Manual Prompt Writing Beats Automated Agent Optimization, Dev Finds

BraceSproul · x · 2026-08-03

Developer Brace Sproul shared practical insights on prompt optimization, noting that humans are still crucially needed in the loop. While agents are useful for reading traces and running scripts, manual prompt writing often yields better results.

Sproul spent about three days trying to automate the optimization of the OpenWiki prompt using Codex via hill climbing, but eval scores barely increased. Switching to full manual mode, he made more progress in a few hours than the agent did in three days.

Original post →

More from coding & agent

coding & agent channel →