← Back to Interaction Rule Set

Design Kickoff: Knowledge Transfer

Created by Sydney Bocik | March 2, 2026 | Category: Design | Last updated: March 12, 2026

Executive Summary

This document is meant to give our design partner an early window into our thinking: the competitors we've studied, the interactions that resonate with us, the product moments we care most about, and the context behind why we're building the Clarity Engine for PreFi and Purlend. It's a starting point for conversation, not a directive. We're excited to get this right and happy to provide anything else that would be helpful as we kick off. Consider this an open invitation to ask questions, push back, and dig deeper.

Related Documents

Design References

Design Adjectives

Non-Vertical Specific Inspiration

Onboarding, Intuitive Design, & Progressive Trust

AI Communication & Confidence

Warmth + Sharpness Done Together

Typography & Editorial Confidence

Competitors & Interaction Reference

  1. AI Mortgage Intelligence: Friday Harbor. AI loan officer assistant for real-time underwriting. Scenario desk, AI underwriting, dynamic checklist. B2B / professional-only; data-dense, transactional UX.
  2. AI LO (Closest to PreFi): Angel AI. Conversational, education-first mortgage exploration for consumers. Progressive disclosure, question-led exploration model, B2C. Patent research useful for gleaning, avoiding, and working around. Chatbot-heavy with weak visual reinforcement; lender-specific fulfillment.
  3. True Cost & Affordability Visualization: TLC Engine. Property affordability engine showing full monthly ownership cost. Cost stacking visuals (PITI+), monthly affordability framing, MLS-integrated B2B. No scenario exploration or decision-state awareness.
  4. White-Labeled Home Search & Embedded Tools: OneHome. White-labeled MLS-powered home search for brokerages. Embedded widgets, PropertyFit lifestyle score, neighborhood data, vendor marketplace, buying checklist. No financial intelligence, hyper-personalization, or decision support beyond static checklist.
  5. Sales & Lead Nurture AI (Contrast Case): Total Expert. AI voice/messaging for LO lead nurture and compliance. Contrast to PreFi's neutrality; not a UX model to replicate.
  6. AI Personal CFO / Wealth Management: Hiro Finance. Financial clarity copilot, no fulfillment. Narrative explanations, "here's what this means for you" summaries. Instant visual output, predictive scenarios, long-term framing, smart context awareness. Long term strategic context only.
  7. CFO-X. AI CFO with real-time visual translation. Instant visual output, predictive scenarios, long-term framing, smart context awareness. Long term strategic context only.

Key MVP UI Takeaways for PreFi

Anti-References: What PreFi Is Not

Aggressive Lead Capture

Chatbot Without Visual Payoff

Corporate / Enterprise Feel

Technical Constraints for Design

User Archetypes & Intent Understanding

PreFi's AI detects and adapts to five behavioral archetypes in real time. These are not fixed user segments: a single person can move between them within one session. Archetype shapes tone, pacing, and framing, not the answer itself.

Note: These might differ slightly from what is in the PRD, but we are hoping to refine these during the design process.

Summary of Archetypes

User Journey with Emotional Intelligence

The Clarity Engine prioritizes early value delivery. Initial scenarios are presented after a small number of inputs, then refined progressively as the user chooses to go deeper. Users may explore lightly or engage in deeper scenario modeling: the system adapts without forcing a single linear path.

1. Primary Persona: Alex

2. Current Behavior (Before PreFi)

3. Journey with PreFi

3.1 Arrive

A friend says: "Try PreFi: it actually explains your situation without trying to sell you anything so you can figure out the best path forward." Visits PreFi, sees: "Explore your mortgage options. No pressure, no steering." Clicks "Start Exploration." Oracle begins detecting user signals.

3.2 Address

Alex enters their property address. The platform auto-fills estimated home value, property type, tax assessment, and existing loan estimates in under 2 seconds. The experience comes alive: 15+ manual inputs reduced to one. If data is incomplete, the AI collects missing details through warm conversational questions. No dead end either way.

