Intercom Support Agent with Claude Code

This is the template where the agent talks straight to a customer, so the boundary of your playbook is doing real work. Claude Code reads what it was given thoroughly before replying, and here that means checking whether an answer is genuinely in the playbook rather than nearly in it. When it is not, the whole output becomes an acknowledgement, an internal note and a Slack line.
Loading preview…
Free to start · guided setup · switch agents any time.

Live demo

Watch it work before it's live

Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.

Adding a teammate to the workspace

Open

Siobhan O'Rourke <siobhan@rathmoredesign.ie>

Hey, how do I get my colleague into our workspace? I only see my own name under members and we are on the Studio plan.

What you'll need

Set up in minutes

Using this template drops you into a guided setup. It asks exactly this, nothing else:

  1. Connect Intercom

    One sign-in. The agent acts through your account, scoped to what this template uses.

  2. Connect Slack

    One sign-in. The agent acts through your account, scoped to what this template uses.

  3. Support playbook

    The answers you are happy to give without a human checking - your common questions, how-to steps, plan limits, and known issues, in your own words. The agent replies only when the answer is in here.

  4. Escalation rules

    The conversations a person must own - refunds, billing, account access, security, cancellations, angry customers, named accounts, whatever you decide. The agent acknowledges these and hands them over instead of answering.

  5. Runs on Claude Code

    Preselected for this page — connect your Claude Code account during setup, or switch to NoClick's built-in models with one click.

  6. Watch it handle a test run

    A staged conversation against a simulated world — then it’s live.

A considered pairing

Why Claude Code for this agent

Knows when to stop

Partly covered is the dangerous case, because it invites the agent to close the gap itself. Careful reading of the playbook is what prevents that in a live chat.

Handovers carry context

The internal note has to say what the customer wants, what was checked and what is blocking. Summarising a whole thread that way suits a harness comfortable with long structured work.

Good to know

Before you fork

What stops it inventing a price or a limit?

The playbook is its only source and it is told to hand over rather than close a gap, but an instruction is not a hard wall, so start the playbook narrow and widen it after reading a week of transcripts. Refunds, billing, account access and angry customers escalate regardless of what the playbook says. It is also barred from promising a callback time, a discount or a fix date.

Other editions

Run it with a different agent

OpenAICodexopencodeopenclawhermesMore Claude Code agents

Make it yours

Put Intercom Support Agent to work on Claude Code.

Free to start. Guided setup, a staged test run, and a workflow you can change at every step.