×

Lorikeet Overview for Numan

A team of AI agents that handles patient triage, clinical admin, and consultation follow-up — so clinicians spend their time on clinical judgement.

Prepared for Rhidian Boobier & Ghalia Alrifai · 19 May 2026
Robbie Tilleard, Lorikeet

The Opportunity

Clinicians are Numan's most expensive and hardest-to-recruit resource — and today they spend hours on admin, follow-up, and macro replies. Imagine the alternative.

Intent-led triage at the front door

No more "clinic or customer care?" button. The AI reads the patient's actual intent — side effect, dose change, missing form, billing — and routes once, correctly. End the ping-pong between teams.

Clinical admin automated

Travel letters, pen-error replacements, GP letters, dose-change prep. The agent does the legwork; the clinician signs off in seconds.

Outreach without the ping-pong

Consultation form missing a field? The agent checks SOP eligibility first, then chases the patient over WhatsApp or voice — reaching the generation that won't reply to email. Less churn, less clinician chase work.

Clinicians on the work that matters

Clinicians stop using macros and chasing forms. They focus on red-flag triage, complex consultations, and the clinical judgement only they can apply. CSAT goes up because the right team replies on the right channel.

State of Play at Numan

Clinic sits outside the AI rollout — customer care is on Lorikeet; clinic was held back for safety reasons. Now Rhidian and Ghalia are in the same team under a new clinical VP and ready to bring AI into clinic.
Patient picks the wrong door — the Intercom flow asks "clinic or customer care?" up front. Patients don't know what they need, so tickets ping-pong between the two teams.
Clinicians on admin work — the most expensive, hardest-to-hire resource spends cycles chasing missing forms, sending macros for mild side effects, and writing travel letters.
Clinic CSAT trails CC CSAT — clinicians are trained for empathy in person, not async. The async voice belongs to the CC team; the clinical judgement belongs to clinic.
Inappropriate outreach drives churn — clinicians outreach for missing consultation info; sometimes the outreach wasn't actually needed. In weight loss especially, patients churn when their preferences aren't met.
Side-effect triage is blurred — mild nausea, constipation, fatigue are expected GLP-1 effects with self-management guidance. Red flags (e.g. coughing up blood) need clinician input fast. Today the same queue holds both.

Three use cases for Numan

All running on the same sandbox. Each pulls from your published KB and respects the same compliance line.

01

Front-door triage

No "clinic or customer care" button up front. The agent reads patient intent and routes once — side effect to a clinician, admin (travel letter, pen issue, GP details) to the AI, account / billing to the right team. End the ping-pong.

Intent-led routing — the volume driver in clinic.

02

Travel letter, end-to-end

Patient asks for a letter to carry their pen onto a flight. The agent gathers flight dates, drafts from your KB, mocks the prescriber sign-off, and delivers the signed letter inline.

Clinical admin done by AI, sign-off by clinician.

03

Outbound, consultation chase

Prescriber blocked on one missing field? The agent SMSes the patient on the channel they actually answer, captures the value, updates the consultation, and queues it for sign-off. Demoed live to your phone.

WhatsApp + voice + SMS — reach the generation that won't reply to email.

Side effects route straight to a clinician — no AI self-management. Pen-error replacement, dose-change queueing, and delivery / billing queries run on the same sandbox — happy to demo on request.

Team of AI agents in action

Two patterns where one AI agent isn't enough.

Inbound — "I need a travel letter"

1

Patient

Messages Numan asking for a travel letter for an upcoming flight.

↓

2

Triage AI agent

Classifies intent as clinical admin (not a side effect, not a clinical decision) and routes to the KB-driven helper.

↓

3

Knowledge AI agent

Pulls the "Can I travel with my weight loss medication?" article and asks for flight dates and destination.

↓

4

Drafting AI agent

Drafts the travel letter on Numan letterhead, attaches treatment details, and queues for prescriber sign-off.

↓

5

Concierge AI agent

Confirms the letter is queued, lets the patient know when to expect the signed PDF, and tags the conversation.

Outbound — Consultation form follow-up

1

Signal

Consultation form submitted with a missing field a clinician would otherwise chase.

↓

2

SOP AI agent

Checks the outreach is actually warranted under SOP — not the inappropriate-outreach pattern.

↓

3

Outreach AI agent

Reaches the patient on WhatsApp or voice — whichever channel they actually answer.

↓

4

Patient

Replies with the missing info — preference, height, BMI evidence, whatever's needed.

↓

5

Form AI agent

Updates the consultation form and queues the prescriber review with the full picture.

Any clinical task with these three properties can run on AI agents

Lorikeet integrates with your clinical systems, gates with guardrails, and communicates across the channels patients actually use.

01

Reading patient data

Patient record, consultation form, prescription history, dose stage, SOP for this condition.

02

Clinician in the loop where it matters

Agent does the legwork — eligibility checks, drafting, evidence-gathering — and queues the clinician for fast sign-off only on the decisions that need it.

03

Communicating with patients

Reply in the patient's channel of choice — in-app chat, email, WhatsApp, voice — with Numan's tone of voice.

Lorikeet runs the orchestration. Numan's clinicians own the clinical judgement.

Appendix

Lorikeet overview, the team, investors, customer voice, architecture, POC plan, security, and pricing.

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.

Re: Travel letter for your flight to Madrid

Numan

To: Sarah J.

