Lorikeet 1 · Try it live

Try a ticket against the live agent.

The real Virgin Active member app with the Lorikeet chat widget embedded across three screens. Click any chat bubble. The same agent handles bookings, freezes, billing, and cancellations in production.

Try: freeze membership
Hi, I'm Joseph Chen. Can I freeze my membership for July? I'm travelling.
Try: book a tennis court
Hi, I'm Sarah Smith. Can I book a tennis court at Wimbledon for Tuesday at 6pm?
Try: cancel a class
Hi, I'm Sarah Smith. I need to cancel my 17:45 Lift Club booking at Wimbledon today.

Sample members for the demo (canned data via the lookupMember mock tool): Joseph Chen · Kensington · Off-Peak £95/mo  ·  Sarah Smith · Wimbledon · Flexi £135/mo. In production, member ID is auto-attached from the app session, so the agent skips this step.

Lorikeet 2 · Architecture

Journey of a member ticket

How Lorikeet's AI agent resolves member issues end-to-end

1
Member sends message
Via app chat, web widget, email, voice, or your ticketing system
2
Channel intake
Mode (chat / email / voice) · Escalation rules · Auto-close config
3
Brand + config loaded
Virgin Active tone · Empathy + retention rules · Region & language matching
4
Inbound guardrail
Evaluate message → pass to triage, or escalate immediately for sensitive cases
5
Intent classification
Bookings, freezes, cancellations, billing, club info, all matched against available workflows
Matched workflow
Run response SOP
FAQ fallback
Search KB
No match
Escalate to club team
6
Workflow executes
Structured decision graph or Natural Language agent follows step-by-step SOP
Tools
Booking system · Member CRM · Billing · Club rosters
Knowledge
Class info · Membership T&Cs · Club facilities
Actions
Tags · Notes · Slack · Salvage offers
7
Outbound guardrail
Check AI response against retention, T&C and tone policies → pass or escalate
8
Reply sent to member
Brand voice · Formatting · Citations · Side effects (tags, CSAT, Slack)

If member replies → loops back to step 5 with full context

If no reply → auto-resolved after idle period

Lorikeet 3 · Proof of concept

Proof of concept

Train and test AI
Integration scoping
Legal / privacy / security review
Week 0 to 1
We will:
  • Train Lorikeet's tone and brand from your guidelines
  • Run response testing over 20 to 50 example tickets
  • Plan training based on your SOPs
We need:
  • Tone of voice, SOPs, ticket corpus
  • Fast feedback on tickets
Week 1 to 2
We will:
  • Build, test and iterate on 1 to 2 agreed use cases (e.g. bookings + freezes)
  • Share learning materials with your team
  • Produce documentation to aid implementation
We need:
  • Continued feedback on AI response quality
Week 2 to 3
We will:
  • Run Lorikeet 101 training session with your champion
  • Complete any necessary security and legal reviews
  • Agree on commercial terms
We need:
  • Tech lead to align on integration plan
Week 3 to 4
We will:
  • Complete security and legal reviews
  • Kick off integration sync
We need:
  • Agreement on commercial terms and signature
Lorikeet 4 · Pricing

You only pay for resolutions

Aligned incentives by design. We both win when member tickets are resolved.

Pay only for resolved tickets

Lorikeet charges per ticket successfully resolved, as determined by you. If we don't deliver, you don't pay.

No platform or per-seat fees

No setup costs, no per-seat licenses, no monthly minimums. The only line item is resolutions.

Volume discounts

Per-resolution price decreases as volume grows. Available across email, chat, app, and voice.

Aligned incentive structure
  • You buy credits from Lorikeet up front
  • Credits are only consumed when the AI reaches the desired outcome
  • You don't pay if the AI fails and the case is passed to a human
  • Credits sized to your forecast volume. Buy top-up packs at a discount mid-contract, no surprise overages
  • Final per-resolution pricing scoped together during the pilot, based on workflow mix
1 / 4