CHATBOTS

Personalized Benefits Answers Using Employee Eligibility Data

Answers benefits questions in Teams by combining policy text from Confluence with the asker's own eligibility and plan tier stored in Postgres, so responses are specific to them.

CategoryChatbots
Enginesim
Difficultyadvanced
Triggerchat
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerEmployee asks a benefits question in TeamsMicrosoft Teams
  • ActionLook up employee plan and eligibility in PostgresPostgreSQLPostgres
  • ActionSearch Confluence for policy pages matching their tierConfluenceConfluence
  • LogicBranch on whether eligibility data was found
  • ActionCompose personalized grounded answer via OpenAIOpenAI
  • OutputReply privately in the Teams threadMicrosoft Teams

What it does

Goes beyond generic policy answers: it looks up the employee's plan tier, location, and eligibility from a Postgres record, then answers their Teams question using the matching Confluence policy. "What's my deductible?" returns their actual plan's number, not a list of all plans.

When to use it

When your benefits vary by tier, region, or employment class and generic answers cause confusion. Use it once you have a trustworthy eligibility table and want the bot to give each person the answer that applies to them.

How it works

  1. 1An employee asks a benefits question in Teams.
  2. 2The flow looks up the employee's profile and plan tier in Postgres using their Teams identity.
  3. 3It searches the HR Confluence space for the policy pages relevant to the question and that tier.
  4. 4A logic step confirms an eligibility match was found; if not, it falls back to a generic answer with a note.
  5. 5OpenAI composes a personalized answer grounded in the policy text and the employee's specific plan details, with citations.
  6. 6The tailored answer is delivered privately in the Teams thread.

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 ConfluenceSpaces, pages, blueprints.
  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.