3.3 Converse: Intent Discovery

AI asks warm questions to understand intent: "What brings you here today?"

Alex: "Thinking about refinancing but not sure if it makes sense."

Oracle: Detects cautious, thoughtful language. Cash-Flow Manager with Risk Reducer tendencies.

Advisor: Detects anxious. Adapts tone to reassuring.

AI: "That's a really common place to be: mortgages can feel overwhelming. Let me help you figure this out, no pressure. What would a successful refinance accomplish for you?"

Alex: "I want to lower my monthly payment. We're planning for a baby and could use the extra cash flow."

Oracle: Real intent = free up cash flow for a life goal.

Navigator: Prioritizes lower payment scenarios, routes toward Cash-Flow Manager framing.

3.4 Explore: Scenario Cards

AI presents 3 named parallel paths. Equal visual weight, no ranking, no recommendation:

"The Freedom Path addresses your stated goal of lowering your payment: here's what that means and what it costs you:"

3.5 Explore: Deeper

Alex clicks each card, uses sliders to adjust assumptions, and compares side-by-side for 10+ minutes. Navigator tracks engagement patterns. Visualizations update instantly.

3.6 Clarity: The Magical Moment

Alex starts to disengage. Advisor detects confusion. Interface responds: chart simplification, alternative analogy surfaces.

"Think of it this way: $450/month is a car payment you don't have to make."

Alex: "Oh: extending the term saves monthly but costs more long-term. Got it."

Advisor detects breakthrough. Celebrates understanding, tone shifts to confident.

3.7 Summary & Soft Exit

Alex feels empowered: "I know what I need to decide now."

The platform presents an optional next step: create an account to save progress or run a soft credit pull to sharpen the numbers. No pressure if declined. Alex leaves having received full value without creating an account.

Refinance Conversation Simulation

A live simulation of the Phase 1 Clarity Engine for refinance/equity strategy (not a rate-shopping flow).

System Components Active Throughout

OracleArchetype classification (updates every msg)
AdvisorEmotional state detection (8 states)
NavigatorState machine / routing logic
Error layerEvery failure has a warm recovery. No dead ends.

Current End User Pain Points (Homeowners)

  1. The internet sends them to salespeople, not answers. The moment a homeowner searches "should I refinance" they enter a lead generation machine. Bankrate, LendingTree, NerdWallet: every result is optimized to capture contact information and route them to a lender as fast as possible. The help is a funnel in disguise. Users leave more confused and now have three loan officers calling them.
  2. They don't know what they don't know. Most homeowners don't understand the difference between rate and Annual Percentage Rate (APR), what Principal, Interest, Taxes, and Insurance (PITI) means, how amortization front-loads interest, or what a break-even calculation is. The existing tools assume fluency they don't have: and the ones that don't are so simplified they're useless.
  3. The math is presented without context and in the wrong order. Every existing tool leads with rate. Rate is the least useful number to a homeowner trying to make a life decision. Monthly cost is what people actually live in: it's what determines whether they can afford the baby, the renovation, the breathing room. A rate is meaningless without a monthly payment. A monthly payment is meaningless without a break-even. A break-even is meaningless without knowing how long they plan to stay. PreFi anchors on monthly cost first and builds the math outward from there: a deliberate inversion of a broken industry norm.
  4. They feel judged for their situation. The Cash-Flow Manager archetype is particularly underserved: users who prioritize monthly relief over lifetime savings are implicitly or explicitly made to feel like they're making the wrong choice. The system is built around rate optimization, not life goals.
  5. No one meets them where they are emotionally. A homeowner exploring refinance options might be anxious, excited, overwhelmed, or skeptical: sometimes all four in one session. No existing product detects or responds to emotional state. They get the same experience regardless of where they are, and if they get confused or frustrated there's nothing to catch them.
  6. They have to start over every time. No memory, no persistence, no "welcome back." Every session begins at zero. For a decision this significant: one most people will sit with for weeks or months: the lack of continuity forces users to re-explain their situation repeatedly or give up entirely.
  7. Trust is never established before information is requested. Every existing tool asks for name, email, and phone number before delivering any value. The implicit message is: your information is the product. PreFi's entire model inverts this: but it's a meaningful enough pain point that it needs to be called out explicitly as what's broken today.
  8. The experience is built for the transaction, not the decision. Most tools are optimized for the moment a user is ready to apply: not the much longer, messier period where they're trying to figure out if and why. PreFi's entire audience lives in that pre-decision space and nobody is serving them there.
  9. Veterans and underserved borrowers are disproportionately failed. The complexity and sales-first nature of existing tools hits hardest for first-generation homeowners, veterans, and anyone without a financially literate network to call. They're not less capable: they just never got the context everyone else inherited. This is the mission underneath the product.
  10. The advice they do get is anecdotal and unqualified. "Ask friends on Facebook" is not a joke: it's genuinely what people do. They get conflicting, context-free advice from people whose situations are completely different from theirs, filtered through whatever their friend's loan officer told them two years ago.

