Sakana AI builds AI agents to automate loan origination work at Japanese banks

Sakana AI has transitioned from research to applied work, deploying AI agents to handle loan origination, client analysis, and proposal drafting at banks. The company's Applied Team, led by engineers Shota Sakai and Katsuhiro Honda, focuses on automating repetitive analytical tasks like gathering client information, analyzing financial data, and drafting proposals. These agents do not replace loan officers but handle initial analysis and document drafting, freeing employees to focus on client relationships and final approval decisions. The team faces the technical challenge of defining "sufficient business quality" for AI systems, particularly given financial institutions' strict security, cloud, and legacy system integration requirements. Sakana AI's approach integrates AI into workflows from the start, utilizing clear instructions, validation environments, and sandbox execution to maintain rigorous governance. The company emphasizes collaboration across business, product, and research roles, aiming to establish its technology as the standard for AI use in Japan before competing globally. This shift requires delivering integrated solutions across user experience, application design, security, and operational evaluation, moving from research papers to shipping products that work in real-world banking environments.

(Source：Complete Ai Training)