“Basically the team that I have now isn't going to change much in the next year. And I need to 10x our customer base by the end of next year.”

Duke Lam

Head of Business Operations

“Basically the team that I have now isn't going to change much in the next year. And I need to 10x our customer base by the end of next year.”

Duke Lam

Head of Business Operations

“Basically the team that I have now isn't going to change much in the next year. And I need to 10x our customer base by the end of next year.”

Duke Lam

Head of Business Operations

Company

Chexy

Industry

Finance

Company size

Scale-up

In this article

CompanyChexy
IndustryFinance
Company sizeScale-up

In this article

5x

more tickets handled by the AI agent each month

24-72%

share of inbound handled by the agent, in one week

24 hrs to 1 min

average handle time on the tickets the agent resolved

5x

more tickets handled by the AI agent each month

24-72%

share of inbound handled by the agent, in one week

24 hrs to 1 min

average handle time on the tickets the agent resolved

Every bill earns rewards

Rent, tuition, tax and insurance normally leave a bank account by transfer and earn nothing. On Chexy they go on a credit card instead, and the points and cashback go back to the customer. Chexy also handles payments such as mortgages by bank transfer, and those earn rewards too. Over 200,000 Canadians use it, and Chexy has processed more than $2B in bills and returned $40M in rewards.

That design makes every support question specific to one customer. A customer wants to know where one payment sits, why one charge looks the way it does, or when one set of Aeroplan points will appear. The answer lives in that customer's transaction history, spread across several of Chexy's internal systems.

The month arrives in one week

Chexy's volume is not spread evenly. Half or more of a month's tickets arrive in the first week, when rent is due. Chexy expects support volume to grow roughly tenfold as it scales. The plan is to absorb that growth without growing the support team in step.

Duke Lam, who runs operations at Chexy, described what the first week did to the queue, and why more headcount was not the answer.

We would get flooded on the first week of the month and it'll take us a week or more to clear the backlog, and we get just over a week of breathing before it starts again.

Duke Lam

Head of Business Operations

Starting with what the agent could already reach

Chexy went live in November 2025 on a narrow slice of its queue. The agent, which Chexy named Chester, took identity verification and Aeroplan questions.

Those workflows run on help centre content and a short list of account attributes, so Chexy could launch them without waiting on engineering. On the tickets Chester resolved, average handle time fell from 24 hours to about a minute.

The ceiling on volume

Payments is Chexy's largest ticket category, and the agent could not reach the data it needed to answer those questions.

A payment question needs the customer's transaction record, their account status and their payment schedule, and at Chexy those lived in several internal systems with no single route in. Building that route is engineering work, and at a company growing this fast, engineering time goes to the product first.

Through those months the agent handled about 1,500 tickets a month against inbound of about 6,000. The rest of the volume stayed with the team.

Connecting Chexy's systems

In June 2026 Ben Gigone, Chexy's CTO and cofounder, connected Lorikeet to multiple internal Chexy systems.

The agent can now look up payment records, account status and eligibility during a live conversation.

We connected Lorikeet to Chexy's systems, and that allows us to give Lorikeet access to a lot of our data which we previously didn't have access to.

Ben Gigone

CTO and Cofounder

5x the volume with the same team

With the data reachable, Chexy opened Chester up to its whole inbound queue at the end of July.

The agent's share of inbound moved from about 24% to about 72% that week. Monthly tickets handled by the agent went from about 1,500 to over 7,500, with payment questions included for the first time. The support team stayed the same size.

What's next

Chester can read a customer's payment data today. The next step is to let customers act on it: change their own payments and manage their own schedule through Chester, without waiting for the team.

Each new capability builds on the connections Chexy already has to its own systems, rather than adding another integration.

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

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.