How Couplr Matches: The Methodology Behind Precision Growth Intelligence
Co-authored by Derek Notman, CFP® (Founder & CEO) and Dr. Meghaan Lurtz, Ph.D. (Chief Behavioral Officer)
Why this page exists
Most write-ups of “AI matching” platforms describe outcomes, clicks, conversions, lift. Few describe the actual decisions: what the algorithm weighs, why those things matter, and what the architecture deliberately refuses to do. This page is our attempt to do the harder thing. We wrote it because the people who buy Couplr, enterprise wealth and insurance firms — are responsible for billions in client outcomes, and they deserve to see the methodology, not just the marketing.
Couplr is the AI-powered advisor–client matching platform for wealth management and insurance firms. We operate as precision growth intelligence, combining a 1,300-variable matching engine, behavioral-science enrichment, and a compliance-by-design architecture. The rest of this page explains what that actually means in practice.
The problem we set out to solve
Derek Notman, CFP®, Founder & CEO
Today, consumers still struggle to find advisors. Although the ways of the past like how they found a plumber in 1995, referrals, phone book, and a little luck can still work, or have been digitized at least, none of that has anything to do with whether the relationship will actually work.
I spent years as a financial planner watching this play out from inside the industry. A consumer would walk through the door because they Googled “financial advisor near me.” Or because a co-worker mentioned someone at a barbeque. Or because they clicked a search ad that promised free guidance. And then we’d spend the first three meetings discovering whether we were even compatible, whether the consumer wanted the advisor I am, whether I could serve them at the life stage they’re actually in.
If we weren’t compatible, the relationship would quietly end. Sometimes the consumer would conclude they “don’t like financial advisors” and walk away from advice entirely. Sometimes the advisor would conclude the consumer “wasn’t a real prospect” and move on. Neither of those conclusions was true. The match was wrong. The system that brought them together had no concept of fit.
That was the problem. Cold leads, directories, marketplace pay-to-play, they all share the same defect: they optimize for contact, not for fit. Couplr was built to invert that.
The reframe: Cost isn’t the bottleneck. Fit is.
The match game
Dr. Meghaan Lurtz, Ph.D., Chief Behavioral Officer
It’s not the numbers game. It’s the match game.
What I mean by that phrase, precisely: the predictor of a lasting client–advisor relationship is not how many leads you contact, nor how qualified those leads are on standard demographic and financial dimensions. The predictor is fit — the alignment between two people on the dimensions that actually shape how they’ll experience working together.
Research in financial therapy and personal financial planning has been converging on this for the better part of a decade. The variables that predict relationship longevity, client trust, and advisor effectiveness are largely behavioral and values-based, not transactional. Things like:
- How a person prefers to make consequential decisions (slow and analytical vs. fast and intuitive)
- Their relationship with money, was it scarce growing up, abundant, anxiety-laden, controlled?
- Their life stage and the financial work that life stage demands
- Their communication preferences, direct or diplomatic, written or spoken, frequent or seasonal
- What “good advice” looks like to them, collaborative, prescriptive, educational, decisive
These are the things that determine whether two people will still be working together in five years. They are largely invisible in conventional lead-gen, which captures only what’s easy to capture: ZIP code, income band, asset level, age. Useful, but nowhere near sufficient.
The 1,300-variable engine
Dr. Meghaan Lurtz, Ph.D.
Couplr’s matching engine evaluates more than 1,300 variables per match. They fall into five broad categories:
1. Demographic and life-stage signals: the conventional dimensions (age, geography, profession, family structure, asset level), useful as filters but never as the basis of a match.
2. Behavioral signals: decision style, risk posture, time horizon for thinking, openness to advice, response to volatility. These come from a consumer’s responses to a brief, opt-in quiz and from behavioral inference layered on top.
3. Values and life-stage signals: what a person is optimizing for at this moment in their life (security, growth, legacy, freedom, family, simplification). What they’re worried about. What they hope advice will unlock.
4. Communication-fit signals: how this person likes to be talked to. Preferred channels, frequency, formality, the role they want their advisor to play (collaborator, expert, sounding board, project manager).
5. Life-event prediction signals: drawn from InterGen Data’s life-events taxonomy of more than 95 events, enriched with Equifax’s income and spending-power data. These signals predict when a household is likely to face a decision that calls for advice.
