Vercel's AI Software Factory: Agents Author 35% of Merged PRs, Close 70% Issues
lgrammel · x · 2026-08-13
Vercel shared its experience building an "AI software factory" for the AI SDK. The workflow assigns development steps to different agents, with humans reviewing and merging changes.
After four weeks, the system showed significant results: agents authored up to 35% of merged PRs, closed 70% of issues in July, and reduced open bugs by 25%. This demonstrates the potential of AI agents in boosting engineering efficiency and maintaining open-source projects.
Related event: Vercel's Agent Factory Maintains AI SDK Effectively(3 posts)→
More from coding & agent
- Dev builds MCP server that lets AI agents outsource phone calls to real humans — Many_Benefit_3393 · 2026-10-16
- A vector DB is not LLM memory: long thread maps write/read paths, failure modes and evals — techNmak · 2026-10-16
- Mergelock: open-source MCP server catches semantic merge conflicts git misses across parallel AI agents — ksadayamuthu · 2026-10-16
- OpenUI 1.0 launches open source, turning agent text answers into live interactive UIs — heyshrutimishra · 2026-10-16
- 10 GitHub repos to see what your AI agent really did, from Langfuse to claude-code-log — victor_explore · 2026-10-16
- Mosaic: multi-session agentic RL with hierarchical advantage estimation — LARK-Lab · 2026-10-16