TICKET MANAGEMENT

Close the loop with Intercom customers when their Linear bug ships

When a Linear bug issue moves to Done, this finds every Intercom conversation linked to it, drafts a tailored fix-shipped reply for each.

CategoryTicket Management
Enginesim
Difficultyadvanced
Triggerevent
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerLinear issue moved to DoneLinearLinear
  • ActionFind linked Intercom conversationsPostgreSQLPostgres
  • LogicFilter conversations needing follow-up
  • ActionDraft per-customer fix replyOpenAI
  • ActionAttach draft + reopen conversationIntercomIntercom
  • OutputMark follow-up sent in PostgresPostgreSQLPostgres

What it does

Closes the support loop automatically when engineering ships a fix. The moment a Linear issue transitions to Done, it looks up all Intercom conversations tied to that issue in Postgres, drafts a personalized "this is fixed" reply referencing each customer's original report, and reopens the conversation as a snoozed draft for agent review.

When to use it

When bugs get fixed but the customers who reported them never hear back, eroding trust and generating "is this fixed yet?" follow-ups weeks later.

How it works

  1. 1A Linear issue moving to Done fires the trigger.
  2. 2The flow queries Postgres for all Intercom conversation IDs linked to that issue.
  3. 3A logic step filters to conversations still open or recently closed where a follow-up is warranted.
  4. 4An OpenAI step drafts a per-customer reply referencing their specific report and the fix.
  5. 5The flow attaches each draft to its Intercom conversation and reopens it for agent review.
  6. 6It marks the linked records in Postgres as follow-up-sent to avoid duplicates.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect LinearIssues, projects, cycles, triage.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect IntercomConversations, contacts, articles.
  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.