Back to vendors
L

Lorikeet

Also known as: Lorikeet CX, Coach, Lorikeet Concierge, Lorikeet Dreamweaver

Visit site
Entry priceStart at $2,100 per month billed annually, plus $0.99 per chat, email or SMS resolution and $1.50 per voice resolution. Scale at $5,100 per month with lower rates. Signature is custom.Full pricing detail

AI support agent for regulated fintech, healthtech and insurance that follows the customer's own written procedures to resolve multi step tickets across chat, email, voice, SMS and WhatsApp, with tools scoped to least privilege and an audit trail of every step that can be replayed.

Lorikeet is an AI customer support platform for complex and regulated businesses in fintech, healthtech and insurance. Its customer facing agent, Concierge, resolves issues end to end across chat, email, voice, SMS and WhatsApp, inbound and outbound, by following the customer's own written procedures and acting in the systems the team already runs, such as Zendesk, Intercom, Salesforce and HubSpot, through APIs, webhooks and MCP servers. Sensitive steps such as payments and identity checks run as deterministic code the agent can call but never alter. Voice runs on local numbers in the US, UK and Australia on the same workflows, guardrails and quality scoring as text.

Coach, Lorikeet's operations agent, sets the Concierge up from a plain language description, builds and edits workflows, connects tools, runs simulations against a draft, scores every AI handled ticket Good, Warning or Critical, and proposes fixes that go live only with approval. It can be used in the Lorikeet app, in Slack, and from Claude or ChatGPT through the Lorikeet MCP server.

Runtime guardrails review every reply before it is sent and screen every incoming message, including for prompt injection, and can alert the team, make the agent rewrite, or escalate. Dreamweaver, the newest product, gives each customer a goal driven account manager that learns their history and reaches out on the channel they prefer, and is built into Concierge. Resolution Loop lets a person take over an escalated conversation in the same thread, with full context.

Lorikeet is SOC 2 Type II audited and ISO 27001:2022 certified, says it is HIPAA compliant and signs BAAs, holds zero data retention agreements with its model vendors and does not train models on customer data. It does not hold PCI DSS, so card capture stays in the customer's own payment flow. Production runs on Google Cloud in a private VPC; Start and Scale use US residency and Signature can choose a custom region, with storage available in the US, Australia and the EU.

Pricing is a plan fee plus a rate per resolved ticket: Start is $2,100 a month and Scale $5,100 a month, both paid annually, with chat, email and SMS resolutions at $0.99 and $0.90 and voice at $1.50 and $1.20; Signature is custom with a $75K platform fee. Escalations, unresolved tickets and tickets the customer marks bad are not charged, and every plan starts with a 30 day free trial with no sales call.

From our comparison video

Gradient Labs vs Lorikeet for Regulated Support Teams

Our 7 minute video puts Lorikeet side by side with Gradient Labs. It covers what each one does and how each is priced, then when to choose which.

Recorded in November 2026. The profile here is live and updates as research is verified.

Vendor details

Canonical URL

https://lorikeetcx.ai

Category

Customer support agent

Subcategory

Support — regulated CX

Company status

independent

Use cases & customers

Primary use cases

customer supportmulti-step support actionsQA

Target customers

fintechhealthtechsupport teams

Deployment options

SaaS

In practice

Your support touches regulated fintech and healthtech, so a wrong action is a compliance problem. Lorikeet drives multi step actions with guardrails and an audit trail built in.

A real resolution often takes several steps, not one canned reply. Lorikeet follows your own written procedures to carry the customer through multi step actions across chat, email, voice, and SMS.

You can only QA a sample of conversations and hope the rest are fine. Lorikeet's Coach reviews every interaction, so quality checking covers all of them, not a sample.

