CHATBOTS

Ask-the-Handoff Bot for Current On-Call State

An on-demand chat bot the incoming engineer messages with questions like 'what's still open?'.

CategoryChatbots
Enginepaperclip
Difficultyadvanced
Triggerchat
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerEngineer messages the bot in SlackSlack
  • LogicInterpret question; choose systems and filters
  • ActionQuery PagerDuty for matching open incidentsPagerDutyPagerDuty
  • ActionQuery Datadog monitor state when relevantDatadogDatadog
  • ActionCompose grounded plain-language answerOpenAI
  • OutputReply in the Slack thread with verifying linksSlack

What it does

Instead of pushing a digest on a timer, this bot answers the incoming engineer's questions whenever they ask. They message it in Slack — 'what incidents are still open?', 'anything firing on the payments service?' — and it queries PagerDuty and Datadog in real time and replies with a concise, current answer. It is the conversational counterpart to a scheduled handoff.

When to use it

Use this when engineers prefer to pull context on demand rather than receive a fixed briefing, or as a companion to a scheduled digest so they can drill into specifics mid-shift without opening four dashboards.

How it works

  1. 1The engineer sends a message to the bot in Slack, which triggers the flow as a chat request.
  2. 2The agent interprets the question to decide which systems to query and with what filters.
  3. 3It calls PagerDuty for open or acknowledged incidents matching the asked-about service or scope.
  4. 4It calls Datadog for the current state of relevant monitors when the question concerns alerts.
  5. 5The agent composes a plain-language answer grounded only in the live data it retrieved.
  6. 6It replies in the same Slack thread, with links so the engineer can verify or dig deeper.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect SlackChannels, DMs, threads, mentions.
  2. 2
    Connect PagerDutyIncidents, on-call, escalations.
  3. 3
    Connect DatadogMetrics, traces, log search.
  4. 4
    Connect OpenAIModels, embeddings, files.
  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.