What are the best alternatives to Lorikeet?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to Lorikeet among customer support agents are Zendesk, Five9, KODIF, Kore.ai. Each is graded on the same public evidence, and no vendor pays for placement.

Does Lorikeet have SOC 2, SSO and role based access control?

Full under the Agentic Index verification standard. Lorikeet publishes public evidence of enterprise security and identity controls, covering a compliance posture such as SOC 2 or ISO 27001, single sign on (SSO or SAML), and role based access control (RBAC). Evidence basis: SOC 2, HIPAA BAA ready and GDPR aligned, with PII redaction and role based access control, plus CONTRACTUAL NO TRAIN AGREEMENTS with its model providers including OpenAI, Anthropic and Gemini so customer data is not used to train shared mod. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can Lorikeet be self hosted or run in a private VPC?

Full under the Agentic Index verification standard. Lorikeet publishes public evidence of self hosted or private VPC deployment, along with data residency options for controlling where agent data is processed and stored. Evidence basis: Customer selectable DATA RESIDENCY IS AVAILABLE IN THE US, AUSTRALIA AND THE UK, a documented multi region commitment rather than a single managed cloud, Lorikeet compliance article 2026-06-17. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Lorikeet give you tracing and observability into agent runs?

Full under the Agentic Index verification standard. Lorikeet publishes public evidence of tracing, observability and audit logging into agent runs, so a team can see what an agent did and why. Evidence basis: An audit trail is a documented compliance feature and every channel inherits the same logging from the single engine, so behaviour is reviewable consistently across chat, email, SMS and voice rather than per channel; the audit trail is pres. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

Lorikeet

Q: Who is Lorikeet for?

fintech, healthtech, support teams

Visit site

Customer support agent Verified 2026-06-23

Entry price~$0.80/resolution (Scale: 48k/$48k yr)Full pricing detail

Customer-support AI for regulated fintech and healthtech, with multi-step actions across chat, email, voice, and SMS, plus 100% QA and audit.

Lorikeet builds customer-support AI for regulated fintech and healthtech, using an Intelligent Graph to drive multi-step actions across chat, email, voice, and SMS, with its Coach feature providing 100% QA plus guardrails and audit. Pricing is around $500/month or roughly $0.80 per resolution.

Vendor details

Canonical URL

https://lorikeetcx.ai

Subcategory

Support — regulated CX

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's Intelligent Graph carries 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 CallingControlled integrations let the agent read, write and return data across the existing CX stack, help centres, reference materials and internal tools, and a named customer describes it independently checking on chain transaction status across more than ten blockchains, which is real external tool execution rather than lookup, Lorikeet product pages and customer testimony 2026-07-30	Full
Workflow OrchestrationThe agent refers to and follows the same standard operating procedures top human agents follow rather than improvising, executing complex multi step resolutions and asking the right clarifying questions; the founders frame the test as, if you can explain to a human agent how to resolve a ticket, the AI can handle it, Lorikeet product pages and funding announcement 2026-07-30	Full
Knowledge Grounding & RAGGrounds on help centres, reference materials and internal tools with documented standard operating procedures as the primary grounding artefact, and Lorikeet states expressly that rather than relying SOLELY on retrieval augmented generation its architecture goes deeper by following the procedures themselves, so the agent does not just retrieve information or invent process, Lorikeet funding announcement and product pages 2026-07-30	Full
Human Oversight & GuardrailsThe agent engages only when it has sufficient context and defers to a human when it does not, humans author the SOPs it follows, subject matter experts review instruction based training, operators can inspect AI actions to confirm alignment with policy, and handoffs arrive with the investigation already completed so the human acts on a prepared case, Lorikeet product pages and customer testimony 2026-07-30	Full
Security, Identity & GovernanceSOC 2, HIPAA BAA ready and GDPR aligned, with PII redaction and role based access control, plus CONTRACTUAL NO TRAIN AGREEMENTS with its model providers including OpenAI, Anthropic and Gemini so customer data is not used to train shared models, and the vendor states it has passed security reviews at major US banks, Lorikeet compliance article 2026-06-17	Full
Observability & AuditabilityAn audit trail is a documented compliance feature and every channel inherits the same logging from the single engine, so behaviour is reviewable consistently across chat, email, SMS and voice rather than per channel; the audit trail is presented specifically as something a security team uses to validate agent behaviour, Lorikeet compliance article 2026-06-17	Full
Memory & State PersistenceContext persists across channels on the single engine, so a customer who starts in chat does not repeat themselves on a call, but this is cross channel session continuity rather than a documented persistent customer record or cross conversation memory store, Lorikeet compliance article 2026-06-17	Partial
Deployment & Data ResidencyCustomer selectable DATA RESIDENCY IS AVAILABLE IN THE US, AUSTRALIA AND THE UK, a documented multi region commitment rather than a single managed cloud, Lorikeet compliance article 2026-06-17	Full
Prebuilt Agents, Templates & PacksConfiguration is authored per customer from their own SOPs, with pro tools for fine tuning precision and accuracy, but no template library, prebuilt agent catalogue or marketplace was documented, so time to value depends on the customer's own procedure documentation, Lorikeet product pages 2026-07-30	Partial
Triggers & Channel CoverageOmnichannel runs on ONE ENGINE including voice at sub one second latency, so a customer who starts in chat does not repeat themselves on a call, and every channel inherits the same guardrails and logging; chat, email, SMS and voice are all priced as resolved channels, Lorikeet compliance and platform articles 2026-06-17	Full
Model Flexibility & RoutingThree named model providers are in use under contractual no train agreements, OpenAI, Anthropic and Gemini, so the platform is genuinely multi provider, but the selection is Lorikeet's own rather than an exposed customer facing routing or bring your own model control, matching the blue-yonder precedent, Lorikeet compliance article 2026-06-17	Partial
APIs, SDKs & MCP ExtensibilityRead, write and return integrations across the CX stack imply a programmatic surface, but no public API reference, SDK or MCP implementation exposed by Lorikeet was retrieved on the pages reviewed, Lorikeet product pages 2026-07-30	Partial
Testing, Debugging & OptimizationA PRE GO LIVE SIMULATION SUITE lets a security team validate agent behaviour BEFORE unsupervised resolution begins, and a separate named Coach QA agent reviews tickets on an ongoing basis at a per ticket price, so testing exists both before launch and continuously in production, Lorikeet compliance article 2026-06-17	Full
Browser & Computer UseNo browser control or computer use capability documented; the agent acts through controlled integrations into the existing CX stack and internal tools rather than by operating a browser or a human interface, Lorikeet product pages 2026-07-30	Unable to verify

