Conversations, contacts, tags, webhooks.
Intercom's API covers conversations, contacts, companies, tags, notes and articles, and webhooks fire when a conversation is opened, replied to or assigned. That lets an agent act within seconds and leave its work visible as a note or a tag.
We keep your team's workflow in Intercom. The agent's output appears as a drafted reply, an internal note with the data it found, or a tag that routes the conversation, so agents and admins see what it did.
What agents do in Intercom.
Topic, language and urgency tagged; conversations routed to the right team.
Answers that need account data (payout status, order, verification step) drafted from your back office.
Refunds, resets or account changes prepared, then approved by a person.
When a human takes over, a short summary of the case and what was already checked.
Top question themes, reply times and which answers to add to the help centre.
How access works.
The agent gets its own access token with the scopes it needs, nothing more.
What it costs.
All prices excl. VAT. "From" covers a standard scope; your fixed quote comes from the Blueprint. Model and messaging fees (for example WhatsApp per-message charges from Meta) depend on volume and are estimated in the Blueprint.
Common questions.
We already use Intercom's AI agent. Why add this?
Keep using it for help-centre questions. We cover the conversations it can't finish because the answer depends on data in your own systems.
Does it work for prop firms and crypto exchanges?
Yes; these teams often run on Intercom. Typical topics are rules, payouts, KYC steps and account access. The agent never approves KYC or payouts itself.
Can it reply automatically?
Only where you choose. Many teams start with drafted replies and switch on auto-reply per topic once they trust the answers.
Want this in your business?
Tell us how you work today. We'll tell you honestly what AI can take off your team's plate, what it costs, and whether we are the right fit.