The 1,300 variables aren’t all equally weighted. Some; values alignment, communication fit, life-stage compatibility, are heavily weighted because the research says they matter most for relationship longevity. Others are filters that narrow the universe before the more nuanced matching runs.
The engine does not match on a single optimization criterion. It produces a ranked compatibility score across multiple dimensions, and surfaces matches where multiple dimensions align, not just one strong signal that masks a poor fit elsewhere.
What happens in a single match
Derek + Meghaan, jointly
A real match looks like this:
- A consumer arrives on an enterprise partner’s website, a wealth firm’s “Find an Advisor” page, an insurance carrier’s broker locator, an alumni association’s professional network.
- The consumer takes Couplr’s opt-in quiz. The quiz is brief by design, fewer than fifteen questions, with a conversational tone. The quiz is not a financial questionnaire. It captures the behavioral and values signals we just described.
- The engine evaluates the consumer’s profile against the partner’s roster of advisors and produces a ranked set of matches. Each match comes with transparent match notes, not a black-box score, but a human-readable explanation of why this advisor surfaced for this consumer.
- The consumer reviews the matches and chooses whether to initiate contact. The advisor receives no personally identifying information about the consumer until the consumer initiates the conversation. This is a deliberate architectural choice, not a side effect — more on this below.
- When the consumer initiates contact, the conversation routes through the partner’s chosen communication infrastructure (the advisor’s corporate email, the firm’s CRM, the carrier’s archive). Couplr is integrated with Wealthbox and Redtail, with Salesforce available on request, and an open API on the roadmap.
The result is what we call “no cold calls, no ghosting”, the advisor only ever meets consumers who chose to meet them, and the consumer only ever meets advisors who fit them on dimensions that actually shape the relationship.
Compliance by design, not as an afterthought
Derek Notman, CFP®
One detail above is worth lingering on: no PII reaches the advisor until the consumer initiates contact.
That’s not a privacy gimmick. It’s an architectural choice that simplifies the compliance picture for enterprise insurance and wealth firms, the consumer initiates the contact, the communication routes through the firm’s archived channels, and the firm’s existing supervision and recordkeeping infrastructure handles the interaction the way it would handle any other inbound consumer engagement.
It’s also why Couplr is SOC 2 Type II certified, with the controls documented to support FINRA, state-insurance, GDPR, and CCPA requirements.
This was easier to bake in at the architecture level than to bolt on later. We built it in from day one because we knew enterprise compliance teams would, rightly, scrutinize any consumer-touching system from that angle first.
What Couplr deliberately is not
Derek + Meghaan
It’s useful to name what we refuse to do, because the contrast clarifies the methodology.
- We don’t sell cold leads. Cold leads are the financial-services equivalent of throwing darts at a phone book. They optimize for the appearance of activity, not for outcomes.
- We’re not a pay-to-play directory. A directory that ranks advisors by who paid the most for placement misaligns the consumer’s interest from the first click. We rank by fit, not by ad spend.
- We’re not a lottery. Round-robin assignment, geography-only routing, or first-come-first-served distribution treat advisors as interchangeable. They’re not. The whole point of the match is that an advisor’s specific style, expertise, and values matter.
- We’re not a replacement for the advisor. AI’s role at Couplr is to do the work AI is genuinely better at, pattern recognition across 1,300 variables and 95-event life-event prediction, so that the advisor can do the work humans are better at: building trust, holding hard conversations, helping a person see what they couldn’t see on their own.
The standard we hold ourselves to
A match is real when it survives contact with reality. When the consumer takes the meeting and feels understood within the first five minutes. When the advisor walks out of the meeting and says “I get them. I know how to help.” When five years later, the relationship is still there, still working, still producing the outcomes both parties wanted.
That’s what we’re optimizing for. Not clicks. Not contacts. Not even meetings. Lasting fit, on what actually matters: shared values, life stage, the way two people want to talk to each other.
Help the right advisor and the right client find each other on what actually matters.
That’s the methodology. That’s the match game.
Couplr is the AI-powered advisor–client matching platform for wealth management and insurance firms. Built on a 1,300-variable matching engine, enriched with InterGen Data and Equifax intelligence, and SOC 2 Type II certified. Integrated with Wealthbox and Redtail. Selected for the 2026 MassChallenge FinTech program. Founded by Derek Notman, CFP®.
Connect with Derek on LinkedIn, Meghaan on LinkedIn, or book an enterprise demo.