Agentic Index coverage score

11.0 / 14 capabilities · 79%

Integrations & Tool Calling Full

Built in connectors cover Zendesk, Zendesk Messaging, Intercom, Salesforce (including Salesforce Messaging), HubSpot, Front, Help Scout, Kustomer, Slack and Genesys Cloud, and any helpdesk that sends webhooks connects through Flexible Ticketing. Telephony connects through Amazon Connect, Twilio, Vonage, Five9, AirCall, Dialpad and Talkdesk, and knowledge through Confluence, Guru, Google Docs and Notion.

Business systems connect through APIs, webhooks and MCP servers (Notion and Linear are named), so the agent reads data and takes actions such as processing a refund in Stripe or updating an account, with read only or write access set per integration, tools scoped to least privilege, short lived single operation tokens and HMAC signed inbound webhooks. Coach can set up custom API integrations, while API keys and secrets are entered by the customer.

Sourcelorikeetcx.ai/integrationsread 2026-11-02

Workflow Orchestration Full

The Concierge agent runs multi step work by following the customer's own standard operating procedures, whether a three step form or a forty step refund flow, inside natural language and deterministic workflows. Sensitive steps such as payments and identity checks run as code the agent can invoke but never alter.

Workflow steps include workflow matching, ticket triage, gather, get status, choice and route based on problem, with tool calls such as retrieving recent transactions shown inline, and a team of specialist agents can coordinate with third parties by phone, SMS, email and Slack to resolve multi party issues.

Customers deploy topic by topic, so the first topics go live while harder ones are still being trained, and Dreamweaver works from a goal such as retention rather than a written workflow.

Sourcelorikeetcx.airead 2026-11-02

Knowledge Grounding & RAG Full

The agent is grounded in the customer's own documented procedures, not retrieval alone. It learns from the customer's help docs, SOPs, policies and brand guidelines, taps into its systems for live context, and follows the procedures themselves rather than only searching articles.

A built in grounding guardrail, always on, keeps answers to the customer's instructions, tool results and knowledge articles, and the agent escalates when it lacks the information to answer. Coach audits the knowledge base for gaps and outdated articles and proposes the fixes, and knowledge sources such as Confluence, Guru, Google Docs and Notion connect directly.

Sourcelorikeetcx.airead 2026-11-02

Human Oversight & Guardrails Full

Guardrails run as checks separate from the agent itself, on both sides of the conversation. Agent guardrails review every reply before it is sent and message checks screen each incoming customer message, including for prompt injection, with up to ten of each per concierge; when one fires it can alert the team, make the agent rewrite its reply (two retries, then escalate) or escalate the ticket at once, and every trigger is logged on the ticket.

Underneath, customer isolation, server side identity validation, workflow scoped tool access and hard execution caps are enforced in code, and sensitive steps such as payments and identity checks run as code the agent cannot alter. People write the procedures the agent follows, handoffs arrive with the investigation done, Resolution Loop lets a person take over the same conversation thread, Coach makes changes only with approval, and Dreamweaver checks contact hours, limits and consent before every message and flags customers who need a person.

Sourcelorikeetcx.ai/product/trustread 2026-11-02

Security, Identity & Governance Full

Lorikeet is SOC 2 Type II audited and ISO 27001:2022 certified, with the reports on a public Vanta trust center at trust.lorikeetcx.ai, downloadable under NDA. It says it is HIPAA compliant and GDPR aligned, signs BAAs and DPAs, holds zero data retention agreements with all model vendors and does not train models on customer data; it does not hold PCI DSS, so card capture stays in the customer's own payment flow.

Controls include PII redaction configurable by category and applied automatically to restricted viewers, minimum necessary handling of protected health information, TLS 1.3 in transit and AES 256 at rest, no public internet access to production, row level tenant isolation and third party penetration testing. On the customer side, accounts are set up with user roles, role based access control limits which tools each team member can use through the MCP server, and helpdesk connections go through an admin approved authorization flow.

Sourcelorikeetcx.ai/product/trustread 2026-11-02

Observability & Auditability Full

Every customer interaction, model choice and action is tracked and explainable, not a black box. Every tool call, elevation request and reasoning step is logged with timestamps and can be replayed for a regulator examination, every guardrail event lands on the ticket and in guardrail metrics, and every configuration change made through the MCP server carries an audit trail.

