CHATBOTS

HR Policy Q&A Assistant in Microsoft Teams (Confluence-grounded)

Answers employee HR questions inside Microsoft Teams by retrieving the relevant Confluence policy pages and replying with a grounded, cited answer.

CategoryChatbots
Enginesim
Difficultyintermediate
Triggerchat
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerEmployee asks a question in Microsoft TeamsMicrosoft Teams
  • ActionSearch Confluence HR space for relevant policy pagesConfluenceConfluence
  • LogicCheck that retrieved pages actually cover the question
  • ActionGenerate grounded answer with citations via OpenAIOpenAI
  • OutputReply in the Teams thread with answer and source linksMicrosoft Teams

What it does

Gives employees a self-serve HR helpdesk in Microsoft Teams. When someone DMs or @mentions the bot with a policy question (PTO, parental leave, expense limits, remote-work rules), it searches your Confluence HR space, pulls the most relevant pages, and answers in plain language with citations linking to the exact policy page.

When to use it

When HR spends hours each week answering the same handbook questions, and employees can't find answers buried in Confluence. Best for companies that already keep their policies current in a Confluence HR space.

How it works

  1. 1An employee message in Teams triggers the workflow.
  2. 2The question is searched against your Confluence HR space to find matching policy pages.
  3. 3The top page bodies are passed to OpenAI with a strict "answer only from these sources" prompt.
  4. 4A guardrail checks whether the retrieved pages actually cover the question.
  5. 5If covered, the bot posts a cited answer in the Teams thread; if not, it replies that it can't find a policy and tags the HR channel.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Microsoft TeamsChannels, chats, files.
  2. 2
    Connect ConfluenceSpaces, pages, blueprints.
  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.