omg I've been waiting for someone to build this for so long
- Both things are like... a prompt awayi would kill for this type of view in codex
- this is the wayReplying to @cgencoYeah this deserves a full blog post 1. Ingestion layer processes all of your sources. Summarize/extract, then embed. Grab as much metadata as possible for faceted searching later. 2. Ingest as many sources as possible. Email, Slack, Zoom calls, etc. 3. Normalize your
- Current models are great at optimizing code, if you ask them to.Everyone who thinks AI slop will ruin code efficiency/performance is going to be so surprised when everything is absurdly well-optimized John Carmack style machine code.
- I tried all of the TUI coding agents and not a single one of them feels perfect, yet all have some unique features I like. Maybe the future is everyone building their own. It's easy to start and when you need new features you just say "hey copy feature X from agent Y".








