22 Agentic Engineering Evaluation

Summary

These slides are based on Chapter On SWE-Bench Pro, six frontier models land within a couple of percentage points of each other. The harness they run inside shifts ... Thank you TestSprite for sponsoring! Check them out at: testsprite.com/?via=brandon-9n Google's report: ... Most AI tutorials show you a chatbot demo. This video shows you how that demo actually becomes a production system inside a ... Find everything from me: linktr.ee/kunchenguid my discord server: discord.gg/Wsy2NpnZDu firstmate: ... For the past year, developers have embraced vibe coding—prompt an AI, accept the code, and move on. It works brilliantly for ... Move Beyond AI Demos. Ship Production-Ready Something's shifting in how software gets built. It's called AI agents are everywhere right now. But are they actually working inside real 90% of developers are using AI at work. Only 13% of companies have a plan for it. Welcome to the reality of modern software ... The main thesis of the video is that building successful AI applications requires a sophisticated A second refund on the same order. A payout sent to the support desk instead of the buyer. An order status of "probably shipped. written version: dylanebert.com/