches recent deploys and the on-call-relevant commit history from GitHub. A logic step checks severity to decide how much detail to include. The agent composes a tailored brief and delivers it as a Slack direct message to the assigned responder, with monitor summary, dashboard links, suspected deploys, and a suggested first check.

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 GitHubRepos, issues, pull requests, actions.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    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.