TICKET MANAGEMENT

Correlate Intercom bug reports with Sentry errors before deduplicating into Linear

When a bug-tagged Intercom conversation comes in, this matches it against recent Sentry issues by symptom, attaches the stack trace and event count.

CategoryTicket Management
Enginesim
Difficultyadvanced
Triggerevent
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerIntercom conversation tagged 'bug'IntercomIntercom
  • ActionExtract error signature with OpenAIOpenAI
  • ActionMatch against recent Sentry issuesSentrySentry
  • LogicFingerprint and find existing Linear issueLinearLinear
  • ActionCreate or increment enriched Linear issueLinearLinear
  • OutputPost Linear and Sentry links to IntercomIntercomIntercom

What it does

Bridges what customers say with what your error tracking sees. A vague "the page crashed" report gets matched to the real Sentry issue, so the deduplicated Linear ticket carries the stack trace, error frequency, and a Sentry link, not just a customer paraphrase.

When to use it

Use it when your stack reports to Sentry and you want engineering-ready bugs: every escalation should already point at the underlying exception and its event volume, with customer reports deduplicated on top.

How it works

  1. 1An Intercom conversation tagged `bug` fires the trigger.
  2. 2OpenAI extracts the symptom, error text, and affected feature from the transcript.
  3. 3The flow queries Sentry for recent issues matching that signature and pulls the top candidate's stack trace and event count.
  4. 4It fingerprints the combined report and searches Linear: if a matching issue exists it increments the reporter count and refreshes the Sentry stats; otherwise it creates one enriched with the stack trace and Sentry link.
  5. 5It posts the Linear issue and matched Sentry link back to the Intercom conversation.

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 SentryErrors, performance, releases.
  4. 4
    Connect LinearIssues, projects, cycles, triage.
  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.