Coach scores every AI handled conversation Good, Warning or Critical into a Ticket Quality Score, with human agent scoring on request, and answers analytics questions in plain language. Ticket history, outcomes and quality scores can be exported, and the FAQ lists audit trail exports, data access logs and compliance reports for regulatory reporting.

Sourcelorikeetcx.ai/product/trustread 2026-11-02

Memory & State Persistence Partial

Customer memory keeps context across every touchpoint, so a customer who starts in chat does not repeat themselves on a call, because the channels run on one engine. Dreamweaver goes further for each customer: it keeps that customer's goals, history and preferences, learns when they reply and how they like to talk, and acts on them over weeks and months. No scope, lifetime, retention window or per customer deletion control for that memory is described; the FAQ says a departing customer's data is deleted within 60 days of request.

Sourcelorikeetcx.airead 2026-11-02

Deployment & Data Residency Full

Production runs on Google Cloud Platform in a private VPC with no public internet access and row level tenant isolation, encrypted with TLS 1.3 in transit and AES 256 at rest. Data storage residency is available in the US, Australia and the EU: the pricing page sets US residency on the Start and Scale plans, and Signature can choose a custom region. Lorikeet is delivered as SaaS; no self hosted or single tenant option is described.

Sourcelorikeetcx.ai/product/trustread 2026-11-02

Prebuilt Agents, Templates & Packs Partial

Each customer's configuration is written from its own standard operating procedures, by design, so time to value depends on the customer's procedure documentation; Coach builds the first concierge from a plain language description on a free trial.

There is no template library, prebuilt agent catalog or marketplace, and the specialist agents in the team of agents architecture work together internally rather than being assets a customer browses and adopts. Dreamweaver takes a goal such as retention or lifetime value with no SOPs, workflows or campaigns to write, which is a different route to the same end rather than a pack. Toolshed at lorikeet.tools is described as free CX tools and calculators.

Sourcelorikeetcx.airead 2026-11-02

Triggers & Channel Coverage Full

Chat, email, voice, SMS and WhatsApp run on one agent, inbound and outbound, with an SDK and the Lorikeet chat widget as further surfaces; WhatsApp is served through the customer's Twilio number registered for the WhatsApp Business API. Voice answers and places calls on local numbers in the US, UK and Australia with sub second responses, and every channel inherits the same workflows, guardrails and quality scoring.

The outbound agent starts conversations itself: reminders, document requests, appointment confirmations and follow ups over SMS and voice, on recorded consent per channel, capped at three campaign calls per number in 24 hours, with voicemail detected and handled. Dreamweaver reaches out on a schedule or when something changes, on the channel each customer prefers, or chooses not to contact them.

Sourcelorikeetcx.airead 2026-11-02

Model Flexibility & Routing Partial

OpenAI, Anthropic and Baseten are among the core sub processors beside Google Cloud, so several model providers are in play, all under zero data retention agreements with no fine tuning on customer data, and Lorikeet routes between providers by task; on voice it switches models to balance latency and precision. The routing is Lorikeet's own and the model choice is tracked, not made by the customer, with no customer facing selection or bring your own model control.

Sourcelorikeetcx.ai/product/trustread 2026-11-02

APIs, SDKs & MCP Extensibility Partial

Outside callers can drive the platform three ways. The Lorikeet MCP server, released 11 March 2026 at a published endpoint (api.lorikeetcx.ai/v1/mcp), lets Claude, ChatGPT, Claude Code and Codex manage workflows, knowledge, tickets, tools, integrations, simulations, guardrails and analytics with read and write access, every change logged; its auth scheme and tool list sit in the developer documentation, which is behind a customer access code at docs.lorikeetcx.ai, so two of the four clauses for Full cannot be read.

