Comment by johnsmith1840

This is why agents suck.

Backpedling is a massive inefficiency.

A better way is the single clean step approach.

Use the largest LLM you can. Have it generate a single output for one update.

If that update has logical errors or dropped anything you asked for restart, refine, narrow until it does.

It's quite hard to plan each step right but the level and conplexity you can get to is far higher than an agent.

Agents are much better at the shallow/broad problems.

Large LLMs are exponentially better deep/narrow problems.