×
Lorikeet Overview for PartyOne
The AI concierge that gets it done. Built for membership businesses where every member expects the room to know their name.
Prepared for Swaminathan Thopa Krishnaswami · 5 June 2026
Alex Holder, Lorikeet
2, The Opportunity
The Opportunity
Let AI handle every curious download and routine question, so your concierge team focuses on the paid members who joined for the white-glove service.
The downloads who haven't paid yet still ask questions. Let AI answer them instantly, in brand voice, without a single human touch. Your team's time stays with the 100 paid members.
Members message from venues at 3am in Ibiza or Singapore. The concierge replies instantly on the channel they're already in. No queues, no business-hours gaps.
You said you don't want more than ten people on CX. AI handles tier-one and tier-two queries so 2-per-shift can serve 100, 500, or 5,000 members without linear hiring.
Your CX team becomes the upsell layer — Gold to Platinum, one-off events to memberships. Lorikeet handles the volume; your humans build relationships with the members who'll pay you $50k/year over five years.
3, State of play
State of Play at PartyOne
- Memberships launch in 1–2 weeks; payment gateway is live, SOPs are written, hiring 3–4 CX (2-per-shift × 2 shifts) before scale
- ~1,000 curious downloads + ~100 paid members in the first 90 days; CX team capped at 10 even as you grow
- Channels you said matter, in-app chat and WhatsApp first, voice later for Solitaire-tier members in transit
Three queries you can't afford to send to a human:
- "What does membership get me?" The free downloads asking the basics. High volume, low stakes, must answer in brand voice and route into a Solitaire/Platinum conversation when they're ready.
- Booking changes, add guests, swap tables, get a refund. Multi-system: needs member tier, booking, payment processor, guest list. The agent has to act, not just answer.
- Lost items + venue incidents, a member messages from a venue at 2am. The agent captures the context properly, logs it, and routes to a human concierge with everything they need.
4, Use cases for the demo
Four use cases, built and live
A working PartyOne sandbox: 5 mock tools, 6 KB articles, 4 NLW workflows. Try every one in the next slide.
"What does membership get me?" The agent answers grounded in the PartyOne knowledge base, names tier benefits and guest allowances precisely, and offers to book a concierge call when the prospect is ready to join.
Member asks "where is my refund?" The agent identifies them, finds the cancelled booking's transaction, reads payment-processor status, and gives a concrete settlement date. No generic "let me check".
"Add Priya and Jordan to my Saturday at Marquee." The agent reads the member's tier, validates against their guest allowance, looks up the booking, writes the guests back, and confirms with an updated booking code. Offers an upgrade if they're over allowance.
"I lost my Cartier at Hï last night." Member is upset, often distracted. The agent leads with empathy, captures member + venue + date + identifying details, logs an incident with structured context, and hands to a human concierge on WhatsApp within 4 hours.
5, Try it live
Try a ticket against the live agent.
Mock PartyOne member UI on the right, with the real Lorikeet chat widget embedded. Synthetic data, real workflows, real agent. Every answer is grounded in a live PartyOne knowledge base.
All four scenarios run against the same agent in the same sandbox. Same setup, swap the mock tools for your real APIs on day one.
7, About Lorikeet
Lorikeet is building the leading AI concierge for complex businesses
Lorikeet exists to give every company the ability to deliver a universal concierge to their customers. Customers should demand better support, Lorikeet's platform solves issues by understanding customer needs and taking actions for them, 24/7, via the channel of their choice.
Hi David, your $480 refund for the cancelled Marquee booking is on its way. Stripe has it as refund_pending since 2 Jun; expected to land on your statement by 16 Jun (5–10 business days).
If it isn't visible after that, message me here and I'll chase the processor directly. Reference: TXN-77104.
8, The team
Our people have decades of experience with AI and building great products
CEO and Co-founder
Steve led product teams at Stripe and Watershed, building tooling to enable complex processes like carbon accounting and financial reporting at scale.
CTO and Co-founder
Jamie was a research tech lead at Google Brain, leading research on factual grounding in large language models. Third named author on Google's breakthrough 2022 LaMDA paper, and fourth named author on the 2020 predecessor Meena paper.
Our team comes from leading companies applying AI and driving large-scale corporate transformation
9, Backed by
Lorikeet is backed by top global investors
We've raised over $50M from investors who backed Nubank, Klarna, Canva, Airwallex, Supabase, Midas, Clearscore and more.
www.lorikeetcx.ai
10, Customer voice
Lorikeet consistently outperforms other vendors in the market
11, Pricing + next steps
You only pay for resolutions
Aligned incentives by design — we both win when tickets resolve.
No platform fee, no per-seat fee, no setup cost. The only line item is a successful resolution — as defined by you.
~1,000 prospect chats + ~100 paid members × ~10 contacts/month each → an envelope inside the $1k–$4k/month range you described. Volume tiered.
Per-resolution price decreases as volume grows. Same rate card across chat, WhatsApp, voice, and email — no channel surcharge.
- 4 deployed engineers ship integrations in days, not months
- Built-in guardrails, off-ramps, and incident-response patterns
- Observability + retraining loop, not just a chat box
- You stay focused on the membership business, not the support infrastructure
Alex Holder
alex.holder@lorikeetcx.ai