TD Bank Group (TD) has launched its first agentic AI model – a major milestone in the Bank’s enterprise-wide AI strategy, to automate and streamline the application process for mortgages and Home Equity Lines of Credit (HELOC).
This is the first step TD is taking to leverage agentic AI to begin an end-to-end transformation of its Real Estate Secured Lending (RESL) operations.
Agentic AI represents the next wave of AI innovation – autonomous AI agents that use generative AI language models to complete tasks with minimal human intervention.
Layer 6, the Bank’s award-winning AI research and development centre, developed its inaugural agentic AI model alongside the Bank’s Global Technology & Solutions, data, Real Estate & Secured Lending and risk management teams. It automates the pre-adjudication process by generating application summary memos for underwriters in minutes instead of hours.
This launch is a foundational step in the Bank’s enterprise-wide AI strategy, which aims to combine advanced machine intelligence with human expertise to deliver faster, simpler and more personalised banking experiences.
The introduction of Agentic AI into RESL reflects how TD is scaling next-generation AI technologies across the organisation to drive efficiency, improve decision-making and move closer to its goal of generating $1bn in annual value from AI in the coming years.
“Agentic AI is enabling us to deliver what clients tell us matters most – speed and simplicity. By providing confident decisions earlier in the homebuying process, one of life’s milestone moments, we’re meeting our clients where they need us most, making the experience simpler and faster.
“This is just the beginning of how we’re using AI to evolve the mortgage experience and bring our promise of being more human to life.”
Mohit Veoli, Senior Vice President, Real Estate Secured Lending, TD
Autonomous agents create application summary memos by classifying client documents, extracting key information, calculating client income and validating figures against select policy requirements, performing consent checks and searching for any discrepancies before generating a concise summary for underwriters.
Early results indicate that agentic AI is reducing this process from an average of 15 hours to an average of less than three minutes, while also providing more accurate results and thereby reducing both risk and the unit cost on adjudication.
“Agentic AI will supercharge our work and put us in a position to deliver more accurate and faster results for our clients. We’re building a hybrid future where our colleagues and AI work together to help our clients get to a ‘yes’ faster on some of their most important decisions. We’re going to approach our vision responsibly so that we maintain the trust of our clients and colleagues.”
Luke Gee, Chief Analytics and AI Officer, TD
This is the first step in transforming the Bank’s RESL operations with agentic AI and generative AI. TD has mapped every step of the RESL journey, from when a client submits their documents to when funding for mortgages or HELOCs is released, and will be introducing agentic AI in each one. TD is also exploring opportunities to introduce Agentic AI in other businesses across the Bank.
The integration of agentic AI will be overseen by the Bank’s Trustworthy AI team, which evaluates AI models on privacy, security, fairness, accountability and explainability and ensures they pass a rigorous series of checks and balances before they encounter humans.
The team continues to monitor models once deployed. The Bank’s Trustworthy AI approach was named Best Responsible AI Program or Initiative in North America by DataIQ in 2025.
