CHATBOTS

Teams 'Who Owns This Service?' Bot

An MS Teams bot that answers 'who owns service X' by reading the service catalog and the most recent commits, then replying in-channel with the owner, team, and last contributor.

CategoryChatbots
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerTeams message mentions the bot with a service nameMicrosoft Teams
  • ActionLook up the service in the Postgres catalogPostgreSQLPostgres
  • LogicBranch: catalog hit vs. no match
  • ActionFetch the repo's 5 most recent commitsGitHubGitHub
  • OutputReply in the Teams thread with owner, team, and last committerMicrosoft Teams

What it does

When a teammate types a question like 'who owns the billing-api' in a Teams channel, this bot looks up the named service in your Postgres service catalog and cross-checks the most recent GitHub commits to that repo. It replies with the registered owner, the owning team, the on-call alias, and the person who last touched the code.

When to use it

Use it when engineers waste time pinging the wrong people about a service during incidents or change requests. It turns tribal knowledge into a one-message lookup, right where people already work.

How it works

  1. 1A Teams message mentioning the bot triggers the flow and the service name is extracted from the text.
  2. 2The catalog query runs against Postgres to find the matching service row (owner, team, on-call).
  3. 3If no row matches, the bot replies asking the user to check the spelling or register the service.
  4. 4The GitHub step pulls the last 5 commits to the mapped repo to identify the most recent contributor.
  5. 5The bot posts a formatted reply in the same Teams thread with owner, team, on-call alias, and last committer.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Microsoft TeamsChannels, chats, files.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Connect GitHubRepos, issues, pull requests, actions.
  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.