Credence
AI Mortgage Concierge
Published 2024
Services
Product Architecture
Frontend Development
Backend Development
AI Integration
Custom Admin Dashboard
Timeline
Scoped, built, and launched in 6 months
About Credence
Credence Funding is a mortgage company that helps people across 24 states get loans without the usual banking nonsense: just clear, sensible advice that actually fits real-life situations. They focus on helping customers secure the right mortgage by actually listening and advising, not just quoting rates.
But as the business grew, so did the challenge of keeping up with inbound leads, especially across different products and campaign funnels.
The Problem
The Credence team was overwhelmed with manual pre-sales work:
Repeating the same early-stage conversations over and over
Manually collecting lead data like credit scores and property details
Answering basic eligibility and payment questions
Following up on cold leads without context or priority
And every customer no matter their goal was getting the same generic website experience.
Credence needed a smarter, more personalised way to guide people toward the right loan and give their brokers time to focus on closing, not qualifying.
Our Solution
We built a fully customised AI Mortgage Concierge: a platform that delivers smart, personalised conversations at scale.
The concierge handles real-time quoting, campaign-specific messaging, lead qualification, and seamless CRM handoff — all while adapting to the user’s financial profile. Once the AI concierge qualifies the lead and runs the numbers, the broker steps in to close — fully informed, with zero time wasted.
What we built
1. Conversational Mortgage Quoting
Users don’t just get answers, they get custom estimates.
The AI concierge pulls real data from Credence’s systems and uses the customer’s:
Postcode
Credit score
Income and property details
to generate:
Personalised refinance or purchase quotes
Monthly payment breakdowns
Eligibility feedback based on their inputs
It’s the same logic a broker would use, but just faster and automated.
2. Campaign-driven AI Assistants
Credence launches individual campaigns using dedicated concierge links — each with its own messaging, tone, and targeting. The AI adapts its intro, prompts, and logic depending on where the user came from and what product they’re interested in.
Each link leads to a different version of the AI bot, depending on what the person’s interested in — like refinancing, locking in a rate, or getting a loan for a home that needs work. These links are shared through ads, emails, or social posts, so users land straight into a conversation that’s actually relevant to them.
3. Admin Panel and Continuous Learning
Credence doesn’t need a developer to update the experience. Through the admin dashboard, the Credence team can:
Upload new product info or FAQs
Train the AI with campaign-specific details
Adjust tone, prompts, and follow-up logic
Create or edit campaign links with a few clicks
Over time, the concierge gets smarter — not just from user input, but from the expanding internal knowledge base that Credence controls. All calculations and recommendations follow Credence’s internal lending criteria and compliance standards.
4. Insellerate CRM Integration
Every qualified lead — name, email, phone, credit score, quote history — is passed directly to Insellerate, Credence’s CRM.
So while the concierge handles:
Answering questions
Calculating real quotes
Collecting and validating lead info
The brokers focus entirely on high-intent users who are already halfway through the process.
Results and Impact
90% of pre-sales work now handled by AI
Faster response time across every product and channel
More relevant lead data available before first broker contact
Smarter segmentation based on real user inputs
Personalised experiences at scale, without added staff
The result is a more modern, scalable, and user-friendly way to sell mortgages.
Timeline
The platform was scoped, built, and launched in 6 months, including:
AI concierge frontend
Admin panel and training tools
Quote engine
CRM integration and data flow
Tech Specs
Frontend
Built with React and Tailwind CSS
Mobile-first design with dynamic flows based on campaign links
Conversational UI that adapts in real-time based on user input
Backend & Data
Node.js, PostgreSQL, tRPC for all app logic and campaign config
Syncs with Incelerate CRM for lead tracking
Pulls personalised financial data (e.g. credit score, postcode, home value) from Credence’s MongoDB to generate live mortgage quotes
AI Engine
Powered by OpenAI, with custom logic per product and campaign
Smart fallback handling and tone-shifting depending on user path
Blends freeform questions with guided inputs (like income or goals)
Admin Panel
Fully self-serve — create/edit campaigns, update AI knowledge, review conversations
Secure role-based access for brokers, marketers, and admins