FAQs

Who are the decision makers for the Clarity Engine?

Primary: David Kawata

Secondary: Sydney Bocik, Ken Bartz

Is there an existing brand?

PreFi does not have an existing brand. Purlend has an existing website, but we are likely going to want to change this. We will need to be able to support this brand fork at some point which we can discuss during discovery.

Who is developing this technically and when?

Our technical partner is Bix Technologies. We are kicking off as soon as possible which will consist of a 4-week discovery. There are items that will overlap with design in their SOW timeline below, so we are looking to align design and development early on in the process to avoid overlap.

  1. Discovery Phase (~4 weeks): Runs first. Key deliverables include refined MVP scope, core user flows across all 5 motivations, interactive UI prototype for Stages 1-3 including the "Magical Moment" with animation timing, emotional design language spec ("Calm Confidence"), system architecture and API specs, AI/math engine validation plan, and sprint-by-sprint plan.
  2. Development Phase (Alpha to MVP to Production): Follows immediately after Discovery. Sprints are 2 weeks long, with continuous shipping to a shared Preview environment.

How do design and development stay aligned during the build?

This is a discussion we want to have on day one of kickoff. At minimum we think it's best to have a shared review cadence, agreed handoff formats from Figma or Lovable including component specs and animation timing, and a clear owner for flagging when a design decision has technical implications that need to be resolved before implementation.

What tools are in place?

Roam (meeting and chat functions), Figma, GitHub, Lovable, Jira, Confluence, Notion. For a document repository, we can set up a Google Drive folder for this project.

Who are our data partners and how does data collection work?

ATTOM Data: For property and mortgage data, we are likely integrating with ATTOM Data to automatically populate property details: estimated home value, property type, lot size, year built, tax assessment, existing loan estimates, etc., the moment a user enters their address.

Array: For credit verification, we are likely integrating with Array for a soft credit pull, which does not affect credit score and is only offered after account creation, never before. Note: When we get to stage 4 and the marketplace, we will likely need a hard credit pull, and lenders require a trimerge pull for underwriting.

Freddie Mac PMMS (GSE): For national mortgage rate benchmarking, we are integrating with Freddie Mac's Primary Mortgage Market Survey (PMMS) to ensure scenario calculations reflect current market conditions. The PMMS publishes weekly every Thursday at noon ET and covers 30-year fixed, 15-year fixed, and 5/1 ARM national averages, derived from thousands of actual loan applications submitted to Freddie Mac. One important consideration: Freddie Mac does not offer a direct public API for PMMS data. The most reliable programmatic access is through the St. Louis Fed's FRED API, which mirrors PMMS data and is freely available. Also worth noting: PMMS rates reflect conventional conforming purchase loans with 20% down and excellent credit: they are national averages, not personalized quotes. Every scenario card must disclose this clearly.

