Building agents with good (often expensive) taste

February 20, 2024 at 03:22 PM

Note: This is not a blog, it's a semi-private digital garden with mostly first drafts that are often co-written with an LLM. Unless I shared this link with you directly, you might be missing important context or reading an outdated perspective.

For building my interactive explanations, I have a very specific workflow:

  1. Start in Claude.ai for small atomic units
  2. Move to Cursor when the file gets large

For real projects, I stay in Cursor

Whether there’s a good clarifier

The branching factor of a planner

The hard limit of an evaluator-optimizer