Building the AI Agent Is Easy. Proving It's Safe Isn't - Jonathan Osborne, NatWest
Source
youtube.com
Author
AI Engineer
Date
Why it matters
Shows concrete evidence that aggregate pass rates and LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → judges can mislead, and a rollout pattern (routing funnel, shadow mode, feature flags) for shipping agents in regulated settings.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
videoWhy AI Makes You 100x Faster but Not Your Company - Mitchell Troyanovsky, Basis
videoDon't Approve the AI Model. Approve the App - Doneyli De Jesus, Langfuse
videoWithout Caching, Your AI Agent Costs 10x More - George Cameron, Artificial Analysis
videoYour AI Agents Shouldn't Care Where They Run - Nikhil Harithas, Factory
videoVoice AI Where One Wrong Question Breaks the Rules - Shiv Indap, Upstart & Brooke Hopkins, CovalAI Engineer
videoWhat a $900M Bank Error Teaches Us About AI Agents - John Feminella, Two SigmaAI Engineer
articleCrossing the Threshold: How OpenAI and Anthropic Approach Autonomy and Safety in Financial AgentsRichard MacManus