Rationale

The philosophy behind this is deliberate and worth understanding as a design principle: we want to bring in as much information about the user and their property as possible while asking them to enter as little as possible. The moment someone types their address, the platform should already know their situation. This is the first and most important trust signal PreFi delivers: value before ask, always.

They should not have to give their name, email, or phone number until they're ready to move forward and save their progress or create a profile.

This directly addresses one of the core pain points we are building against: every existing tool in this space requires a user to hand over their name, email, and phone number before receiving anything in return. The Clarity Engine inverts that entirely. The data infrastructure exists to serve the user, not to qualify them as a lead. Design should reinforce this at every step: the experience of data appearing automatically should feel like the platform is working for you, not gathering information about you.

What is the Now, Next, Later+ Vision?

Now: Proving the Empowerment Model (P1 & P2)

PreFi and Purlend are building the Clarity Engine together. The first expression of that engine is PreFi's anonymous refinance exploration experience: a homeowner enters their property address, the platform hydrates their situation automatically, an AI conversation understands their goals, and scenario cards show parallel paths with no ranking, no steering, and no lead capture before value is delivered. Just clear benefits and tradeoffs that are hyper personalized. They leave feeling informed and in control, whether or not they ever create an account.

This is not a prototype. It is a production Alpha product built API-first, as a standalone service, so that every component we ship today can be distributed, white-labeled, and embedded independently tomorrow. The conversation engine, the scenario math, the emotional intelligence layer, the property data hydration: each is its own service. We are not building a monolith we will later have to break apart.

P2 follows immediately after beta validates the model: PDF reports, shareable scenarios, advanced calculators, and refinement trained on real user data. At this stage, we are not focused on monetization of the end consumer. That will come in P3 or P4.

Next: Extending the Engine (P3 & P4)

P3 extends the Clarity Engine into ongoing homeowner value. PreFi stops being a one-time refinance exploration tool and becomes the homeowner's ongoing advisor: property tax optimization, insurance intelligence, equity strategy, and proactive opportunity alerts delivered at the right moment across the full arc of homeownership. Every P3 interaction generates training data that makes the system smarter.

P4 is the marketplace and undefined monetization layer: lender marketplace, lead quality packages, white-label infrastructure, API distribution, multi-tenant architecture, and partnership integrations. This is where the Clarity Engine becomes a platform and true intelligence layer.

The Later: A Fork, Two Brands, One Engine

P3 or P4 is also where PreFi and Purlend begin expressing their distinct identities at full scale. The Clarity Engine remains the shared intelligence underneath both. The surface, the audience, and the mission diverge.

PreFi is B2C. It serves homeowners directly: the people sitting at their kitchen table at 10pm trying to figure out if refinancing makes sense, whether they're paying too much in property taxes, whether their insurance actually covers what they think it does. PreFi is the product they return to across the full arc of owning a home.

Purlend is B2B2C. It serves the industry (realtors) and through the industry, reaches borrowers at scale.

The timing for the fork in the road between the brands is not yet defined, but we will need to make a copy of the code and account for there being two brands in the future.

The Later+: Purlend: The Digital Lending Highway

Purlend's vision is the Digital Lending Highway: a full-funnel platform, from Search to Settlement, that brings verified affordability and real underwriting intelligence to the very start of the home financing journey, not after the offer is accepted and the damage is done.

The platform runs on three rails: Structure → Search → Settle. Real underwriting and curing of issues upfront. Personalized affordability guiding borrowers to homes they can actually buy during search. The best products and programs orchestrated automatically at settlement. Borrowers and properties verified before the offer, not after.

The long arc extends from refinance and purchase into a complete picture of how Americans manage the largest asset they will ever own, and eventually, how they optimize every liability across their financial life.