“Before Dreamweaver, it was volume-based. And after that, it's strategic-based.”

Luis Pineda

Telesales Operations Manager

“Before Dreamweaver, it was volume-based. And after that, it's strategic-based.”

Luis Pineda

Telesales Operations Manager

“Before Dreamweaver, it was volume-based. And after that, it's strategic-based.”

Luis Pineda

Telesales Operations Manager

Company

PayJoy

Industry

Finance

Company size

Enterprise

In this article

CompanyPayJoy
IndustryFinance
Company sizeEnterprise

In this article

30%

more new customers used their credit line in 14 days vs a random holdout

17,000+

PayJoy customers, each with an agent of their own

98%

of promised callbacks kept

30%

more new customers used their credit line in 14 days vs a random holdout

17,000+

PayJoy customers, each with an agent of their own

98%

of promised callbacks kept

Credit for people the system turns away

PayJoy is a public benefit corporation dedicated to helping underserved customers in emerging markets achieve financial stability and success. We serve people who often face barriers to traditional financing, including informal workers, small business owners and entrepreneurs who are just getting started.

A customer walks into a store with an ID and a small down payment, leaves with a smartphone, and pays it off in weekly or monthly installments.

For many, PayJoy is the first lender to give them credit. Their repayment history helps establish their first formal credit record and can open the door to additional financial products, including a revolving credit line through the PayJoy Card.

For customers new to formal credit, using a credit line for the first time can come with questions: where to find their card, how to make a purchase, and how to access cash. That is where Luis's team comes in. Their role is to guide approved customers through those first steps and help them make their first purchase with confidence.

Five calls, whatever happened

Until this year, PayJoy’s telesales ran the way most contact centers do: on fixed campaigns. Every day, Luis Pineda, who runs the operation, built lists of eligible customers and assigned them to a set calling cadence, typically five calls over two weeks, and five more for customers in a second segment.

It’s a proven model, but it has a built-in limit: the schedule is set before the first call is made, so it can’t react to what happens during it. A customer who converted on the third call could still be queued for the fourth and fifth. For a business that depends on long-term customer relationships, that was the cost that mattered most: not the wasted calls, but the customers who got contacted once too often.

An agent of their own

In September, PayJoy moved its credit line outreach in Mexico onto Dreamweaver. Instead of a campaign, each customer now has an agent of their own, with one goal: their first purchase on the credit line within 14 days. More than 17,000 PayJoy customers have had an agent of their own so far.

The agent reads PayJoy's customer data every day, so new customers are picked up automatically and anyone who converts drops out straight away. For everyone else, it decides whether to call, send a text, try a different time or wait, and it logs why. When a customer asks for a call back tomorrow at 11, it books that time and keeps it. It remembers what each customer said last time, so the next call picks up where the last one ended.

The calls themselves are practical. The agent walks customers through finding their virtual card in the PayJoy app and the details they need to use it, and explains other ways to use their credit, like withdrawing cash at a bank teller with a code when they don't have a bank account of their own.

For Luis, the operational change was immediate.

"Now I don't have to upload a CSV daily or 2 CSVs daily. You don't have to configure a campaign. We don't have to burn our customers and it opens the door to more strategic contacting."

It also changed what Luis thinks outreach can be.

Hearing 10,000 conversations a month

The part Luis didn't expect to value most is what the conversations reveal. Coach reads every call and turns patterns into insights: why customers hesitate, where they get stuck, what they ask that nobody has answered well.

"We're humans. There's no way we're going to listen through 10,000 conversations per month, with this insight report, we get the contact reason, what's happening. It even makes a suggestion as to what to fix. And then you get an action to do."

Those insights feed back into the agents themselves. Dreamweaver has saved 71 learnings at PayJoy, and agents have looked them up more than 750,000 times while deciding what to do for a customer. They also travel beyond the calls. One insight about how customers respond to certain reassurances made it into PayJoy’s wider messaging. The company now uses that framing across its campaigns.

From volume to strategy

PayJoy measures everything against a control group, and Dreamweaver is held to the same standard. In early results, 30% more new customers made their first purchase on the credit line within 14 days than a random holdout group.

The agents also correct course on their own. They have kept 98% of the callbacks they promised customers, and called off nearly 2,000 messages that no longer made sense, like a reminder to someone who had already made their first purchase.

Asked to sum up the change, Luis is brief.

"Before Dreamweaver, it was volume-based. And after that, it's strategic-based."

What's next

Luis sees Dreamweaver growing from a way to win new customers into a way to keep them.

"I envision it as an acquisition and retention tool, acquiring, it's really easy. The trick is retaining customers."

Next, PayJoy is turning its attention to re-engagement: using what the agents have learned to bring back customers who haven’t been in touch for a while.

He also sees room to bring the same approach to PayJoy's other markets.

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
Lorikeet offers a 30-day free trial.

Lorikeet

The AI concierge
for complex, regulated customer support

Ask AI about Lorikeet

ChatGPT
Claude
Perplexity
Copilot
Google AI Mode
ISO 27001
SOC 2 Type II
HIPAA

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

© 2026 Lorikeet. All rights reserved.

ABN: 53 669 390 149

LinkedIn

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.