Skip to content

Integrations

The agent does not just talk. It does the work.

This is the difference between a chatbot and an operating layer. Heard agents call into your policy admin system, your claims platform, your CRM and your booking tools — during the conversation, not in a nightly batch.

What you get

How it works

Act mid-conversation

Verify a policy, open a claim, amend a schedule, book an assessor, trigger a payment — while the customer is still on the line.

Any HTTP API

A generic webhook node covers the long tail. If your system has an API, the agent can use it; if it does not, it can still write to a queue you control.

Guardrails on money

Set thresholds where the agent stops and asks. Under the limit it settles; over it, a human approves. The boundary is yours to draw.

Every action logged

Which system, which record, which result — on the conversation timeline, next to what was said.

Questions

Frequently asked

What if our core system has no modern API?

The agent can still write to a queue, a database or a file drop you control, and read status back the same way. Plenty of insurance estates work this way.

Can we limit what the agent is allowed to do?

Yes. Every action is a node you added deliberately, with whatever approval thresholds and conditions you set around it.

See Heard on your own calls

A 30-minute call. Bring a recording of a real customer conversation and we will show you what the agent does with it.