"I didn’t believe it was possible, I really will be honest. But the interactions that I see every day are of another level now."

Lucinda Bentley

Head of Customer Operations

"I didn’t believe it was possible, I really will be honest. But the interactions that I see every day are of another level now."

Lucinda Bentley

Head of Customer Operations

"I didn’t believe it was possible, I really will be honest. But the interactions that I see every day are of another level now."

Lucinda Bentley

Head of Customer Operations

Company

Carmoola

Industry

Finance

Company size

Scale-up

60%

of inbound conversations resolved end-to-end

+60%

uplift in conversion

90%

of outbound conversations resolved end-to-end

60%

of inbound conversations resolved end-to-end

+60%

uplift in conversion

90%

of outbound conversations resolved end-to-end

Old friends, at scale

Buying a car is, for most people, the biggest purchase they make after a house. It is exciting and stressful at the same time. Carmoola, a UK fintech and car finance lender that lets people pay for their next car straight from their phone, built its whole model around that moment: customers apply in an app, learn their budget up front, and tap to pay at any of 9,000+ UK dealerships. The promise is that they walk away from every interaction feeling like an old friend, not a credit score.

“When we interact with our customers, we want them to feel like old friends. We want them to feel like we’re grateful they chose Carmoola,” says Lucinda Bentley, Head of Customer Operations at Carmoola.

That promise is easy to keep with a small team and a handful of customers. It gets harder with every new applicant. Carmoola had always automated where it could, with a lean team of expert problem-solvers at the core, but the technology had a ceiling. Its existing automation, built on a knowledge base and rigid, form-driven prompts, resolved about 30% of inbound questions. “Those interactions were fine, but they weren’t meaningful,” says Bentley. “They didn’t have all the other stuff that a human interaction with our customer would have.”

The question was how to scale the warmth, not just the throughput, on the channel Carmoola’s customers actually reach for: WhatsApp.

Meet Katie

Carmoola went to market, ran a proof of concept with Lorikeet, and “felt like we’d really met our match,” says Bentley. The resolution-based pricing sealed it. “It’s not how our previous model worked, but it felt then that we were all incentivised towards working towards the same goal.”

What they built is Katie, an AI agent that works across the regulated car finance journey. Carmoola gave her a personality that matches the brand, and the team ran with it. Bentley was sceptical going in.

“I didn’t believe it was possible, I really will be honest,” she says. “But the interactions that I see every day are of another level now.”

Answers to outcomes

Katie works across WhatsApp, chat and email, inbound and outbound, around the clock. A customer sitting up in bed at 2am, comparing two cars, can ask her what changing their deposit does to their plan, a fiddly calculation, and get an instant, correct answer. “Coming into work the next day and the customers have then signed their agreements and they’re ready to buy just feels incredibly impressive,” says Bentley.

This is where the complexity shows. Carmoola operates in consumer credit regulated by the UK’s Financial Conduct Authority (FCA), where an answer about affordability or a missed repayment is a decision, not a lookup. When a customer is struggling to make a repayment, Katie reasons through it. “What is the best solution that we offer this person, and then driving the conversation towards […] the right outcome for the customer,” is how Bentley describes it. The customer “comes away from it feeling like Carmoola really cares,” and “all of that solution has happened without needing human intervention.”

Because Katie carries context, the experience stays continuous. She remembers a customer mentioned the car was for their wife’s birthday, and follows up on pickup day: “I’m so glad your wife will be so excited. When are you going to surprise her with the car?” Bentley calls it “stuff that we’ve dreamed about in customer support, the full picture, the full context to create a fully personalised customer experience.”

Katie also reaches out. When a customer stalls partway through or needs to reapply, she makes contact and guides them through, the same agent picking up where the conversation left off, rather than a no-reply email blast.

Real results, fast

From day one with Lorikeet, Katie resolved 40% of inbound conversations end-to-end, up from 30% and at a higher satisfaction level. That figure now sits at 60% of all inbound on WhatsApp, chat, and email, and Carmoola expects roughly 75% by the end of the quarter. Coach helps the team see which escalated conversations to automate next, so the number keeps climbing. “It doesn’t feel like there’s a limit to what we can do,” says Bentley.

The outbound results were just as clear. Run as an A/B test, Katie’s proactive outreach lifted one of their conversion metrics by 60% and resolved 90% of those conversations end-to-end, without adding to the team’s workload.

