# Lorikeet

> Lorikeet is an AI customer support platform for complex and regulated businesses. AI agents that work across voice, chat, and email to resolve customer issues autonomously.

## 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": "<IANA tz>" }` - 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/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=<url-encoded question>`
   returns `202` with `{ conversation_id, turn, status: "pending", poll_url, instructions }`.
2. 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 }`.
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.

## Main Pages

- [Homepage](https://www.lorikeetcx.ai): AI customer support platform overview
- [Pricing](https://www.lorikeetcx.ai/pricing): Lorikeet pricing information
- [Free trial](https://www.lorikeetcx.ai/free-trial): Start a 30-day free trial of Lorikeet (goes to app.lorikeetcx.ai/sign-up)
- [Product Overview](https://www.lorikeetcx.ai/product): Lorikeet platform for AI-powered customer support
- [Product - Coach](https://www.lorikeetcx.ai/product/coach): AI quality assurance that reviews 100% of interactions
- [Product - Voice](https://www.lorikeetcx.ai/product/voice): AI voice agents for phone-based customer support
- [Product - AI Agents](https://www.lorikeetcx.ai/product/ai-agents): AI agents for customer service that resolve end-to-end, not deflect
- [Product - Trust & Security](https://www.lorikeetcx.ai/product/trust): SOC 2 Type II, ISO 27001:2022, HIPAA and GDPR; never trains on customer data
- [Product - Quality Assurance](https://www.lorikeetcx.ai/product/quality-assurance): Coach QA reviews 100% of tickets with a refund-backed Quality Guarantee
- [Product - Simulations](https://www.lorikeetcx.ai/product/simulations): Test AI agents pre-launch with simulations from real tickets and adversarial scenarios
- [Product - Guardrails](https://www.lorikeetcx.ai/product/guardrails): Two-tier guardrails with deterministic boundaries; designed for blast radius, not immunity claims
- [Product - How It Works](https://www.lorikeetcx.ai/product/how-it-works): How the Lorikeet AI concierge connects, trains, tests and improves
- [Product - Outbound](https://www.lorikeetcx.ai/product/outbound): Proactive AI outreach over SMS and voice with consent and opt-out controls
- [Convert - AI agents that drive revenue](https://www.lorikeetcx.ai/convert): Outbound AI agents across WhatsApp, SMS, phone and email that recover abandoned applications, re-engage lapsed users and convert leads
- [B2A (business to agent)](https://www.lorikeetcx.ai/blog/launching-b2a): Serve and convert the personal AI agents that research, recommend and buy for your customers
- [Customer Stories](https://www.lorikeetcx.ai/customer-stories): How teams use Lorikeet to resolve complex support at scale
- [Competitors](https://www.lorikeetcx.ai/competitors): How Lorikeet compares to other AI customer support platforms
- [Integrations](https://www.lorikeetcx.ai/integrations): Lorikeet integrations with helpdesks, CRMs, and backend systems
- [FAQ](https://www.lorikeetcx.ai/faq): Frequently asked questions about Lorikeet
- [Get a Demo](https://www.lorikeetcx.ai/get-a-demo): Book a demo with the Lorikeet team
- [About](https://www.lorikeetcx.ai/about): About Lorikeet - team, mission, and investors
- [Careers](https://www.lorikeetcx.ai/careers): Open roles at Lorikeet
- [Partner](https://www.lorikeetcx.ai/partner): Partner with Lorikeet
- [Release Notes](https://www.lorikeetcx.ai/release-notes): Latest product updates and releases
- [Press Kit](https://www.lorikeetcx.ai/press-kit): Lorikeet press assets and company information
- [Blog](https://www.lorikeetcx.ai/blog): Latest posts on CX, AI, and product updates
- [Articles](https://www.lorikeetcx.ai/articles): In-depth articles on AI in customer service
- [Thoughts on CX](https://www.lorikeetcx.ai/thoughts-on-cx): Perspectives on customer experience from Lorikeet and industry leaders
- [Glossary](https://www.lorikeetcx.ai/glossary): Complete CX and AI glossary
- [CX Jobs](https://www.lorikeetcx.ai/cx-jobs): Curated job board for CX, AI, and support roles
- [Help Center Audit](https://www.lorikeetcx.ai/help-center-audit): Free audit of your help center readiness for AI
- [Team of Agents Resource](https://www.lorikeetcx.ai/resources/team-of-agents): How Lorikeet's Team of Agents coordinates across channels and tools
- [Privacy Policy](https://www.lorikeetcx.ai/privacy-policy): Lorikeet privacy policy
- [Terms of Service](https://www.lorikeetcx.ai/terms-of-service): Lorikeet terms of service

