Release Notes
Product updates and features
Mar 11, 2026
Lorikeet MCP
Lorikeet MCP
What is it?
The Lorikeet MCP server lets you interact with your Lorikeet account directly from Claude Code, Claude.ai, ChatGPT, and Codex. Easily manage workflows, knowledge base, tickets, tools, integrations, simulations, guardrails, analytics and metrics with full read and write access. Any configuration change made through the MCP is logged with a full audit trail, and role-based access control ensures each team member only sees and uses the tools relevant to their role.
What is the impact?
Your AI tool becomes the primary interface for managing your Lorikeet account. Configure workflows, audit your knowledge base, diagnose tickets, run simulations, and build tools — all conversationally, from the tool you already work in.
Key capabilities
Diagnose tickets by tracing workflow execution and identifying root causes
Audit your entire knowledge base for gaps, outdated articles, and quality issues
Build, edit, and deploy workflows using natural language
Run simulation batches to test workflows against different customer scenarios
Test and validate tool configurations directly from your assistant
Inspect and configure integrations, guardrails, and metrics
Analyze automation rates, resolution trends, and performance breakdowns
How to use it
Claude Code:
Claude.ai: Settings > Connectors > Add Custom Connector > URL:
ChatGPT: Settings > Connectors > Add Connector > URL:
Start with
whoamito confirm your subscriber context
Mar 5, 2026
Resolution Loop
Resolution Loop
What is it?
Resolution Loop is Lorikeet's native escalation management system. When the AI concierge can't resolve a conversation, a human agent steps in directly inside the same platform within the same channel, the same conversation thread and full context intact. We launched the Take Over mode: a human replaces the AI and drives the conversation to resolution. And we are rolling out: Steer mode, where a human guides the AI agent while it stays in control, with instructions saved to the knowledge base so Coach handles that situation autonomously next time.
What is the impact?
Escalations resolve faster with full context intact, without a system switch and without the customer repeating themselves. Every human resolution is captured, and over time Coach uses that data so the same issue doesn't escalate twice and your escalation rate goes down over time. We launched it on SMS and WhatsApp channels, where conversations are async and thread continuity matters most, followed by email and chat. And because everything stays in one platform, you get real-time observability across every escalation with built-in compliance guardrails.
Key capabilities
Triage queue with unassigned, assigned, and resolved filters
One-click ticket claiming and reassignment
Reply and internal notes from a single conversation view
Full customer context including profile and previous tickets
Real-time updates as conversations progress
How to use it
Configure escalation routing in your Concierge settings. When a ticket escalates, assigned agents receive a Slack notification and can manage the conversation directly in Lorikeet's agent workspace.
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.