CHATBOTS
Teams Owner Bot with Confluence Runbook Context
An agent-driven Teams bot that answers ownership and 'how do I reach the owner' questions by combining the Postgres catalog, recent commits, and the service's Confluence runbook…
How it runs
The automated pipeline, trigger to output.
- TriggerTeams mention with a free-form ownership questionMicrosoft Teams
- ActionQuery Postgres catalog for owner and teamPostgres
- ActionPull recent commits to confirm active maintainersGitHub
- ActionSearch Confluence for the service runbookConfluence
- LogicAgent reasons over sources to compose the answer
- OutputReply in Teams with owner, escalation, and runbook linkMicrosoft Teams
What it does
This is a smarter ownership assistant. When someone asks about a service in Teams, an agent gathers three sources: the owner record from the Postgres catalog, the recent commit history from GitHub, and the service's runbook page from Confluence. It then composes a natural-language answer covering who owns it, how to escalate, and where the docs live.
When to use it
Use it when 'who owns this' questions usually become follow-ups like 'what's their escalation path' or 'where's the runbook'. The agent answers the whole chain in one pass instead of three separate lookups.
How it works
- 1A Teams mention triggers the agent with the user's free-form question.
- 2The agent resolves the service name and queries the Postgres catalog for the owner and team.
- 3It pulls recent GitHub commits to confirm active maintainers.
- 4It searches Confluence for the service's runbook and escalation section.
- 5The agent reasons over all three sources, deciding what the user actually needs.
- 6It replies in the Teams thread with the owner, escalation path, and a runbook link.
Set it up
What you configure once, before turning it on.
- 1Connect Microsoft TeamsChannels, chats, files.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 3Connect GitHubRepos, issues, pull requests, actions.
- 4Connect ConfluenceSpaces, pages, blueprints.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Chatbots workflows
Discord Onboarding Completion to CRM Sync
The moment a member finishes Discord onboarding, captures their submitted profile answers, creates or updates a contact in HubSpot.
Discord FAQ-Gated Role Concierge
Greets each new Discord member in a private onboarding thread, walks them through required FAQ steps one at a time.
Discord FAQ Free-Text Answer Grader
When a member submits a free-text answer in their onboarding thread, an agent grades it against the canonical FAQ knowledge base, replies with targeted feedback.
Discord verify-button onboarding via web form webhook
Receives a completed external verification form by webhook, matches it to the Discord account, grants the verified role, and confirms back to the member in Discord.
Discord intro-gated role granting concierge
Watches your #introductions channel, uses AI to confirm a new member's intro is genuine and complete, then auto-assigns the verified Member role and welcomes them.
Daily Discord Digest of Repeated WAF False-Positive Reports
Each morning, scans logged Discord WAF reports in Postgres, groups them by the Cloudflare rule that keeps firing.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.