B2A: Lorikeet supports the Personal Agent Protocol

Steve Hind

Oct 12, 2026

0 Mins

Today Lorikeet adds support for the Personal Agent Protocol, or Poppy, the draft open protocol from Sierra, Meta and partners. It joins the agent-facing endpoint, WebMCP and A2A as a way for a personal agent to reach your concierge. It is live on Lorikeet now, and you can turn it on yourself.

Why one more protocol

Last week Sierra and Decagon both announced their own standard for how personal agents talk to businesses. By the end of the week there was some convergence on Poppy. It is the XKCD comic about competing standards, playing out in real time. Over time, we may coalesce around one standard for the way agents and companies talk. But this is not certain: restaurant reservations, customer identity and customer support itself never got a common standard, for reasons that have more to do with incentives than technology.

Meanwhile, different personal agents have different capabilities. Today ChatGPT cannot speak Poppy. Neither can most of the agents your customers actually use: Instinct doesn't have native support yet, and they're part of the protocol group! So our bet is on all of them: give your concierge the widest possible set of doors, and if another protocol gets traction we will add that door too. That means Lorikeet concierges now support Poppy, Agent2Agent protocol, WebMCP and agent-facing endpoint. Whichever way an agent arrives, it reaches the same concierge, with the same knowledge, workflows, guardrails and tickets behind it.

What Poppy adds

A standard way for a customer to sign their agent in. The agent starts as a stranger: it finds you from your domain at yourcompany.com/.well-known/poppy.json and holds a conversation with no access to any account. When a question needs the account, the customer signs in on your own page, then approves exactly what the agent may do on Lorikeet's consent page: read their account, act on it, or neither. From then on the agent gets account-specific answers for that customer only. Both sides also declare whether a person or an AI is speaking, so your concierge knows who it is talking to.

Every conversation is a ticket in Lorikeet, labelled with the protocol and the agent, with your usual escalation rules. You can allow or block specific agents.

Turn it on

Open Integrations, choose Agent-facing concierge, and pick your endpoint.
In the Personal Agent Protocol card, enter your domain and save.
Add one redirect on your site from /.well-known/poppy.json to the URL the card shows, then press Verify.

The docs have the redirect rules for Cloudflare, Vercel, Next.js and nginx, and the details for agent developers. Not on Lorikeet yet? Start free at lorikeetcx.ai/sign-up.

Try Lorikeet on your own tickets

Start a 30-day free trial. Coach sets up your first concierge in minutes.

Start free trial

Book a call

See what Lorikeet is capable of

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.