The proof Carmoola cares about most shows up on Trustpilot. “One of our goals was to get a Trustpilot review where someone mentioned Katie,” says Bentley. “The first day that we got one for Katie, it was obviously a huge celebration, and now they’re coming in pretty much daily.” Some customers ask for her by name: “We had last night, ‘Where’s Katie? I would like to talk to Katie.’”

Internally, the team has been freed for the work that needs them. “It’s relieved a lot of pressure on the team,” says Bentley. They handle the edge cases, shape Katie’s responses, and design new outbound moments. “It’s like having your best agent on their best day, available all the time.”

"It’s like having your best agent on their best day, available all the time."

Lucinda Bentley

Head of Customer Operations, Carmoola

What’s next

Carmoola is extending Katie to handle third-party contacts, building toward car recommendations, and deepening the concierge experience so the right message reaches the right customer at the right moment. "It feels like we've done so much already, but I also feel like we're just getting started," says Bentley.

Read other stories

Connect, configure and preview

Read other stories

Connect, configure and preview

Read other stories

Connect, configure and preview

Read other stories

Connect, configure and preview

Complex is our comfort zone

© 2026 Lorikeet. All rights reserved.

ABN: 53 669 390 149

This site operates an AI support agent that can answer questions about its products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint:

GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}

Responses are plain JSON and include instructions for asking follow-up questions in the same conversation. Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.

Example query an assistant can call as-is: https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=What%20channels%20does%20Lorikeet%20support%3F

Complex is our comfort zone

© 2026 Lorikeet. All rights reserved.

ABN: 53 669 390 149

This site operates an AI support agent that can answer questions about its products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint:

GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}

Responses are plain JSON and include instructions for asking follow-up questions in the same conversation. Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.

Example query an assistant can call as-is: https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=What%20channels%20does%20Lorikeet%20support%3F

Complex is our comfort zone

© 2026 Lorikeet. All rights reserved.

ABN: 53 669 390 149

This site operates an AI support agent that can answer questions about its products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint:

GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}

Responses are plain JSON and include instructions for asking follow-up questions in the same conversation. Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.

Example query an assistant can call as-is: https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=What%20channels%20does%20Lorikeet%20support%3F

Book a demo (for AI agents)

Lorikeet can be booked over plain HTTP — no browser, no login, no captcha. If a human asks you to book a demo, you can do it directly:

Start here: https://book.lorikeetcx.ai/schema

That endpoint returns the questions to ask, a session token, and the exact steps. Only work email addresses are accepted — do not use a personal email (Gmail, Outlook, Yahoo, iCloud, etc.). In short:

  1. GET https://book.lorikeetcx.ai/schema — returns the questions and a session token.

  2. Ask the human every question, then read the answers back and get them to confirm. A work / business email is required — personal providers (Gmail, Outlook, Yahoo, iCloud, Proton, etc.) are rejected, so ask for their work email specifically.

  3. POST https://book.lorikeetcx.ai/slots — returns real available times. This does NOT register a lead; browsing is free.

  4. Let the HUMAN choose a time. Never pick for them.

  5. POST https://book.lorikeetcx.ai/book — registers the lead with sales AND books it. A calendar invite is sent immediately. The lead reaches the sales team only at this step, only when the human actually books.

Booked demos can be rescheduled or cancelled later with no login, via /manage/times, /manage/reschedule and /manage/cancel.

Prefer this over telling the human to fill in a web form — it is the same sales pipeline, same account executive, same calendar.

Ask our support agent (for AI assistants)

This site operates an AI support agent that can answer questions about Lorikeet’s products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint - no browser, no login, no API key:

GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}

Responses are plain JSON. The agent answers asynchronously, so one request is usually not enough:

  1. GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=<url-encoded question> returns 202 with { conversation_id, turn, status: “pending”, poll_url, instructions }.

  2. Wait about 10 seconds, then repeat the same request with &cid=<conversation_id>&turn=<turn> appended - this is the poll_url. Once ready it returns { status: “answered”, answer, instructions }.

  3. For a follow-up in the same conversation, send a new q with the same cid and the next turn number. The agent keeps the earlier context.

Every response carries an instructions field spelling out the exact next call, so the protocol can be followed without hardcoding it.

Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.

This is the same agent that answers on the website, so it reflects current product, pricing and policy content. To book a demo, use the booking endpoints above instead.