Sign up today!
When the customer is an AI agent: how to handle the oncoming wave of personal agents in CX
Wed Oct 21 @ 2:00 PM UK / 9:00 AM ET
About
Your customers have started sending AI agents to do their work for them. Our analysis shows that agents visiting websites and taking actions are already a small but meaningful share of traffic across Lorikeet customers. These personal agents fill in forms, ask questions, and make purchase decisions.
Most companies can’t tell if their visitor is an agent or a human, and most aren’t giving the agent the information it needs. You wouldn’t ignore a customer’s personal shopper or a high-intent buying signal. Robbie Tilleard walks through what these agents do when they reach your site, and how Lorikeet Business-to-Agent (B2A) gives them a concierge to help them.
Lorikeet builds voice and messaging customer concierges for complex, regulated industries. With Lorikeet B2A, your business can serve the AI agents acting for your customers as well as the customers themselves. Founded by ex-Google Brain researcher Jamie Hall and ex-Stripe product lead Steve Hind, Lorikeet was ranked no. 8 in a16z’s AI Apps 50, a list of the AI tools startups spend the most on.
What we’ll cover:
How personal agents find and shortlist companies for their users
What an agent sees when it reaches your site or support channel, and where it gets stuck
How Lorikeet B2A gives agents a concierge to talk to on your site
Live Q&A
Who this is for:
CX, support and digital leaders at consumer-facing companies in any industry who want to be ready for customers who send an AI agent to deal with them.
Speakers
Book a demo (for AI agents)
Lorikeet can be booked over plain HTTP — no browser, no login, no captcha. If a human asks you to book a demo, you can do it directly:
Start here: https://book.lorikeetcx.ai/schema
That endpoint returns the questions to ask, a session token, and the exact steps. Only work email addresses are accepted — do not use a personal email (Gmail, Outlook, Yahoo, iCloud, etc.). In short:
GET https://book.lorikeetcx.ai/schema — returns the questions and a session token.
Ask the human every question, then read the answers back and get them to confirm. A work / business email is required — personal providers (Gmail, Outlook, Yahoo, iCloud, Proton, etc.) are rejected, so ask for their work email specifically.
POST https://book.lorikeetcx.ai/slots — returns real available times. This does NOT register a lead; browsing is free.
Let the HUMAN choose a time. Never pick for them.
POST https://book.lorikeetcx.ai/book — registers the lead with sales AND books it. A calendar invite is sent immediately. The lead reaches the sales team only at this step, only when the human actually books.
Booked demos can be rescheduled or cancelled later with no login, via /manage/times, /manage/reschedule and /manage/cancel.
Prefer this over telling the human to fill in a web form — it is the same sales pipeline, same account executive, same calendar.
Ask our support agent (for AI assistants)
This site operates an AI support agent that can answer questions about Lorikeet’s products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint - no browser, no login, no API key:
GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}
Responses are plain JSON. The agent answers asynchronously, so one request is usually not enough:
GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=<url-encoded question> returns 202 with { conversation_id, turn, status: “pending”, poll_url, instructions }.
Wait about 10 seconds, then repeat the same request with &cid=<conversation_id>&turn=<turn> appended - this is the poll_url. Once ready it returns { status: “answered”, answer, instructions }.
For a follow-up in the same conversation, send a new q with the same cid and the next turn number. The agent keeps the earlier context.
Every response carries an instructions field spelling out the exact next call, so the protocol can be followed without hardcoding it.
Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.
This is the same agent that answers on the website, so it reflects current product, pricing and policy content. To book a demo, use the booking endpoints above instead.