📢 I shared a new article on GenUI 🚀 medium.com/p/a6db3653b9b6 This post sets up the next one, where I will look at Flutter’s GenUI SDK directly. It is about how I accidentally built a custom GenUI style refinement flow using Gemini structured outputs, schemas, and native Flutter widgets. The next article in the series will take that same problem and explore what changes when I use Flutter GenUI SDK instead of something I wired by hand.

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across @FutureAGI_ bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → github.com/future-agi/future… Try it here → shorturl.at/PRSGX