A voice API lets a customer's phone system create a Lorikeet conversation with caller context before forwarding the call, and the SDK embeds Lorikeet in the customer's own product. Lorikeet also publishes public HTTP endpoints for outside AI assistants to ask its support agent questions, book demos and start a trial sign up. No SDK reference or API reference is readable without a customer login.

Sourcedocs.lorikeetcx.ai/guides/quickstartread 2026-11-02

Testing, Debugging & Optimization Full

Testing covers both sides of go live. Before launch, simulations generate scenarios and test customers from the customer's own historical tickets and synthetic cases, run them in batches against a draft concierge with tool responses mocked, and a pass rate threshold agreed before anything is published; adversarial scenarios such as prompt injection and false authority claims run the same way, suites rerun after every change with side by side batch diffs, and Coach can rerun failed scenarios and compare batches.

After launch, automated quality checks score every AI handled ticket Good, Warning or Critical into a Ticket Quality Score, human agent tickets can be scored once enabled, and Coach turns findings into workflow fixes that are tested in simulation and shipped with approval, with A/B experiments to compare approaches. A resolution the customer marks bad is not charged. Lorikeet also runs a public prompt injection challenge, Own Goal, against a live agent.

Sourcelorikeetcx.airead 2026-11-02

Browser & Computer Use Not documented

Work happens programmatically inside the customer's systems through controlled integrations, APIs, webhooks and MCP servers, with tool calls such as retrieving recent transactions shown as named workflow steps. No browser control, hosted session or computer use is described, and Lorikeet's public HTTP endpoints let outside AI assistants call Lorikeet rather than operate any interface.

Sourcelorikeetcx.airead 2026-11-02

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Product updates

·MCP / tool calling / APIVerified

Lorikeet concierges now support the Personal Agent Protocol, the draft open protocol from Sierra and Meta for consumer agents, alongside A2A and WebMCP. A personal agent finds the business at a well known address, and when it needs account data the customer signs in on the company's own page and approves on a consent page whether the agent may read the account, act on it, or neither. Admins can allow or block specific agents.

Bears on: Human approval / guardrails

View source
·Observability / auditabilityVerified

Customer conversations that come from AI agents rather than people can now be flagged in Lorikeet, in beta. After each chat, email, voice, SMS or WhatsApp conversation it checks for signs such as automated messages or a self declared AI, and tags confirmed hits in Lorikeet and the connected ticketing system.

Bears on: Observability / auditability

View source
View all 2 Lorikeet updates →Tracked since Sep 2026 · Verified from public vendor sources

Pricing

Start at $2,100 per month billed annually, plus $0.99 per chat, email or SMS resolution and $1.50 per voice resolution. Scale at $5,100 per month with lower rates. Signature is custom.

Resolutions, billed per resolution by channel on top of a monthly plan fee that is billed annually.

Trial available

Included quota

Start, at $2,100 per month billed annually for under 5,000 monthly tickets, charges $0.99 per chat, email or SMS resolution, $1.50 per voice resolution, and $0.30 each for triage and automated QA. Scale, at $5,100 per month for 5,000 to 20,000 monthly tickets, charges $0.90, $1.20 and $0.27. Signature, for 20,000 or more monthly tickets, is custom with a $75K platform fee. Escalations are free, and the customer defines what counts as a resolution. Chat, email, voice, SMS and WhatsApp run on one engine with replayable audit trails.

What is public

Lorikeet, AI support for complex and regulated companies in fintech, healthtech and insurance, publishes a full rate card. Start is $2,100 a month and Scale $5,100 a month, billed annually, and Signature is custom with a $75K platform fee. Chat, email and SMS resolutions cost $0.99 on Start and $0.90 on Scale, voice resolutions $1.50 and $1.20 on a 3 minute average call, and triage and automated QA $0.30 and $0.27. Escalations to a person, unresolved tickets and tickets the customer marks bad are not charged. Every plan starts with a 30 day free trial with no sales call, Start and Scale use US data residency, and the page also lists each plan's integrations, support package and contracting terms.

