How Lorikeet works

Lorikeet is a platform that complex and regulated businesses use to provide their customers with a universal concierge: one agent that resolves issues end-to-end across chat, email, voice and SMS.

Connect. Train. Test. Improve.

Connect and train

Start from the systems you already run

Connect your ticketing system or use Lorikeet’s chat widget, then train the agent on your business context, brand guidelines, help docs and standard operating procedures. No migration required: Lorikeet works alongside your existing tools.

Test and deploy

Simulate before a single customer conversation

Replay historical tickets and synthetic scenarios in bulk to see projected resolution quality and knowledge gaps, then deploy on the topics the agent is trained for and leave the rest with your team.

Act and improve

Resolve end-to-end, then score the results

The agent takes action through your APIs and MCP servers inside natural-language and deterministic workflows, and Coach reviews the results so you can fine-tune training and workflows to keep raising resolution quality.

Trusted by leaders in customer experience

  • “We trust Lorikeet to help us help our customers, and get them real answers.”

    Lindsay Boland

    CX AI Product Lead

  • "We were especially impressed by the way Lorikeet integrates with the tools we already use, saving us valuable time and effort."

    Millie Yang

    Co-Founder and CEO, Breeze

  • "Lorikeet’s customer satisfaction scores are now nearly on par with that of our human agents."

    Daniel Cavagnino

    Operations Manager

  • "Lorikeet’s AI agent is fantastic at connecting customers to the information they want and providing them with near-immediate answers."

    Layla Huang

    Senior Customer Support Manager

Trusted by leaders in customer experience

“We trust Lorikeet to help us help our customers, and get them real answers.”

Lindsay Boland

CX AI Product Lead

Pockets of determinism where it matters

Lorikeet pairs agentic orchestration with strictly deterministic operations: the interface is permissive, the operation is strict. Sensitive steps like payments and identity checks run as code the agent can invoke but never alter, and a team of specialist agents can coordinate with third parties by phone, SMS, email and Slack to resolve multi-party issues.

Frequently asked questions

What is Lorikeet?

Lorikeet is a platform that complex and regulated businesses use to provide their customers with a universal concierge. One AI agent works across chat, email, voice and SMS, pulls live context from your systems, follows your policies and resolves issues end-to-end, with guardrails and quality scoring built in.

How is Lorikeet different from a chatbot?

Chatbots answer from scripts and deflect what they can’t match. Lorikeet resolves: it takes action in your backend systems through workflows, handles regulated steps with deterministic code, escalates with context when human judgment is needed, and is scored on whether the issue was actually fixed.

Which channels and integrations does Lorikeet support?

Chat, email, voice and SMS are live, with voice available in the US, UK and Australia. Lorikeet integrates natively with ticketing systems like Zendesk and Intercom, and connects to your business systems through APIs, webhooks and MCP servers.

How do I test Lorikeet before going live?

With simulations. Replay your historical tickets and synthetic scenarios in bulk against the configured agent, review projected resolution quality and knowledge gaps, and only deploy the topics where the evidence holds. Rollout is staged, and everything the agent handles is scored from day one.

How does Lorikeet pricing work?

Lorikeet charges for successfully resolved conversations rather than seats or platform fees, and if you mark a resolution as bad you are not charged for it. Full details and current rates are on the pricing page.