CRM

Route Intercom Feature Requests to Linear and Tag the Account in Attio

Detects feature-request intent in Intercom conversations, files or links a Linear issue.

CategoryCRM
Enginesim
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerIntercom conversation closedIntercomIntercom
  • ActionExtract feature request from threadOpenAI
  • LogicSearch Linear for duplicate, exit if none requestedLinearLinear
  • ActionCreate or link Linear issue with quoteLinearLinear
  • OutputUpdate Attio with feature + request countAttio

What it does

This workflow captures the feature requests buried in support conversations. When a closed Intercom chat asks for missing functionality, it extracts a clean request title, searches Linear for a matching issue, creates one or links to the existing thread, and then increments a request counter and notes the feature on the customer's Attio company record. Product sees demand with customer weight attached; revenue sees which accounts are blocked by which gaps.

When to use it

Use it when product prioritization needs revenue context and support requests vanish after a conversation closes. Ideal for tying a Linear backlog to account value in Attio.

How it works

  1. 1A closed Intercom conversation triggers the workflow.
  2. 2The thread is read and a feature request is extracted, or the run exits if none is present.
  3. 3A branch searches Linear for a duplicate; matched requests link instead of creating noise.
  4. 4A Linear issue is created or updated with the customer quote and account link.
  5. 5The customer's Attio record is updated with the requested feature and an incremented request count as the final output.

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
    Connect AttioReal-time CRM with structured data + powerful views.
  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.