CHATBOTS

Service Health Q&A Bot for Microsoft Teams

A Microsoft Teams bot that answers "what's broken right now?" by summarizing all currently-alerting Datadog monitors grouped by service into a readable adaptive reply.

CategoryChatbots
Enginepaperclip
Difficultyintermediate
Triggerchat
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerUser @-mentions bot in Teams with status questionMicrosoft Teams
  • ActionFetch all non-OK Datadog monitorsDatadogDatadog
  • LogicGroup by service, all-clear short-circuit
  • ActionCompose grouped health summaryOpenAI
  • OutputPost summary card to Teams threadMicrosoft Teams

What it does

Responds to broad health questions in Microsoft Teams like "what's down?" or "any active incidents?" by pulling every Datadog monitor currently in Alert or Warn and summarizing them grouped by service, so a manager or stakeholder gets the full blast radius in one message.

When to use it

When non-engineers (support leads, execs, customer success) need a quick read on overall platform health without learning Datadog. Useful in a shared ops or leadership Teams channel during a noisy day.

How it works

  1. 1A user @-mentions the bot in Teams with a status question.
  2. 2The flow fetches all monitors in non-OK states from the Datadog API.
  3. 3A logic step groups them by `service` tag and counts alert vs warn severity per group.
  4. 4If nothing is alerting, it short-circuits to an all-clear message.
  5. 5Otherwise it composes a grouped summary (service, count, worst severity, oldest active alert).
  6. 6The bot posts the adaptive summary card back to the Teams thread.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Microsoft TeamsChannels, chats, files.
  2. 2
    Connect DatadogMetrics, traces, log search.
  3. 3
    Connect OpenAIModels, embeddings, files.
  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.