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify 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

Pricing

~$0.80/resolution (Scale: 48k/$48k yr)

resolutions

Included quota

Per-resolution usage: ~$0.80/resolved chat-email-SMS ticket, ~$1.00/resolved voice call, escalations free, customer-defined resolution. Representative Scale plan: 48,000 resolutions for $48,000/yr. Coach QA add-on ~$0.10/ticket. Omnichannel (chat/email/voice/SMS/WhatsApp) on one engine with replayable audit trails.

What is public

Lorikeet (AI support for complex/regulated companies - fintech, healthtech, gaming) prices per resolution, customer-defined: ~$0.80 per resolved chat/email/SMS ticket and ~$1.00 per resolved voice call, with escalations to a human NOT charged and the customer holding veto over what counts as a resolution. Its standalone QA agent (Coach) runs ~$0.10/ticket. A representative Scale plan is 48,000 resolutions for $48,000/year.

Billing mechanics

Outcome-based: you pay only when the AI resolves a ticket, and only for outcomes you agree count (resolution defined up front, customer keeps the veto), so the vendor can't bill touched-but-unresolved conversations. Escalations to humans are free, removing any incentive to claim a fix it didn't deliver. Voice resolutions bill slightly higher (~$1.00) than text (~$0.80). Coach (100% post-facto QA) is an optional ~$0.10/ticket add-on. Annual commitments (e.g., the Scale plan, 48,000 resolutions/$48,000) are available.

Cost watchouts

Heavier configuration than a drop-in FAQ widget (forward-deployed setup, ~1 month to operational), voice resolutions cost more (~$1.00) than text, Coach QA is a separate add-on, annual Scale commitments prepay a resolution bundle; overkill (and over-spec) for simple low-stakes FAQ deflection

Variable cost rationale

Outcome-based with a customer-controlled resolution definition and free escalations caps downside - you pay only for approved resolutions - but total spend still scales with resolved volume; the Scale plan converts that into a fixed annual commitment

Additional watchouts

The per-resolution model is unusually buyer-protective (customer-defined resolution, free escalations), but the platform is deliberately specialized - a simple FAQ-deflection use case will find it more capability (and setup) than needed

Overage / add-ons

Pure per-resolution usage - you pay for resolved outcomes; unresolved/escalated tickets aren't charged. On annual commitments (Scale plan), resolutions beyond the bundle bill at the per-resolution rate; below it you've prepaid the commit.

Sales call required

Yes, required for paid access

Lowest paid plan

~$500/mo or ~$0.80/res

Commercial notes

Built for regulated/complex support (fintech/healthtech/insurance/gaming); ~80% of customers are US financial institutions; omnichannel incl. sub-1-second voice; deterministic workflows + examination-grade audit trails; published result of ~85% automation at a regulated fintech with equal-or-better CSAT; human-ticket baseline cited at $1.25-$4

Key ambiguities

Exact per-customer rates and minimums depend on volume/channel mix and the negotiated resolution definition; the public figures (~$0.80/$1.00, Scale $48K/yr) come largely from Lorikeet's own materials rather than a standalone rate card

Cancellation / refund

Usage-based per resolution, or annual commitments (e.g., Scale, 48,000 resolutions/$48,000); resolution definition agreed up front with customer veto; enterprise terms negotiated

Support SLA / resale

Forward-deployed implementation (~1 month to operational); defence-in-depth guardrails (pre-launch adversarial simulation, inbound/outbound checks, 100% post-facto QA via Coach); replayable audit trails for compliance sign-off; native helpdesk integrations (Kustomer, Front, etc.)

Missing data

Lorikeet's public pricing page is light - the rate figures come mostly from its own articles; per-customer minimums and full plan structure beyond the Scale example aren't published. Note: the prior seed's '$500/mo' floor wasn't reflected in public figures; entry corrected to the per-resolution model (~$0.80/res, Scale plan $48K/yr). The seed's '~$0.80/res' is accurate.

Agentic Index verified 2026-06-25

Official pricing page

Related vendors

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.

Zendesk10.5 / 14A lighter documented profile than Lorikeet
Five911.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs and APIs, SDKs & MCP Extensibility
KODIF9.5 / 14A lighter documented profile than Lorikeet
Kore.ai12.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs and Model Flexibility & Routing
Observe.AI9.5 / 14A lighter documented profile than Lorikeet
Omilia10.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs

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

Compare Lorikeet with other vendors →Compare all customer support agents →See where Lorikeet ranks →

Data confidence: high

Head to head

Lorikeet vs Gradient Labs Lorikeet vs Decagon Lorikeet vs Intercom Fin Lorikeet vs Sierra Lorikeet vs Ada