CHATBOTS

New-Hire Onboarding HR Concierge over Confluence

When a new hire joins, an agent-driven concierge in Teams proactively walks them through key HR policies from Confluence, answers their questions in context.

CategoryChatbots
Enginepaperclip
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew hire added event fires
  • ActionPull designated onboarding pages from ConfluenceConfluenceConfluence
  • ActionWalk the new hire through each policy in Teams chatMicrosoft Teams
  • LogicRecord acknowledgement and decide advance or re-explain
  • OutputLog acknowledgements and notify HR on completionPostgreSQLPostgres

What it does

Gives every new hire a guided HR onboarding chat instead of a wall of links. The concierge introduces the must-read policies from your Confluence HR space one at a time in Teams, answers follow-up questions grounded in those pages, and records acknowledgements so HR has a compliance trail.

When to use it

During onboarding, when you need new employees to actually read and confirm core policies (code of conduct, security, leave, expenses) rather than skimming a folder. Best when onboarding volume makes manual walkthroughs impractical.

How it works

  1. 1A new-hire-added event triggers the onboarding flow.
  2. 2The agent pulls the designated onboarding policy pages from the Confluence HR space.
  3. 3It opens a Teams conversation and presents each policy in turn, answering questions using only the page content.
  4. 4After each policy, a logic step records the new hire's acknowledgement and decides whether to advance or re-explain.
  5. 5Each acknowledgement is written to a Postgres onboarding table, and a completion summary is delivered to HR when all policies are covered.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect ConfluenceSpaces, pages, blueprints.
  2. 2
    Connect Microsoft TeamsChannels, chats, files.
  3. 3
    Connect PostgresAny Postgres URL — query, write, migrate.
  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.