Why teams compare building in-house with Lorikeet: your engineers can build an AI agent on Amazon Bedrock, Amazon Connect or your own MCP servers, and the first demo will look great. The real cost is everything after the demo: evals and regression testing every time a model changes, guardrails, helpdesk and voice integrations, compliance evidence, and a team that maintains all of it for as long as it runs. Lorikeet ships that layer, and your engineers keep building on top of it.
The Lorikeet difference:
Simulations replay your real tickets before every change, so a model upgrade is a regression test, not a leap of faith
Built-in connectors for Zendesk, Intercom, Salesforce, Front, HubSpot, Help Scout and Kustomer, plus voice through Amazon Connect, Twilio, Genesys Cloud and more
SOC 2 Type II, ISO 27001:2022, HIPAA and GDPR, with BAAs signed for healthcare customers
An API, SDK and product MCP server, so your engineers extend Lorikeet instead of rebuilding it
Trusted by CX leaders in fintech, health tech and complex industries
What is
?
Building in-house means your own engineers assemble the AI support agent: a foundation model from a provider such as Amazon Bedrock, retrieval over your knowledge base, tool calls into your systems, a voice layer such as Amazon Connect, and the guardrails, evaluation suite, monitoring and helpdesk integrations around it. AWS now sells solid building blocks for most of those pieces, including Bedrock Guardrails, Bedrock Evaluations and agentic self-service in Amazon Connect. What stays with you is the assembly: your policies, your workflows, your test sets, and the team that keeps it all working as the models underneath keep changing.
What is Lorikeet?
Lorikeet is an agentic AI platform built for CX teams in complex, regulated industries. Unlike deflection-first tools, Lorikeet agents take real action processing refunds, updating customer records, booking appointments, and closing tickets end-to-end across voice, chat, email, and SMS. Teams get dedicated PM and engineering support, and pay only for resolutions they define as successful.
Lorikeet
vs
Building in-house
See how Lorikeet stacks up
10 questions to evaluate an agentic AI platform for CX
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.