Skip to content
Per-pair page

Intercom + OpenAI: AI inside every customer conversation.

Use GPT-4o to triage Intercom conversations, draft replies, summarize threads, or classify intent. AI keeps support fast without removing humans from the loop.

Trigger app
OpenAI as the trigger

Workflows fire when something happens in OpenAI.

  • OpenAI has no triggers yet. Use the catalog's universal Webhook trigger as the upstream.
Action app
Intercom as the action

Workflows do something in Intercom, instantly.

See all 20 actions →
Both directions

Pick the way that fits your stack.

Pair pages are mirrored. Each direction gets its own dedicated page.

OpenAIIntercom

When something happens in OpenAI, do it in Intercom.

0 OpenAI triggers wired to 20 Intercom actions.

    IntercomOpenAI

    Or fire it the other way around.

    5 Intercom triggers wired to 16 OpenAI actions downstream.

    See IntercomOpenAI
    Popular pairings

    Common OpenAI → Intercom workflows.

    Pick a pairing to set it up in two minutes. Each one is a fully editable recipe.

    Showing 0 of 0 combinations
    How it works

    Connect OpenAI and Intercom in five steps.

    No code, no glue, no half-day setup. Each step is one click.

    1. 1
      Connect
      Authorize OpenAI and Intercom

      Open Tiny Command, authorize OpenAI and Intercom once each. Both connections are available to every workflow on your account.

    2. 2
      Trigger
      Pick a OpenAI trigger

      Drop the OpenAI → New event trigger onto the canvas. Tiny Command auto-registers the webhook.

      POST /v1/webhooks/openai.event
    3. 3
      Transform
      Add a filter or AI step

      Optionally add a Filter node ("subject contains URGENT") or an AI step ("classify intent") between trigger and action.

    4. 4
      Action
      Add the Intercom action

      Drop the Intercom → Assign Conversation action below it. Map fields from the OpenAI payload into the Intercom inputs.

      intercom.assign-conversation
    5. 5
      Publish
      Publish and forget

      Hit Publish. Tiny Command runs it in production from second one. Watch the run-log fill up.

    FAQ

    Questions about OpenAI + Intercom.

    How do I AI-triage Intercom conversations?
    Intercom Conversation Created → OpenAI classifies intent (billing, bug, feature, account) and urgency → Intercom Assign Conversation to right team + Add Tag. Reduces triage to seconds.
    Can GPT draft replies that match my brand voice?
    Yes. Pull past replies as voice examples. GPT generates a draft → Intercom Add Note prefixed "AI suggestion:". Human reviews and sends the final reply.
    How do I get GPT to write KB-grounded answers (RAG)?
    Index help center articles into vector store. On user question, retrieve top-3 articles, pass as context to GPT with "answer only from these sources, cite which article". Cuts hallucination.
    Can GPT detect when Intercom conversations need human handoff?
    Yes. Add confidence score to GPT's answer. If < 0.7 or escalation phrases detected, Intercom Assign Conversation to human agent and stop the bot loop.
    How do I summarize Intercom conversations when they close?
    Intercom Conversation Closed → fetch all messages → OpenAI summarizes resolution + root cause + action items → write to Airtable "Closed Tickets" for product feedback or QA review.
    How much does GPT on Intercom cost?
    With gpt-4o-mini, triage + classification costs ~$0.002 per conversation. Drafting with gpt-4o runs ~$0.01. Even at 1000 conversations/day, that's under $10/day for substantial AI augmentation.
    Related

    Other apps that pair well with OpenAI.


    Wire OpenAI to Intercom in 2 minutes.

    Free tier available. No credit card. No onboarding call.