## Industries

- [Financial Services](https://www.lorikeetcx.ai/industry/financial-services): AI customer support for banks, fintech, and financial services companies
- [Healthcare](https://www.lorikeetcx.ai/industry/healthcare): AI customer support for healthcare and healthtech companies
- [Insurance](https://www.lorikeetcx.ai/industry/insurance): AI customer support for insurers handling complex claims and policyholder workflows

## Integrations

Ticketing and messaging:
- [Zendesk](https://www.lorikeetcx.ai/integrations/zendesk): Turn Zendesk tickets into completed work: classification, action and closure
- [Zendesk Messaging](https://www.lorikeetcx.ai/integrations/zendesk-messaging): Resolve real-time customer conversations through Zendesk Messaging
- [Intercom](https://www.lorikeetcx.ai/integrations/intercom): Resolve conversations inside Intercom while keeping context and outcomes consistent
- [Front](https://www.lorikeetcx.ai/integrations/front): Handle customer conversations in Front with AI resolution and team handoffs
- [Help Scout](https://www.lorikeetcx.ai/integrations/help-scout): Resolve Help Scout conversations with AI while keeping your team's personal touch
- [HubSpot](https://www.lorikeetcx.ai/integrations/hubspot): Sync customer context and follow-up so support and revenue teams stay aligned
- [Salesforce](https://www.lorikeetcx.ai/integrations/salesforce): Execute support workflows inside Salesforce for consistent, auditable outcomes
- [Slack](https://www.lorikeetcx.ai/integrations/slack): Handle support requests and internal workflows directly in Slack
- [Lorikeet Chat](https://www.lorikeetcx.ai/integrations/lorikeet-chat): Deploy AI agents directly on your website without a ticketing system

Telephony:
- [Genesys Cloud](https://www.lorikeetcx.ai/integrations/genesys-cloud): Conversational voice capability as a Genesys Audio Connector
- [Twilio](https://www.lorikeetcx.ai/integrations/twilio): SMS notifications and voice interactions at scale
- [Lorikeet API](https://www.lorikeetcx.ai/integrations/lorikeet-api): Initialise a Lorikeet voice conversation before routing the live call

Knowledge bases:
- [Confluence](https://www.lorikeetcx.ai/integrations/confluence): Access Confluence documented knowledge and procedures
- [Google Docs](https://www.lorikeetcx.ai/integrations/google-docs): Access documents, sheets and presentations from Google Workspace
- [Guru](https://www.lorikeetcx.ai/integrations/guru): Access verified company knowledge in Guru
- [Notion](https://www.lorikeetcx.ai/integrations/notion): Access your Notion workspace as a knowledge base

Tools and data:
- [MCP](https://www.lorikeetcx.ai/integrations/mcp): Extend agent capabilities with custom tools and data sources over the Model Context Protocol
- [SendGrid](https://www.lorikeetcx.ai/integrations/sendgrid): Deliver transactional emails and track engagement
- [Shopify](https://www.lorikeetcx.ai/integrations/shopify): Sync order data and customer info to power commerce experiences
- [Stripe](https://www.lorikeetcx.ai/integrations/stripe): Process payments and update customer records in real time

