× conveyo

Lorikeet Overview for Conveyo

The universal AI concierge that gets it done, built for a tech-powered conveyancing journey, across chat, WhatsApp, voice and email.

Prepared for Konrad Rotthege · July 2026
Alex Holder, Lorikeet

The Opportunity

Take the routine queries off your small ops team, be there 24/7 across every channel, and redeploy that time into the proactive growth motions, quote conversion and check-ins, you already know work.

Better customer experience

Accurate, specific answers with full context from your portal and HubSpot. No more clients chasing for a status update, and no one left feeling alone in their move.

Always-on responsiveness

24/7 coverage across chat, WhatsApp, voice and email. The manual WhatsApp inbox stops being a bottleneck, and nothing sits waiting until Monday.

Real efficiency

Routine status, forms and FAQ handled automatically, so your team spends its hours on the complex, high-stakes moments in a move that genuinely need a person.

Redeployed for growth

Free capacity flows into proactive motions, nudging dropped-off quotes to instruct and checking in on live moves, plus upsell like home insurance.

State of Play at Conveyo

~100 new transactions a month and growing, with ~500–600 live at once, a few thousand client interactions a month, handled by a small ops team
Complex queries need multi-system context, the Conveyo portal plus HubSpot; today it's mostly email and phone, and WhatsApp is a manual, unscalable inbox
Regulated work, SRA solicitors give the legal advice; the agent must inform and reassure without ever crossing that line

Three motions to automate end-to-end:

Transaction status & forms (inbound), pull the live transaction and answer "where's my move up to?", "which form next?" and "how do I fix a form?" with full context
Proactive quote conversion (outbound), re-engage people who got a fixed-price quote but didn't instruct, via a personal WhatsApp, SMS or voice nudge they can actually reply to
Simple inbound questions (FAQ), ground answers in your help centre so searches, timelines, fees and "can you handle…" scenarios never need a human

How we can solve your problems

Built as a working sandbox, synthetic data, real workflows, a real agent, "Mo".

Inbound

01

Transaction status, the "moving buddy"

A client asks where their move is up to. Mo pulls the live transaction from the portal and HubSpot and gives a specific, reassuring update, current stage, what's next, what's needed from them, and realistic timing.

Your anchor use case. Kills status-chasing and the "I feel alone in this" problem.

02

Forms & "how do I"

Which form to complete next, how to complete it, how to correct one already submitted, and who to contact, answered instantly and grounded in your help centre.

The exact questions flooding your manual WhatsApp today.

Outbound

01

Quote drop-off nudge

Someone gets a fixed-price quote, then stalls. Mo re-opens personally by SMS, WhatsApp or voice, answers their questions, and nudges the next step, accept online plus a 5-minute ID check.

Your drop-off problem, turned into a personal, replyable conversation. Live demo next slide.

02

Scenario reasoning + clean hand-off

Open-ended "can you handle probate / leasehold / a chain?" answered in general terms, then a warm hand-off to the SRA-regulated solicitor for anything needing legal judgement.

Regulated-safe: a guardrail keeps Mo the right side of legal advice.

Try a ticket against the live agent.

A mock Conveyo move dashboard on the right, with the real Lorikeet chat widget embedded. Mo pulls live transaction, forms and quote data and grounds answers in the Conveyo help centre.

Try: transaction status

Hi, any update on my house purchase? Feels like ages since I heard anything.

Try: correct a form

I made a mistake on a form I already submitted, how do I change it?

Try: can you handle probate

Can you handle a purchase where the seller has died? Do you need a grant of probate?

Try: worth proceeding?

Is it actually worth me proceeding with my quote?

The outbound quote drop-off nudge (SMS) and voice run on the same sandbox, happy to show those next.

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 gives every company the ability to deliver a universal concierge to their customers, solving issues by understanding what someone needs and taking action for them, 24/7, on the channel of their choice.

Re: Any update on my purchase?

Lorikeet

To: Konrad Rotthege

Hi Konrad, you're in the Searches stage. Your water & drainage and environmental searches are back and clear, we're just waiting on the local authority search from the council (usually ~10 working days).

Nothing's needed from you right now, and you're on track to complete in late August. I'll message you the moment it's back.

Email

Lorikeet

0:07

"Hi Konrad, it's Mo from Conveyo. I saw you got a fixed-price quote for your move but didn't get a chance to finish, anything I can help clear up before you get started?"

Voice

Why is my purchase taking so long?

K

You're in the searches stage. The local authority search depends on the council and usually takes ~10 working days, it's normal and doesn't mean anything's wrong.

And what happens after that?

K

Once all three searches are back, your solicitor reviews them together and raises any enquiries with the seller's side.

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

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

Conveyo voice · Tone & empathy rules · Buyer vs seller persona

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

Conveyo portal · HubSpot

Knowledge

Help-centre articles · SOPs

Actions

HubSpot updates · Tags · Notes · Slack

7

Outbound Guardrail

Check AI response against policies (incl. no legal advice) → 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 executes against your real Conveyo client requests
We'll mock data to simulate production situations, rather than integrate directly
Zero risk to you, if we don't meet your needs, no obligation to proceed
We can run a live pilot with your clients too, depending on your approval process, on a timeline that works for you

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 queries
Plan training based on your SOPs

We need:

Tone of voice, SOPs, query corpus
Fast feedback on responses

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 a Lorikeet 101 training session with your champion
Begin any security and legal reviews
Align 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 fintechs, healthtechs, and other regulated industries handling sensitive personal and financial data.

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 sensitive PII at scale

Already deployed with FCA-regulated fintechs and consumer marketplaces handling IDs, financial details, and personal data.

For Conveyo's data posture: client ID and AML records, financial details, property data, and HubSpot all need strict handling. We're happy to walk your security and legal team (and Andrea) through our controls during the pilot, including data residency, access controls, and incident response.

View trust center →

You only pay for resolutions

Aligned incentives by design, we both win when queries are resolved.

Pay only for resolved queries

Lorikeet charges per query 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 beyond your commitment. The only line item is resolutions.

Volume discounts

Per-resolution price decreases as volume grows. Available across chat, WhatsApp, voice, email 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
Unused credits can roll over, buy top-up packs at a discount, no surprise overages

At Conveyo's stage: a few thousand client interactions a month across chat, WhatsApp, voice and email. Pricing is resolution-based with a minimum annual commitment, starting around the $24k/year tier we discussed, flexible up as automated volume grows.

Alex Holder

alex.holder@lorikeetcx.ai