Integration · Support

An AI agent for your Help Scout mailboxes.

Connect Help Scout and an OpenHelm agent can keep shared mailboxes under control: recurring triage, a daily list of conversations going stale, drafted replies for the routine questions, and a weekly read on what customers are actually asking.

Recurring jobs

What an OpenHelm agent can do with Help Scout.

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.

Mailbox triage sweep

Classify new conversations by topic and urgency on a schedule, tagging and assigning so the right person sees the right thread first.

Going-stale chaser

Each morning, list conversations without a reply inside your target window and nudge the assigned owner.

Weekly support insights

A short report on question themes, resolution times and recurring friction, built into a data table you can track over months.

Get started

Connect Help Scout in minutes.

  1. 1

    Connect Help Scout

    Add Help Scout 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": "Help Scout", "type": "token", "secret": "<your Help Scout 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 Help Scout:

Common questions about the Help Scout integration

Put an agent to work in Help Scout 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.