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.
More from coding & agent
- OpenAI launches reusable Codex cloud environments so agents keep working with your laptop closed — jarrodwatts · 2026-09-30
- Vorflux partners with OpenAI: ChatGPT subscriptions now OAuth into its agent harness — ycombinator · 2026-09-30
- Open Dots: a 4.3k-star open-source, self-hosted alternative to OpenAI's Dots — matchaman11 · 2026-09-30
- ChatGPT subscription now works in 16+ partner products including Devin and Notion — charliermarsh · 2026-09-30
- Armin Ronacher: Pi's default theme now follows your terminal's color scheme — mitsuhiko · 2026-09-30
- VendorPulse adds an organizational memory layer to procurement, going beyond static supplier dashboards — GautamRaju2107 · 2026-09-30