## Reports and webinars

- [The Support Exception](https://www.lorikeetcx.ai/content/the-support-exception): Survey of 2,015 recent AI-support users across the US, UK and Canada; views of AI support improved close to 2 to 1 while general AI sentiment fell. Full text at https://www.lorikeetcx.ai/content/the-support-exception/read
- [Consumer Attitudes Toward AI Customer Support](https://www.lorikeetcx.ai/content/consumer-attitudes-toward-ai-cs-report): Survey of 1,083 consumers across the US and Europe on the gap between what people say they want from support and what they choose. Full text at https://www.lorikeetcx.ai/content/consumer-attitudes-toward-ai-cs-report/read
- [Webinar: AI-Powered Customer Engagement in Insurance](https://www.lorikeetcx.ai/webinar/ai-customer-engagement-in-insurance): With speakers from SageSure, QBE Ventures and Lorikeet
- [Webinar: Claude Code 201 for CX and Ops leaders](https://www.lorikeetcx.ai/webinar/claude-code-201): What changes when Claude Code goes from individual use to a team rollout

## Customer Stories

- [Hnry](https://www.lorikeetcx.ai/customer-stories/how-hnry-went-from-zero-to-70-automation-through-the-hardest-week-of-the-year): Hnry went live with Lorikeet from a baseline of zero automation and reached around 70% automation in the peak week of the Australian financial year.
- [Taptap Send](https://www.lorikeetcx.ai/customer-stories/how-taptap-send-supports-remittance-customers-across-80-markets-with-ai): How Taptap Send is using Lorikeet's AI agents to deliver fast, multilingual remittance support across 35 send markets and 80+ receive markets.
- [Firm360](https://www.lorikeetcx.ai/customer-stories/how-firm360-turned-its-support-stack-into-a-self-improving-system-with-ai): Firm360 uses Lorikeet to handle support across 5 workflows and automatically close knowledge base gaps every two weeks - support that improves itself.
- [Carmoola](https://www.lorikeetcx.ai/customer-stories/how-carmoola-resolves-60-of-support-end-to-end-with-lorikeet): Carmoola’s AI agent Katie resolves 60% of inbound conversations end-to-end, up from 30%, while keeping every car-finance customer warm and on-brand.
- [Wonderschool](https://www.lorikeetcx.ai/customer-stories/how-wonderschool-answers-every-parent-call-with-ai): How Wonderschool's Helping Hands line went from a 10% answer rate to 100% in 30 days with Lorikeet's voice AI, grounded in live marketplace data.
- [Arbor](https://www.lorikeetcx.ai/customer-stories/lorikeet-helped-arbor-automate-complex-support-flows-across-13-states): Lorikeet helped Arbor automate complex support flows across 13 states - matching human CSAT and navigating sensitive, regulated energy workflows.
- [Flex](https://www.lorikeetcx.ai/customer-stories/lorikeet-helps-flex-scale-support-with-ai-agents-that-match-urgency-with-accuracy): Lorikeet helps Flex scale support with AI agents that match urgency with accuracy - doubling CSAT and resolving rent-related tickets at record speed.
- [Summ](https://www.lorikeetcx.ai/customer-stories/how-summ-efficiently-handles-support-spikes-during-tax-time): Learn how Summ (prv. Crypto Tax Calculator) uses Lorikeet AI to handle massive support spikes during tax season - maintaining speed, accuracy, and CX quality.
- [Linktree](https://www.lorikeetcx.ai/customer-stories/learn-how-linktree-s-support-team-cut-first-response-time-to-1-minute-and-automated-complex-workflows-with-lorikeet): Learn how Linktree’s support team cut first response time to 1 minute and automated complex workflows with Lorikeet - all with full transparency and fail-safes.
- [Breeze](https://www.lorikeetcx.ai/customer-stories/how-breeze-used-lorikeet-to-build-for-support-scale-from-the-start): Discover how Breeze resolved 40% of complex support tickets autonomously in 30 days using Lorikeet - scaling CX without scaling headcount.
- [Amber](https://www.lorikeetcx.ai/customer-stories/how-amber-uses-lorikeet-to-get-the-right-tickets-to-the-right-agents-including-their-ai-agent): See how Amber uses Lorikeet to triage support tickets with 99% accuracy - reducing delays, boosting team efficiency, and improving customer satisfaction.
- [Magic Eden](https://www.lorikeetcx.ai/customer-stories/how-nft-marketplace-magic-eden-use-lorikeet): See how NFT marketplace Magic Eden improved CSAT and scaled customer support by using Lorikeet’s AI agent for fast, high-quality and complexity resolutions.
- [Eucalyptus - Topics](https://www.lorikeetcx.ai/customer-stories/how-eucalyptus-improved-operationally-with-topics): Discover how Eucalyptus used Lorikeet Topics to gain actionable insights, streamline support workflows, and improve operational efficiency.
- [Eucalyptus - Patient-first support](https://www.lorikeetcx.ai/customer-stories/how-eucalyptus-use-lorikeet-to-deliver-healthcare-support-that-puts-patients-first): Learn how Eucalyptus delivers fast, patient-first healthcare support with Lorikeet - cutting response times from 20 hours to 90 seconds with no quality loss.
- [Eucalyptus - Triage CSAT lift](https://www.lorikeetcx.ai/customer-stories/how-eucalyptus-boosted-csat-10pts-with-lorikeet-triage): Learn how Eucalyptus increased CSAT by 10 points using Lorikeet’s triage workflow to route tickets accurately and resolve support issues faster.
- [Easykind](https://www.lorikeetcx.ai/customer-stories/how-easykind-delivered-24-7-patient-support-without-increasing-headcount): How easykind scaled 24/7 patient support with Lorikeet's AI agent - 92% faster response times, no extra headcount, full compliance with Australian healthcare rules.
- [Eucalyptus - Crisis response](https://www.lorikeetcx.ai/customer-stories/how-eucalyptus-uses-lorikeet-to-turn-chaos-into-calm-during-their-biggest-moments): Learn how Eucalyptus used Lorikeet’s AI to respond to patient crises fast - deploying complex workflows and keeping CSAT stable under pressure.

