Integration · Support

An AI agent behind your Intercom inbox.

Connect Intercom and an OpenHelm agent can keep the support queue honest: triaging new conversations on a schedule, chasing threads that slipped through, drafting suggested replies from your documentation, and mining conversations for the questions your docs never answer.

Recurring jobs

What an OpenHelm agent can do with Intercom.

Each of these runs as a scheduled, self-correcting job: you describe it in plain English, approve the plan once, and an independent evaluator checks every run against the goal.

Queue triage runs

On a recurring schedule, classify open conversations by topic and urgency, and flag the ones that look angry, churny or high-value.

Unanswered-conversation digest

A daily list of conversations past your response target, grouped by assignee, emailed before the morning stand-up.

Suggested reply drafts

For common question types, draft replies grounded in your help centre and past answers, left as notes for the agent handling the thread.

FAQ gap mining

Log recurring questions into a data table with counts, so the docs team writes the article that removes fifty tickets, not the one that removes two.

Get started

Connect Intercom in minutes.

  1. 1

    Connect Intercom

    Add Intercom under Connections in the OpenHelm app and paste a scoped API key, or provision it programmatically with POST /v1/connections.

  2. 2

    Describe the job in plain English

    Tell OpenHelm what you want done and how often. It drafts a plan with a schedule, the tools it will use, and a clear definition of done.

  3. 3

    Approve the plan

    No job fires until you have reviewed the plan. Set the autonomy level to control whether writes execute directly or queue for your approval.

  4. 4

    It runs, self-checks and reports

    Runs execute in isolated cloud sandboxes on schedule. An independent evaluator scores each run against the goal, and results arrive as logs, emails or data-table rows.

For developers

Or provision the connection over the API.

POST /v1/connections
curl https://api.openhelm.ai/v1/connections \
  -H "Authorization: Bearer oh_live_..." \
  -H "Content-Type: application/json" \
  -d '{ "name": "Intercom", "type": "token", "secret": "<your Intercom API key>" }'
# secret is write-only: stored encrypted, injected only at run time

The same connections back runs started over REST. See the AI agent API and the Connections API docs.

Related ways to put agents to work with Intercom:

Common questions about the Intercom integration

Put an agent to work in Intercom this week.

Connect once, describe the job, approve the plan. From then on it runs on schedule, checks its own work, and reports back with evidence.