Show HN: Huzzah – a novel approach to coding with AI

Post by tananan » Fri, Aug 21, 2026, 4:42 PM UTC

greenpizza13 wrote: post #215

tananan wrote: post #191

Preface: unpolished thoughts — it is refreshing to see so many people working on this issue! Lately I've been dreaming about a way of using LLMs that never (or in majority of the cases) results in chatting with an agent or checking its traces. Instead, you provide prompts in natural language, e.g. refactor these modules in this way ..., and the result is shown as a visual proposal (some kind of diff on a graph). Then…

Check out Plannotator. It’s not exactly visual, but instead of chats you just give something more like an inline code review. Highlight text, add emoji reactions, contextual comments. This is my preferred way of reveling AI plans. Now I’ve started using it to open planning sessions on existing files and annotating them instead of starting from a prompt, in some cases.