## Developer resources (machine-readable)

- [OpenAPI spec - demo booking API](https://www.lorikeetcx.ai/openapi.json): Full OpenAPI description of the keyless demo booking API at book.lorikeetcx.ai.
- [auth.md](https://www.lorikeetcx.ai/auth.md): How an agent authenticates with Lorikeet - which surfaces are keyless, and the OAuth 2.1 flow for the product MCP server.
- [ai-catalog](https://www.lorikeetcx.ai/.well-known/ai-catalog.json): Typed index of every agent interface on this domain (ARD / AI Catalog).
- [api-catalog](https://www.lorikeetcx.ai/.well-known/api-catalog): RFC 9727 catalog of the same API surfaces.
- [ai-plugin manifest](https://www.lorikeetcx.ai/.well-known/ai-plugin.json): Plugin manifest for the keyless surfaces.
- [CX jobs MCP server card](https://www.lorikeetcx.ai/.well-known/mcp/server-card.json): CX + AI jobs board MCP server - Streamable HTTP at https://cx-jobs.lorikeetcx.ai/api/mcp, read-only, no auth.
- [Product MCP server card](https://www.lorikeetcx.ai/.well-known/mcp/product-server-card.json): Product MCP server - Streamable HTTP at https://api.lorikeetcx.ai/v1/mcp, OAuth 2.1.
- [index.md](https://www.lorikeetcx.ai/index.md): Markdown twin of the homepage.

## Section indexes

- [Blog posts](https://www.lorikeetcx.ai/blog/llms.txt): Every Lorikeet blog post, linked and described.
- [Articles](https://www.lorikeetcx.ai/articles/llms.txt): Every Lorikeet article, linked and described.
- [Glossary](https://www.lorikeetcx.ai/glossary/llms.txt): Every CX + AI glossary term, linked and described.
- [Competitor comparisons](https://www.lorikeetcx.ai/competitors/llms.txt): Every Lorikeet competitor comparison, linked and described.
- [Full site text](https://www.lorikeetcx.ai/llms-full.txt): The complete text of every page on lorikeetcx.ai.

## Optional

- [Full Content](https://www.lorikeetcx.ai/llms-full.txt): Complete text of all articles and glossary definitions in one file