TICKET MANAGEMENT

Bundle repeated Intercom bug reports into one deduplicated Linear issue

When a support agent tags an Intercom conversation as a bug, this fingerprints the report and either opens a new Linear issue or increments a reporter count on the matching…

CategoryTicket Management
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerIntercom conversation tagged 'bug'IntercomIntercom
  • ActionFingerprint the report with OpenAIOpenAI
  • LogicSearch Linear for matching fingerprintLinearLinear
  • LogicBranch: existing issue vs. new issue
  • ActionIncrement count or create Linear issueLinearLinear
  • OutputPost issue link back to Intercom as a noteIntercomIntercom

What it does

Turns a stream of look-alike bug reports into a single Linear issue with an accurate "reported N times" count. Instead of engineering wading through fifty tickets that are all the same crash, they get one issue that grows in priority as more customers hit it.

When to use it

Use it when your support team triages in Intercom and you want every confirmed bug to land in Linear without manual dedup. Best for teams where the same defect surfaces across many conversations before a fix ships.

How it works

  1. 1A support agent applies the `bug` tag to an Intercom conversation, firing the trigger.
  2. 2OpenAI reads the conversation transcript and produces a normalized fingerprint: a short canonical title plus a stable hash of the symptom, ignoring customer-specific wording.
  3. 3The flow searches Linear for an open issue carrying that fingerprint.
  4. 4If a match exists, it increments the reporter count in the issue body and appends the new conversation link; if not, it creates a fresh Linear issue stamped with the fingerprint.
  5. 5It writes the resulting Linear issue URL back onto the Intercom conversation as a note so the agent can reply with status.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect IntercomConversations, contacts, articles.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect LinearIssues, projects, cycles, triage.
  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.