Your Team Doesn't Need to Understand RAG. It Needs These 3 Things

Prudential in Singapore built an AI assistant for its insurance representatives. Six of its own experts graded the answers, and 59% failed. Four months later 99% passed. Nobody on that team had to learn how the model works. A solo episode of Curiosity Code on what people in a financial firm actually need to know about RAG and AI agents. Most need to know how to use it and where it goes wrong. The firm needs three things: an owner who decides what a correct answer is, a set of graded questions it reruns whenever something changes, and a register of which model wrote which answer. I show the three ways an answer goes wrong on a small mock-up (a made-up travel insurer, a real model), then what OpenAI, Anthropic and Singapore's regulator have published about it. Three questions for your team: Which model produced the last AI answer that someone here relied on? If that model changed tomorrow, how would we find out? And who decides what a correct answer is? Chapters 0:00 An AI assistant that failed 59% of the time 0:24 What most people need to know, and what they don't 1:20 Why Prudential's assistant scored 41% 2:35 Three ways an answer goes wrong 6:27 Who does the work 7:28 Three questions for Monday Episodes mentioned Stéphane Malrait, "Burning Cash Too Fast? Why Most Fintechs Collapse Within 3 Years":    • Burning Cash Too Fast? Why Most Fintechs C...   Daniel Flowe, "The DARK Side of AI in Finance, Can We Trust It?":    • The DARK Side of AI in Finance, Can We Tru...   Sources Project MindForge, AI Risk Management Implementation Examples (the Prudential case): https://www.mas.gov.sg/-/media/mas-me... Jeff McMillan of Morgan Stanley on the RegulatingAI podcast (write-up, January 2026): https://americanbazaaronline.com/2026... OpenAI, API deprecations page (read 9 October 2026): https://developers.openai.com/api/doc... Anthropic, "A postmortem of three recent issues" (17 September 2025): https://www.anthropic.com/engineering... Monetary Authority of Singapore, Guidelines on Artificial Intelligence Risk Management (October 2026): https://www.mas.gov.sg/-/media/mas-me... 🎙️ Subscribe for weekly episodes on fintech, AI, and innovation 🌐 Website: https://curiositycodepodcast.com/ 📱 Follow on LinkedIn:   / alexkhomyakov   🎧 Listen on Spotify: https://open.spotify.com/show/4ePKf2q... 🍎 Apple Podcasts: https://podcasts.apple.com/podcast/id... The mock-up in this video is an illustration: the insurer and its policy wording are made up, the model output is real (Claude Opus 5.5, 9 October 2026). Music: "Soundbed" by Blue Saga, via Epidemic Sound. #AIinFinance #RAG #AIAgents #Fintech #CuriosityCode