OutSystems, a leading Agentic Systems Platform, is expanding its Agentic Industry Solutions portfolio for banking, enabling financial institutions to modernize consumer lending by bringing agents, customer-facing applications, and deterministic workflows together into a governed system that institutions can adapt to their own products, policies, and existing banking systems.

“OutSystems Agentic Loan Applications layers over existing banking systems. By grounding agents in an operational context—including the bank’s policies, systems, and dependencies—it helps them operate more efficiently and accurately while keeping every lending decision under the bank’s control.” – according to the press release.

While banks are rapidly adopting AI, they face mounting pressure to translate these investments into ROI by moving from experimentation to high-impact customer journeys – all while maintaining the strict governance, auditability, and human oversight required in a highly regulated industry. Yet many lending experiences still rely on lengthy forms, manual document collection, repetitive data entry, and fragmented handoffs that delay when loan officers can act and increase the risk of application abandonment. The result is a dual mandate for financial institutions: to improve the consumer experience and reduce operational friction so they can grow faster, while still maintaining the reproducible and auditable operations essential to risk and compliance teams.

“Banks do not need more isolated agents. They need governed agentic systems that improve real customer journeys and can stand up to risk review,” said Luis Blando, OutSystems CPTO. “OutSystems brings agents into auditable workflows so institutions can move beyond isolated pilots and apply AI to complex lending journeys with the oversight the industry requires.”

A governed approach to agents in consumer lending

OutSystems Agentic Loan Applications demonstrates this approach in practice. Built on the OutSystems Agentic Systems Platform, leading financial institutions, including KeyBank, Paragon Bank, and Axos Bank, trust OutSystems with their most highly regulated decisions.

“Hope is not a governance strategy. As AI adoption accelerates, banks need full visibility into how agentic solutions are built, what data they’re accessing, and how they’re being used,” said Mike Reynolds, Business Technology Executive at KeyBank. “Striving for centralized governance layers provides the oversight, auditability, and controls necessary to innovate confidently while staying within regulatory guardrails.”

Agentic Loan Applications combines mobile and web applications, data models, governed agents, and deterministic workflows to help banks address the manual, document-heavy work surrounding lending decisions:

• A guided, agent-assisted application journey: Agentic Loan Applications captures and verifies documents, runs identity and sanctions screening, and compiles a complete application that passes to the bank’s existing loan origination system.
• Agents evaluated before they reach production: Banking agents are rigorously tested against dozens of agent evaluations encompassing criteria like relevance, accuracy, PII protection, and many others. Re-testing after any model, prompt, or tool modification ensures agents reliably remain within guardrails.
• Model selection tested for cost and accuracy: OutSystems evaluated multiple models through Amazon Bedrock and pre-selected models that perform optimally at up to 82% lower cost. Banks configure the system around their own products, policies, and existing banking systems while retaining control over their data.

“This approach reflects the broader OutSystems strategy for Agentic Industry Solutions: pairing pre-built industry capabilities with OutSystems unified platform so organizations can apply AI to real operational processes. The OutSystems Banking Agents Kit is also available on the OutSystems Forge, providing developers with building blocks for creating banking apps and agents on the OutSystems platform.” – the company explained.