Agent PRs merge at just 32.7% vs 84.4% for humans, with 91% more review time
gerardsans · x · 2026-11-09
Citing new data, gerardsans argues the bottleneck in AI coding has shifted from writing code to trusting it:
- Only 32.7% of agent-authored PRs merge within 30 days, versus 84.4% for humans
- Review time is up 91% for just 21% more tasks
- Controls haven't kept up with agent speed: code snippets are online, but the decisions behind them aren't — you can't sample what isn't in the data
Takeaway: agents generate code far faster, but human review and trust have become the new bottleneck.
Related event: Agent PR merge rate of 32.7% exposes AI coding trust gap(2 posts)→
More from coding & agent
- Peer-reviewed paper applies truth maintenance systems to LLM memory belief revision — letandrewcook · 2026-11-09
- System One models are back: decision/extraction APIs cut insurance claim flow from 61.7s to 19.3s — max_gladysh · 2026-11-09
- User builds a 'chief of staff' Grok agent that runs projects and sends one weekly brief — RachelVT42 · 2026-11-09
- 10 Open-Source Tools for Building Trustworthy AI Apps, from Langfuse to TruLens — Shruti_0810 · 2026-11-09
- Shipping AI agents: attack it before release, read the traces, not just the answers — Plastic_Secret1303 · 2026-11-09
- Appwrite launches MCP1: one URL for every MCP server your team uses — eldadfux · 2026-11-09