Hi Sarah, your travel letter is ready — I've attached a PDF on Numan letterhead covering the Mounjaro pen and needles for your 22 May flight to Madrid (return 28 May), signed by your prescriber this morning.

Keep it with your pen in your hand luggage. If anything changes with your flights, reply here and I'll reissue. Safe travels.

Email

Lorikeet

0:08

"Hi James, it's Numan calling. Your consultation is one field short of being ready for a prescriber — we just need your most recent weight. Can I take it now, or would you rather I text a link?"

Voice

My Mounjaro pen feels like it's not delivering a full dose this week. What should I do?

P

Let's check it. Can you tell me: does the dose counter return to zero after injecting, and did anything feel different (resistance, a click)?

Counter went back to zero but it felt looser than normal.

P

Sounds like a pen error. I'm queuing a replacement order and flagging the dose loss for your prescriber. You'll have the new pen by Friday.

Chat

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

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.

Announcing our

$35M

Series A

Led by QED Investors

Blackbird

Square Peg

Capital49

Skip Capital

Airtree

Operator Partners

www.lorikeetcx.ai

Lorikeet consistently outperforms other vendors in the market

"We tested AI solutions head-to-head and Lorikeet was a winner in every metric."

Lindsay Boland

Product Manager, Flex

"We ran POCs with Fin AI, Decagon... Lorikeet was a clear winner."

Jiaona Zhang

Former CPO, Linktree

"Considered Sierra and other well-known players... [Lorikeet] could handle nuance, de-escalate emotional moments, and follow SOPs without breaking a sweat."

Jessica Mishlove

Head of Customer Relations, Arbor

Read case studies

Already running clinical and complex regulated support — from telehealth to fintech

Journey of a Support Ticket

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

1

Customer sends message

Via chat widget, email, WhatsApp, voice, or ticketing system

2

Channel Intake

Mode (chat / email / voice / SMS) · Escalation rules · Auto-close config

3

Brand + Config Loaded

Numan voice · Patient-facing tone · Per-treatment SOP set

4

Inbound Guardrail

Evaluate message → pass to triage, or escalate immediately

5

Intent Classification

AI matches customer intent against all available workflows

Matched Workflow

Run response SOP

FAQ Fallback

Search knowledge base

No Match

Escalate to human

6

Workflow Executes

Structured decision graph or Natural Language agent follows step-by-step SOP

Tools

Patient record · Consultation form · Rx history

Knowledge

Side-effect SOPs · Red-flag rubric · Treatment policy

Actions

Draft letter · Queue Rx review · Replacement order · Reply

7

Outbound Guardrail

Check AI response against policies → pass or escalate

8

Reply Sent to Customer

Brand voice · Formatting · Citations · Side effects (tags, CSAT, Slack)

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

If no reply → auto-resolved after idle period

Proof of concept

2–4 weeks, offline, free, to prove Lorikeet handles 2–3 hard clinic use cases end-to-end — you pick (e.g. mild side-effect triage, dose maintain, travel letters)
We'll mock the patient data to simulate production scenarios, rather than integrate with Numan's clinical systems on day one
Zero risk, if it doesn't meet the bar Rhidian and Ghalia's teams set, no obligation to proceed
Live pilot, narrow scope, e.g. one clinical topic across a single treatment area, then expand once the resolution and CSAT bar is hit

Train and test AI

Integration scoping

Legal / privacy / security review

Week 0–1

We will:

Train Lorikeet's tone and brand from your guidelines
Run response testing over 20–50 example tickets
Plan training based on your SOPs

We need:

Tone of voice, SOP, ticket corpus
Fast feedback on tickets

Week 1–2

We will:

Build, test and iterate on 1–2 agreed use cases
Share learning materials with your team
Produce documentation to aid implementation

We need:

Continued feedback on AI response quality

Week 2–3

We will:

Run Lorikeet 101 training session with your champion
Complete any necessary security and legal reviews
Agree on terms of contract including cost

We need:

Tech lead to align on integration plan

Week 3–4

We will:

Complete security and legal reviews
Kick off integration sync

We need:

Agree on commercial terms and sign

Lorikeet is built securely for enterprise

Compliance-grade architecture, day one. Designed for CQC and GPhC-regulated telehealth handling patient PII, prescription data, and clinical conversations.

SOC 2 Type II
& ISO 27001

Both certifications independently audited. Your data is always protected and is never used for training.

GCP + VPC

Built on Google Cloud, running in a virtual private cloud. Audit-grade logging end-to-end.

Ex-Stripe security

Founding engineering team includes an ex-Stripe Staff Security Engineer. Security reviewed by industry leaders.

Handles clinical PII at scale

Already deployed with regulated digital health players including Eucalyptus (UK Juniper, Pilot, Software, Compound) and Mosh (AU) handling patient PII, prescription, and side-effect data daily.

For Numan's data posture: patient PII, consultation forms, prescription history, and clinical conversations all need strict handling and audit trails. UK data residency is supported. We're happy to walk your security, compliance, and clinical governance leads through our controls, access policies, and incident response.

View trust center →

You only pay for resolutions

Aligned incentives by design, we both win when 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, voice, and SMS.

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

At Numan's clinic volume: exact per-resolution price depends on the workflows we scope during the pilot, with volume-based step-downs as more clinical and CC topics come on. We'll model the breakeven against clinician hours saved during the next session.

Robbie Tilleard

robbie@lorikeetcx.ai