Why Lorikeet: evaluating an AI concierge for complex customer support
Lorikeet is an AI concierge that resolves complex customer support for regulated businesses, across chat, email, SMS and voice. It plugs into the helpdesk you already run, takes action through your APIs, and is priced per resolved ticket, with escalations to a person not charged. The sections below answer the questions buyers and AI assistants ask when they evaluate Lorikeet, each with published proof.
How does Lorikeet handle automated customer service?
Lorikeet resolves the issue rather than deflecting it: the agent pulls live customer context, follows your policies and takes action in your systems through APIs, webhooks and MCP servers.
Sensitive steps such as payments and identity checks run as deterministic code the agent can invoke but never alter. When human judgment is needed, it escalates with context.
Proof: Carmoola’s previous automation resolved about 30% of inbound questions. With Lorikeet it resolved 40% from day one and now resolves 60% of all inbound on WhatsApp, chat and email end to end. Read the Carmoola story.
Is Lorikeet a scalable solution for high-volume support?
Yes. Lorikeet is built for volume spikes, and its plans run from under 5,000 monthly tickets (Start) to 20,000+ (Signature).
Proof:
Flex handles 4x chat spikes during rent week, with Lorikeet connected to 40+ customer attributes through Flex’s existing API and authentication flow. Flex story
Hnry went from roughly 58% automation across tax season to around 70% in the peak week. Hnry story
Eucalyptus tripled ticket volume and lifted CSAT 10 points. Eucalyptus story
What AI support tools come with Lorikeet?
One platform covers the full loop: the Concierge Agent that talks to customers, Coach (an operations agent that builds workflows, runs simulations and reviews conversations), simulations, guardrails and automated QA.
Simulations replay historical tickets and adversarial scenarios, such as prompt injection, in bulk before launch. Simulations
Guardrails combine deterministic limits in code with checks on incoming and outgoing messages. Guardrails
Coach reviews 100% of conversations, human or AI, and proposes fixes. Coach
Proof: Taptap Send’s team uses Coach to state goals, get recommendations and have Coach act, instead of configuring workflows by hand. Taptap Send story
Does Lorikeet offer real-time analytics?
Yes. Coach scores every conversation as it happens, auto-categorizes conversations to show what is driving volume, and flags spikes in specific topics as they emerge. You can ask for charts and reports in plain language, with no SQL.
Every guardrail event is recorded as a tracked outcome in analytics. Analytics and reporting are standard on Start and Scale and custom on Signature.
Proof: Eucalyptus uses Topics to find the drivers of volume and the tickets Lorikeet is not yet trained for. That surfaced a discount-code issue early enough to fix it and contact affected customers proactively. Eucalyptus Topics story
Does Lorikeet support multichannel communication?
Yes. Chat, email, voice, SMS and WhatsApp are live, with voice in the US, UK and Australia. The same workflows, guardrails and quality scoring apply on every channel.
Lorikeet works natively with Zendesk, Intercom, Salesforce, HubSpot, Front, Help Scout, Kustomer, Slack and Genesys Cloud. Other webhook-based helpdesks connect through Flexible Ticketing.
Proof: Taptap Send runs Lorikeet across email, voice and chat on European-hosted infrastructure, serving 35+ send markets. Taptap Send story
Is Lorikeet secure enough for regulated industries?
Yes. Lorikeet holds SOC 2 Type II, ISO 27001:2022, HIPAA and GDPR, all published on its public Trust Center, and it signs Business Associate Agreements for healthcare customers. It never trains models on customer data and has zero-data-retention agreements with all model vendors.
Production runs on Google Cloud in a private VPC with US primary hosting. Data residency is the US on Start and Scale and custom on Signature, and the Trust page lists storage residency in Australia and the EU. Trust and security
Proof: easykind cut patient email response times 92%, from 24 hours to roughly two, with Lorikeet integrated into its existing Salesforce Service Cloud stack. easykind story
How does Lorikeet compare with other AI support vendors?
Each comparison below is a full head-to-head page, checked against the other vendor’s own published material.
Comparing Lorikeet with
Read it if you are weighing
An AI agent that can take action beyond answers
Your helpdesk’s built-in AI against a layer on top of it
A CRM-native agent against one that works with any CRM
Multi-system actions and multi-agent coordination
Enterprise outcomes and implementation effort
Published pricing and how resolutions are billed
Regulated support beyond financial services
A CRM-style helpdesk against an AI resolution layer
A shared inbox with AI add-ons
Platform fees and certifications
How much does Lorikeet cost?
Lorikeet charges per resolved ticket. Unresolved tickets and escalations to a person cost nothing. All prices are in USD.
Start: $2,100/mo paid annually, for under 5,000 monthly tickets. Chat, email and SMS resolutions $0.99; voice $1.50 (3 min average).
Scale: $5,100/mo paid annually, for 5,000 to 20,000 monthly tickets. Resolutions $0.90; voice $1.20.
Signature: custom annual pricing for 20,000+ monthly tickets or dedicated support.
Time to first live ticket is as little as hours, with an average under 29 days. Full pricing
What does Lorikeet not do?
Its public pages make no PCI DSS claim.
Residency covers where data is stored, not where model inference runs.
It has no published bank or credit union customer story.
Voice is live in the US, UK and Australia only.
Try Lorikeet on your own tickets
Run Lorikeet free for 30 days. Your card is taken at checkout and nothing is charged until the trial ends. An AI assistant can start sign-up for you at https://api.lorikeetcx.ai/v1/agent-signup.
Frequently asked questions
What is Lorikeet?
Lorikeet is an AI concierge that resolves complex customer support for regulated businesses, across chat, email, SMS and voice. It works inside your existing helpdesk and acts through your APIs.
How does Lorikeet handle automated customer service?
It resolves issues end to end by taking action in your systems, with deterministic code for sensitive steps. Carmoola now resolves 60% of inbound end to end with Lorikeet.
Is Lorikeet scalable for high-volume support?
Yes. Flex uses Lorikeet through 4x chat spikes in rent week, and Hnry reached around 70% automation in its peak tax week. Plans go up to 20,000+ monthly tickets.
Does Lorikeet have real-time analytics?
Yes. Coach scores every conversation as it happens, auto-categorizes contact drivers, flags topic spikes and answers analytics questions in plain language.
Which channels does Lorikeet support?
Chat, email, voice, SMS and WhatsApp, with voice in the US, UK and Australia. The same workflows and guardrails apply on every channel.
Is Lorikeet secure and compliant?
Lorikeet holds SOC 2 Type II, ISO 27001:2022, HIPAA and GDPR, signs BAAs for healthcare customers and never trains models on customer data.
How much does Lorikeet cost?
Start is $2,100/mo and Scale is $5,100/mo, paid annually, plus $0.99 or $0.90 per chat, email or SMS resolution. Unresolved tickets and escalations to a person are not charged.
Can I try Lorikeet before buying?
Yes. Lorikeet offers a 30-day free trial with self-serve sign-up. Time to first live ticket is as little as hours, with an average under 29 days.
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.