How Eucalyptus scaled patient support 4x without adding headcount

How Eucalyptus scaled patient support 4x without adding headcount

Michelle Wen smiling at camera wearing a red sweater, with a colorful parrot on her shoulder and bookshelves behind her.

Michelle Wen

|

|

0 Mins

From a conversation with Tim Doyle, CEO of Eucalyptus, on the Be Customer Led podcast hosted by Marbue Brown, founder of the Customer Obsession Advantage and former CX executive at JP Morgan Chase, Amazon, Microsoft Corporation, and Cisco Systems.

When Tim Doyle's telehealth company Eucalyptus needed to scale patient support across four countries with different regulatory frameworks, he faced a choice most healthcare operators know well: hire hundreds more agents, or find a fundamentally different approach.

Eucalyptus chose the latter. The result: a 4x increase in patient volume with zero increase in human support costs, a 10-point lift in CSAT scores, and 60-70% of tickets resolved entirely by AI with no human in the loop.

"ROI is directly tied to ambition. If you go after hard use cases, you will see results. If you are timid with your approach, you'll see tepid results."
- Tim Doyle, CEO, Eucalyptus

Born in Complexity

Lorikeet's story is inseparable from Eucalyptus. Before writing a line of code, Lorikeet co-founders Steve Hind and Jamie spent months embedded with the Eucalyptus patient support team in Sydney, watching how they actually worked.

"We noticed really quickly that all of the support solutions coming to market were fundamentally based on just summarizing FAQ material," Hind said. "We watched the Eucalyptus team working and 0% of their day was spent summarizing FAQs. Their day was orchestrating complicated workflows to solve complicated customer problems with severe constraints."

Those constraints are real. In Australia, it's illegal to name a prescription medication to someone who hasn't been prescribed it. If a patient emails asking "Do you have Ozempic?" and you reply "Yes, we have Ozempic," you've committed a crime.

"We had to launch an AI agent from day one that would not commit that crime," Hind said. "That's the bar we held ourselves to."

Why Healthcare Patients Prefer AI

Lorikeet recently commissioned research on consumer attitudes toward AI in support. One finding stood out: consumers are 50% more likely to prefer AI support for questions they consider personal or embarrassing.

In healthcare, where patients reach out about weight loss, erectile dysfunction, or sensitive symptoms, this matters. Being able to talk to something that understands you and helps you, but isn't another person, can be preferable to speaking with a human.

"The reality is people want to be heard and have their questions actioned quickly," Hind said. "AI's ability to understand and empathize and then respond very quickly often produces a superhuman experience, especially relative to an overwhelmed human operator."

AI support as a catalyst for global expansion

Eucalyptus operates clinics in Australia, Japan, Canada, and Germany. Each market has different regulations, different cultural expectations, different languages.

"The nuances of communicating with a Japanese patient are very different to a Canadian patient and very different again to a German patient," Doyle said. "Solving that complexity has been the heart of the business model."

Lorikeet has four deployed engineers embedded with Eucalyptus across London and Sydney. The integration with internal systems and systems of record is at least half the work of any deployment at scale.

"It's easy to talk about the fun, cool technology," Hind said. "But actually getting integrated into internal systems, integrating with systems of record, it's just real hard work."

Better Triage, Not Just Automation

Not every ticket should be automated. What matters as much as answering questions is knowing when not to answer them.

Eucalyptus previously relied on keyword matching to escalate severe side effects to practitioners. If someone wrote "I have heart palpitations" and misspelled "palpitation," it wouldn't hit the priority queue.

"Now we read the messages and identify from the underlying meaning when there's an urgent medical issue," Hind said. "We saw a 10 percentage point increase in Eucalyptus's aggregate CSAT scores by using AI to put the most complex tickets in front of the best and most qualified human agents, as well as using AI to quickly answer the rest."

What Support Looks Like Now

Doyle's team is now thinking beyond traditional support boundaries.

"Customer support has a strange historical limitation," he said. "You have marketing on both sides and support in the middle. Now that we have this very fast, very high quality response system, the question is: why limit that to any point? Why not have customer support in this high empathy, high speed model deliver everything?"

For Hind, the lesson is simpler: "Every interaction a consumer has with your brand is your product. There is no difference between your app and your support email and your support phone number. It's all just your product."

Eucalyptus is a telehealth platform operating digital healthcare clinics across Australia, Japan, Canada, and Germany. The company recently signed an agreement to be acquired by Hims & Hers.

Book a call

See what Lorikeet is capable of

Share this article

Related posts

Ready to deploy human-quality CX?

© 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

Ready to deploy human-quality CX?

© 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

Ready to deploy human-quality CX?

© 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.