Lorikeet ×

Lorikeet Overview for Yesim

The universal AI concierge that gets it done, built for eSIM providers running a multi-vendor, multilingual, always-on support operation.

Prepared for Sergei · 16 May 2026
Alex Holder, Lorikeet

Lorikeet 2, The Opportunity

The Opportunity

Resolve the complex eSIM cases your current bot escalates. Stop paying per message; pay per resolution. Free your 20-person first line to focus on the calls only a human can handle.

Resolves complex eSIM cases

Multi-eSIM accounts, vendor-specific quirks, screenshot diagnosis, country-by-country branching. The cases your current bot punts to the first line — Lorikeet finishes them.

Multilingual, always-on

Russian, German, French, Italian, Spanish, English — same agent, native fluency. 24/7 across in-app, web, and email. Travellers don't wait on local business hours.

Paid per resolution, not per message

Incentives aligned with yours. You only pay when the AI closes the ticket. No surprise bills from chatty customers, no buying credits we burn on conversation noise.

Easy to maintain monthly

Workflows in plain English, edited like a Notion doc. When a new vendor lands or an OS update breaks a path, change one paragraph and simulate against your historical tickets before going live.

Lorikeet 3, State of play

State of Play at Yesim

  • 25–30,000 contacts a month, ~90% in-app SDK plus web and email, handled by a 20-person first-line team. Today's bot covers ~35–50% — but only when the queue overflows, because the complex cases break it
  • Complex queries need multi-vendor, multi-eSIM context — Intercom for the conversation, Yesim's in-house admin panel for the user, plus vendor dashboards for the eSIM profile, install state, and ICCID
  • Maintenance is the rate-limit, with product changes shipping almost monthly. Every change is a bot-retrain task. If the platform is hard to edit, quality slips fast

Three motions to automate end-to-end:

  • Complex eSIM troubleshooting, the case your current bot escalates. Multi-eSIM disambiguation, vendor + OS branching, screenshot reads, vendor escalation when it's genuinely upstream
  • Outage response, when 50 customers in Bangkok report no signal at the same time, the agent recognises a regional vendor outage, gives accurate ETAs, and stops the queue from burning through troubleshoot steps
  • FAQ at scale, grounded in your live help centre (already scraped, 200+ articles across EN/RU/DE/FR/IT/ES) so questions about Turkey IMEI blocking, PDP authentication failure, or QR scan errors never reach a human
Lorikeet 4, Use cases for the demo

How we can solve your problems

Four inbound use cases built as a working sandbox — synthetic Yesim data, real workflows, real agent.

Resolves end-to-end
01
Complex eSIM troubleshooting

Customer has 4 active eSIMs across vendors and countries. Agent pulls the account, disambiguates which eSIM is failing, branches on OS + vendor, reads the install-error screenshot, and walks them to a fix in their language.

The case your current bot escalates. Live demo on the next slide.
02
FAQ grounded in your help centre

"PDP Authentication Failure", "Errors while scanning the QR code", "IMEI blocking in Turkey", APN settings on Samsung. Every answer cited against the 200+ articles scraped from help.yesim.tech in EN, RU, DE, FR, IT, ES.

Eliminates the high-volume, low-stakes contacts that should never reach a human.
Routes correctly
03
Outage triage

Customer in Bangkok messages "I have no signal". Agent identifies the eSIM's vendor + country, calls the outage API, finds an active VendorC outage with an 18:00 ETA, communicates it accurately, and stops running pointless device checks. Same answer, same accuracy, across 50 conversations at the same time.

Stops the queue from burning hundreds of tickets on the same upstream cause.
04
Vendor escalation with context

When troubleshooting confirms the problem is on the vendor's side, agent drafts and emails the original vendor's support team with the customer's ICCID, eSIM details, device, OS, and everything tried so far. Customer is told the timeline. Internal note logged for the team.

Removes the manual handoff your first line writes today.
Lorikeet 5, Try it live

Try a ticket against the live agent.

Real Yesim app screen on the right, with the live Lorikeet chat widget embedded. Try a FAQ — every answer is grounded in your live help centre (200+ articles scraped from help.yesim.tech across six languages). Account-specific troubleshooting needs an authenticated login; we walk through that flow in the sandbox.

Try: device compatibility
Which phones support eSIM? Will my iPhone 13 work with Yesim?
Try: Turkey + long stay
I'm in Istanbul for the next 3 months. Will my Yesim eSIM keep working, or does Turkey block phones after a while?
Try: APN settings
What's an APN and do I need to configure it manually on my Yesim eSIM?
Try: in Russian
Что такое YCoins? Как накопить бонусы в Yesim?

FAQ answers cite live Yesim articles. Account-aware flows — multi-eSIM troubleshoot, outage detection, vendor escalation — run on the same sandbox once the customer is authenticated.

Appendix

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

Lorikeet 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.

Email
Lorikeet
0:08
"Hi Marco, this is Yesim — quick heads-up, VendorC has reported an outage in central Thailand where you're travelling. ETA to resolve is 18:00 local. No action needed on your end."
Voice
What's PDP Authentication Failure?
L
It's a carrier-side error meaning your phone couldn't authenticate with the network. Usually a quick fix — let me walk you through it.
OK
L
Toggle Airplane Mode on, wait 10 seconds, toggle it off. If it still fails, I'll reset your APN to internet.vendora.de.
Chat
Lorikeet 8, The team

Our people have decades of experience with AI and building great products

Steve Hind, CEO & Co-founder

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.

Jamie Hall, CTO & Co-founder

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

Stripe
Google
Atlassian
Canva
Salesforce
Dropbox
BCG
Bain & Company
Lorikeet 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.

Announcing our
$35M
Series A
Led by QED Investors
Blackbird
Square Peg
Capital49
Skip Capital
Airtree
Operator Partners

www.lorikeetcx.ai

Lorikeet 10, Customer voice

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
Lindsay Boland
"We ran POCs with Fin AI, Decagon... Lorikeet was a clear winner."
Jiaona Zhang
Former CPO, Linktree
Jiaona Zhang
"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
Jessica Mishlove
Airwallex
Eucalyptus
Tap Tap Send
Airalo
Flex
Carmoola
Lorikeet 11, Architecture

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
Yesim voice · Multilingual tone · Customer language detection
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
Intercom · Yesim admin panel · Vendor APIs
Knowledge
help.yesim.tech · SOPs · Vendor manuals
Actions
Tags · Internal notes · Vendor escalation
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

Lorikeet 12, Proof of concept

Proof of concept

Train and test AI
Integration scoping
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 13, Security

Lorikeet is built securely for enterprise

Compliance-grade architecture, day one. Designed for fintechs, healthtechs, and other regulated industries handling sensitive household 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 subscribers and travel/telco subscribers handling traveller PII, passport scans, payment data, and device IMEIs at international scale.

For Yesim's data posture: customer PII, device IMEIs, payment methods, and vendor credentials all need careful handling across regulatory regimes (EU GDPR, Swiss FADP, plus the local rules in each coverage country). Happy to walk your security and legal team through our controls during the pilot — data residency, access controls, and incident response.
View trust center →
Lorikeet 14, Pricing

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 Yesim's volume: ~25–30k contacts/month puts you in our Enterprise / Custom tier. We size the per-resolution price to your actual workflow mix and forecast volume once we scope the pilot together — talk to us for an exact quote. The key point — you stop paying for conversation noise, you start paying only when we close the ticket.
Lorikeet

Alex Holder

alex.holder@lorikeetcx.ai

1 / 15