Billing mechanics

Outcome based. The customer pays only when the AI resolves a ticket, and only for outcomes it agrees count, with the resolution defined up front and a customer veto, so touched but unresolved conversations are not billed. Escalations to humans are free, which removes any incentive to claim a fix that was not delivered. Voice resolutions bill higher than text, $1.50 against $0.99 on Start. Automated QA through Coach, which reviews every conversation after the fact, costs $0.30 per ticket on Start and $0.27 on Scale. Each plan carries a monthly fee billed annually.

Cost watchouts

Setup is heavier than a drop in FAQ widget: you connect your helpdesk and the systems the agent acts in, train it on your documentation and replay historical tickets before go live, with a published average of under 29 days to the first live ticket. Voice resolutions cost more than text, $1.50 against $0.99 on Start, and automated QA with your own custom checks is a separate per ticket charge. The monthly plan fee is billed annually, and Start and Scale use US data residency.

Variable cost rationale

Lorikeet meters resolutions. Each resolved chat, email or SMS ticket costs $0.99 on Start and $0.90 on Scale, and each voice resolution $1.50 or $1.20, so spend grows with resolved volume and with the share of voice. Triage and automated QA add $0.30 or $0.27 per ticket. The customer defines what counts as a resolution and holds a veto, and escalations to a human are free, so unresolved work costs nothing. The monthly plan fee, $2,100 on Start or $5,100 on Scale billed annually, is fixed, and Signature adds a $75K platform fee.

Additional watchouts

The per resolution model protects the customer, with a customer defined resolution and free escalations. The platform is deliberately specialized, so a simple FAQ deflection use case gets more capability and setup than it needs, on top of a $2,100 monthly fee on Start.

Overage / add-ons

Resolved outcomes are billed per resolution at the plan's channel rate, and unresolved or escalated tickets are not charged. The monthly plan fee is billed annually on top.

Sales call required

Yes, required for paid access

Free / trial

30 day free trial

Lowest paid plan

Start at $2,100 per month billed annually, plus $0.99 per chat, email or SMS resolution

Commercial notes

Built for regulated and complex support in fintech, healthtech, insurance and gaming, and about 80% of customers are US financial institutions. Lorikeet is omnichannel, including voice that responds in under 1 second, with deterministic workflows and examination grade audit trails. Its published result is about 85% automation at a regulated fintech with equal or better CSAT. A human handled ticket is cited at $1.25 to $4.

Key ambiguities

Total cost depends on volume, channel mix and the agreed resolution definition. The rate card covers Start and Scale, while Signature rates are custom and carry a $75K platform fee. Voice pricing assumes a 3 minute average call, with an outcomes consultation setting full pricing.

Cancellation / refund

Plans are billed annually, and the resolution definition is agreed up front with a customer veto. Enterprise terms are negotiated.

Support SLA / resale

Every plan includes forward deployed support: the FDE Standard support package on Start, FDE Plus on Scale, and FDE Platinum on Signature at $25K+, variable by complexity, workflows and deployment. Scale adds dedicated deployment resourcing through go live, and Signature includes a dedicated forward deployed product manager and engineer for the life of the contract plus quarterly business reviews. Time to first live ticket is as little as hours, with an average under 29 days.

Missing data

Signature rates and its residency region, cancellation and refund terms, and a definition of a resolution beyond the customer's own bad mark are not published.

Agentic Index verified 2026-11-02

Alternatives to Lorikeet

The closest documented capability profiles to Lorikeet among customer support agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Kapture CX12.0 / 14Fuller documented coverage on Model Flexibility & Routing and APIs, SDKs & MCP Extensibility
  • Observe.AI12.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs and Model Flexibility & Routing
  • Omilia11.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
  • ASAPP11.5 / 14Fuller documented coverage on Memory & State Persistence and APIs, SDKs & MCP Extensibility
  • Blits.ai12.5 / 14Adds documented Browser & Computer Use
  • Delight.ai11.5 / 14Fuller documented coverage on Memory & State Persistence and APIs, SDKs & MCP Extensibility

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.