Mortgage Experiences

UX Tools 

• 365 MS Copilot 

• Figma Make 

• FigJam 

• Jobs To Be Done

Moving through Discovery

To understand the Mortgage industry, a few hypotheses and what is the problem we are trying to address.  I will share in the kick-off conversation.  So what is Discovery? It's a milestone where we start gathering open questions, interviewing stakeholders, and understanding the problem space. Discovery is also 1 of 5 milestones that I've practiced as a product leader over the past 10 years. Do you have a method for product design and strategy? Let's come back to this topic. 

Mundo's conversation with

MS Copilot 

Kicking off the conversation: 

• We want to create a web application within the Mortgage industry.

• Within this application, we have the following persona types: Loan Officer, Loan Assistant, Loan Processor, and Borrower.

• We want the application to streamline the loan process, from receiving a borrower request to financing, within 10–20 days.

Moving through Prompt Engineering 

My learnings over the past year have come from leveraging tools such as Claude, ChatGPT, M365, and other AI tools that use different LLMs to compare and gain familiarity with their capabilities. These are my quick tips and learnings as they relate to Microsoft (MS) Copilot, but can be used for other AI assistant tools. 

1. The MS Copilot is powerful but DUMB! You need to provide context and guardrails, as the conversation will quickly become overwhelming. 

2. Problem statement is GOLD! This is the primary reason you're leveraging an LLM: to help you gather information and quickly understand if IT MAKES SENSE. 

3. ​Convert notes into transcripts to import into MS Copilot to summarize findings. 

4. When you start a conversation, name this conversation "Mundo's Mortgage ​Design Project". This will allow you to include more resources or references to this project. For example, capturing notes via the desktop vs mobile app MS Copilot 

5. You are the expert, don't just cut and paste. Validate that the response is aligned with stakeholders' knowledge or industry practices. And correct MS Copilot by making its language align with your client's business practices. For example, within Mortgage, the term Borrower could be the primary persona type. However, the mortgage company believes the Loan Office is the Primary user of this web application. So the tasks and goals need to be realigned. 

​

Now, let's see what AI shares about the feature types required for the Mortgage company application. 

Ai's response ​

This is where critical thinking is important, and UX Strategy is powerful. is the response below correct? Does this make sense? Are we missing anything? So what do we do with this information?  "Skip the raw data and follow me to the next section". 

1. Borrower Intake & Pre‑Qualification

• Online account creation + identity verification (KYC)

• Smart, guided application flow

• Pre‑qualification questionnaire (income, assets, credit consent)

• Automated document request list based on loan type

• Integration with credit bureaus for instant soft/hard pulls

• Borrower dashboard showing application progress

 
2. Unified Document Management Workspace
A single shared repository for all personas (Loan Officer, Loan Assistant, Loan Processor, Borrower).
Features:

• Secure upload/scan using phone camera

• AI‑powered document classification (W‑2, 1003, paystub, VOE, etc.)

• Real‑time validation (missing pages, unreadable text)

• Version control + audit trails

• Borrower‑specific document checklists

• Permission access per persona

3. Automated Task & Workflow Engine
Designed to move files from application → underwriting → conditions → closing quickly.
Features:

• Role‑based task assignment

• Workflow templates for loan types (conventional, FHA, VA, jumbo)

• SLA timers + alerts for overdue tasks

• Auto‑routing to Loan Processor when documents arrive

• Condition tracking (cleared vs outstanding)

• Escalation logic for bottlenecks

4. Real‑Time Collaboration & Communication Hub
A shared communication layer across all personas.
Features:

• Secure in‑app messaging (no texting/email gaps)

• Commenting directly on documents

• Automated borrower reminders (missing docs, signatures, disclosures)

• Notification center (credit received, appraisal scheduled, underwriting decision)

• LO ↔ Processor ↔ Borrower chat threads

5. Loan Officer Workspace
Features tailored to the LO’s revenue‑driving role:

• Borrower pipeline dashboard

• Automated lead routing

• Pre‑approval letter generator

• Pricing engine integration (rates, fees, scenarios)

• CRM‑light tools (notes, follow‑ups, reminders)

6. Loan Assistant & Loan Processor Tools
Tools designed to eliminate manual operations.
Features:

• Automated document review assistance (AI: detect missing docs, compare values)

• Automated follow‑up generation

• Condition and milestone management

• Integration with DU/LP and AUS decisioning

• Fraud/identity flagging

7. Borrower Portal
Easy, transparent experience for the borrower.
Features:

• Step‑by‑step progress tracker

• Secure document upload

• Digital disclosure review & e‑sign

• Payment portal for appraisal fees

• Notifications for changes or status updates

• FAQs / help center

8. Integrations (Critical for 10–20 Day Close Time)

• Credit bureaus (Experian, TransUnion, Equifax)

• AUS (Desktop Underwriter, Loan Product Advisor)

• Pricing engines (Optimal Blue, Polly, etc.)

• Title & escrow

• e-Sign platform (DocuSign, Notarize)

• VOE/VOI providers (Equifax The Work Number, Truv)

• LOS if applicable (Encompass, MeridianLink, etc.)

9. Compliance, Audit & Security Layer

• Audit trails for all actions

• HMDA data capture

• Automated compliance alerts (TRID timing, ECOA notifications)

• Role‑based permissions

• SOC 2/GDPR/CCPA alignment

• Secure encryption + MFA

10. Analytics & Operational Intelligence

• Loan cycle‑time reporting

• Bottleneck detection

• Persona productivity metrics

• Drop‑off analysis

• Forecasting for closing timelines

• Regulatory reporting

Output of Discovery 

Leveraging AI tools has accelerated my process but it has also introduced me to more opportunities to further understand my craft.  

Mundo's conversation with

MS Copilot 

Additional Chat prompts 

• Summarize the features list into a bullet point list with 5 items. 

• How does this information look in CXDNA? Reference AI Strategy for Business Transformation?  

• Let's see what this looks like in the Jobs to be Done framework

• Can you present the jobs to be done in a Table format? 

• Break out the Jobs to be done by persona types. 

I've created a separate page to demonstrate all command prompts and outputs to further view my Discovery journey 

Mundo's summary

I believe that using any tool is not the end of a trade. The tool is only as good as the person who picks it up and learns its capabilities. 

​

AI tools are strong; they can consolidate large amounts of data, but it's up to you, the user, to make sense of the organization. Within Human-Centered Design, information architecture is a fundamental practice for organizing and making sense of complex patterns. This goes back to the days of learning from authors such as Nielsen Norman and Don't Make Me Think. 

​

The NEW goals of the AI tools are to help us Crawl, Walk, Run, and FLY!  As a technologist and UX professional i'm here to share.  Let's keep it real. If you don't get the foundation right your still going to stumble. What are the foundational items that you can't skip?  Here are some items to think about

Can you skip building persona types? Can you start without understanding the problem space? What type of tools will you need to help you define success? How do you define success?  

​

As an AI Strategist, I'll continue to share my insights if you continue to advocate for human-centered design.