One prompt before bed: agent delivers a stack of verified performance PRs via Alchemy

samgoodwin89 · x · 2026-09-30

Developer RhysSullivan is again praising Alchemy (alchemyrun): he sent a single prompt telling his agent to improve performance and use Alchemy to measure the impact, and woke up to a reviewable stack of PRs with performance improvements.

He credits the verification loop as the key — the agent can measure whether each change actually helps and iterate accordingly. The "set a goal, auto-verify, ship PRs" workflow is directly reusable.

Original post →

More from coding & agent

coding & agent channel →