CHATBOTS

Teams IT Bot: Self-Service SaaS Seat Provisioning

Employees request a SaaS license in a Teams chat and the bot provisions the seat after a manager approval check, then confirms back in the same thread.

CategoryChatbots
Enginepaperclip
Difficultyintermediate
Triggerchat
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerTeams message mentions IT bot with seat requestMicrosoft Teams
  • ActionParse app, requester, and reason from messageOpenAI
  • LogicCheck requester department against allowed-apps policy
  • ActionProvision SaaS seat via provider admin APIFigmaFigma
  • ActionOpen ClickUp approval task when not pre-approvedClickUpClickUp
  • OutputReply with grant or approval-pending in Teams threadMicrosoft Teams

What it does

Turns a casual Teams message like "I need a Figma seat" into a real, governed license grant. The bot parses the requested tool, checks whether the requester's role is pre-approved for that app, provisions the seat in the target SaaS via its API, and replies in-thread with confirmation or an approval-pending notice.

When to use it

When IT is drowning in one-off seat requests and you want self-service that still respects entitlement policy. Best for teams that already centralize requests in a Teams channel and want zero ticket-queue latency for low-risk apps.

How it works

  1. 1A Teams message mentions the bot and names a SaaS app and reason.
  2. 2The agent extracts the app name, requester, and justification from the message.
  3. 3A logic branch checks the requester's department against an allowed-apps policy.
  4. 4If pre-approved, the bot calls the SaaS provider's admin API to create or assign the seat.
  5. 5If not pre-approved, it opens a ClickUp approval task for the manager instead.
  6. 6The bot posts the outcome back into the original Teams thread.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Microsoft TeamsChannels, chats, files.
  2. 2
    Connect FigmaFiles, frames, comments, assets.
  3. 3
    Connect ClickUpDocs + tasks + chats in one workspace.
  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.