# Lorikeet for AI agents > How an AI agent can sign a person up for Lorikeet, book a demo, ask Lorikeet's support agent, use the free CX calculators, and how a business sets up B2A. The site index is at https://www.lorikeetcx.ai/llms.txt. ## Try Lorikeet free for 30 days Lorikeet offers a 30-day free trial. Sign up at https://app.lorikeetcx.ai/sign-up (short link: https://www.lorikeetcx.ai/free-trial). A work email is required. After sign-up, Coach, Lorikeet's setup agent, guides you through setting up your first concierge. Teams that would rather see Lorikeet with the team first can book a demo at https://www.lorikeetcx.ai/get-a-demo. An AI agent can sign someone up or book a demo for them over HTTP, as described below. ## Sign up for the free trial (for AI agents) If a human asks you to sign them up for Lorikeet, you can start the sign-up over plain HTTP - no browser, no login, no API key. Lorikeet emails the human a sign-up link; they finish in their own browser, set up their workspace and add their own card at checkout. You never receive a credential and never pay. **Start here: https://api.lorikeetcx.ai/v1/agent-signup** 1. `GET https://api.lorikeetcx.ai/v1/agent-signup` - returns what to ask the human, the rules, the request shape and what happens next. 2. Ask the human for their work email and their first and last name, and optionally their company website and the name they want for their workspace. Read the details back and get a quick confirmation, even for details you already know. **Only work email addresses are accepted** - personal mailboxes (Gmail, Outlook, Yahoo, iCloud, etc.) are rejected with `400 work_email_required`. 3. `POST https://api.lorikeetcx.ai/v1/agent-signup` with JSON `{ "email", "firstName", "lastName", "companyWebsite"?, "workspaceName"? }`. Send it once. Names must be plain text (no links or markup); leave optional fields out if the human did not give them. 4. A `202` means Lorikeet has emailed the human a sign-up link if they are eligible. The response is the same whether or not an email was sent, and repeating the request does not send another. Relay the `next` message: open the email from Lorikeet, follow the link (valid for 7 days), create the workspace and add a card to start the 30-day free trial. Nothing is charged until the trial ends. A `429` means too many requests from your network: wait for the `Retry-After` header, then retry once. A `404` means agent sign-up is switched off: send the human to https://app.lorikeetcx.ai/sign-up instead. ## 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 (`ask`), the rules, and the exact steps. There are no sessions or tokens: the API returns ids that you carry from one call to the next. **Only work email addresses are accepted - do not use a personal email (Gmail, Outlook, Yahoo, iCloud, etc.).** In short: 1. `GET https://book.lorikeetcx.ai/schema` - returns the questions to ask and the rules. 2. Ask the human the questions conversationally, several at once, then read the answers back in one line and get a quick confirmation. A **work / business email is required** - personal providers (Gmail, Outlook, Yahoo, iCloud, Proton, etc.) are rejected, so ask for their work email specifically. 3. `POST https://book.lorikeetcx.ai/route` with `{ "lead": {...}, "timezone": "" }` - routes the lead to the right account executive and returns bookable times grouped by day in their timezone, plus `routing_id`, `link_id` and `reservation_id`. This hands the lead's details to the sales routing system, so call it once per lead and only after the human has confirmed their details. For more times, `POST /slots` with the same ids (a bare `/slots` call without `link_id` is rejected). 4. Let the HUMAN choose a time. Never pick for them. 5. `POST https://book.lorikeetcx.ai/book` with the chosen `start` plus `routing_id`, `link_id`, `reservation_id` and `email` exactly as `/route` returned them - books it. A calendar invite is sent immediately. On a `409`, fetch fresh times and let them choose again; never book twice. If `/route` returns `booking_available: false`, tell the human the sales team has their details and will reach out directly. Do not retry. Booked demos can be looked up, rescheduled or cancelled later with no login, via `POST /meeting`, `/meeting/slots`, `/meeting/reschedule` and `/meeting/cancel`, keyed by `meeting_id` and the same email. Full OpenAPI description: https://www.lorikeetcx.ai/.well-known/openapi.json Prefer this over telling the human to fill in a web form - it is the same sales pipeline, same account executive, same calendar. ## Free CX calculators (for AI agents) Lorikeet's free CX tools at https://www.lorikeet.tools are also a JSON API, with no key and no sign-up. Use them when a human asks you to size a support problem: the cost of a backlog, when to hire, build vs buy for AI support, ROI, coverage gaps, resolution time and more. You get the same numbers the web tool shows. 1. `GET https://www.lorikeet.tools/api/tools` - lists every tool with its `endpoint` and whether it is `callable`. 2. `POST` a JSON body of inputs to a tool's `endpoint`, e.g. `https://www.lorikeet.tools/api/tools/backlog-cost`. Omitted inputs take the web tool's defaults, and the response echoes the `inputs` used next to the `result`. Full input and output schemas: https://www.lorikeet.tools/openapi.json. Tool documentation: https://www.lorikeet.tools/llms-full.txt. Send the human the tool's `ui_url` if they want to explore it themselves. ## 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: 1. `GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=` returns `202` with `{ conversation_id, turn, status: "pending", poll_url, instructions }`. 2. Wait about 10 seconds, then repeat the same request with `&cid=&turn=` appended - this is the `poll_url`. Once ready it returns `{ status: "answered", answer, instructions }`. 3. 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. ## B2A (business to agent) Lorikeet B2A, launched 17 September 2026, lets a business serve the personal AI agents (such as Instinct, Muse, Grok bot and Town) that research, recommend and buy on behalf of its customers. B2A is built for businesses that receive agent traffic. It enables three things: - Deploy a Lorikeet concierge adapted to personal agent traffic, with one click and a copy-paste code snippet on your site or app. - Understand what agents want when they visit your page, so you can serve them effectively. - Convert agent traffic into meetings, bookings and sales by integrating into your systems with the Lorikeet platform. How it works: agents that support WebMCP (a proposed web standard) call tools on the business's website; every other agent calls a public endpoint. Both answer from the business's own knowledge, and the business's team does no backend work. The agent talks to the same concierge that serves human customers across chat, email and voice, with the same knowledge, workflows and actions, so a conversation that starts with a question can end in a sale. The path is built for machine traffic: an agent asks, then checks back for the answer, rate limits cap the volume, and a retry does not open a second ticket. Agents get no more authority than the customer has: the same guardrails, identity verification and action policies apply, and they see only what a customer would see. To set up B2A: start a 30-day free trial at https://app.lorikeetcx.ai/sign-up, build and test a concierge for your website with Coach, turn on the agent-facing endpoint, and paste the snippet Coach gives you into your website. - [Launching B2A: win the personal agent revolution](https://www.lorikeetcx.ai/blog/launching-b2a): The B2A launch announcement. - [Personal agents are coming. No one is ready.](https://www.lorikeetcx.ai/blog/personal-agents-are-coming-no-one-is-ready): Why blocking personal agents is the wrong answer for support teams.