Why a one-line change can break your whole stack — Qodo on review as the new bottleneck
AI Engineer · youtube · 2026-10-29
At the AI Engineer summit, Qodo solutions engineer Cole Gannaway explained why review has become the bottleneck as code generation accelerates: a one-line data model change can pass every test yet silently break web, mobile, CLI, and MCP clients.
Key points:
- Build a software graph of your repos to reveal the blast radius of any change.
- Turn tribal knowledge and PR comments into custom review rules.
- Bring review context in before code is written, not after.
- The agent that wrote the code shouldn't grade it; check PRs against the original ticket to catch intent drift.
The full talk includes a Q&A on catching wrong intent.
More from coding & agent
- How I turned Claude into a full ad agency with two connectors — one afternoon vs 3-6 weeks — PrajwalTomar_ · 2026-10-29
- How we share MCP servers company-wide without giving every agent every credential — Kluff_AI · 2026-10-29
- XBOW's AI agent finds critical unauthenticated RCE in EAC voting calculator, fixed before midterms — moyix · 2026-10-29
- PipesHub dumped Docling for pdfplumber: parse time halved, memory down 1GB — Effective-Ad2060 · 2026-10-29
- What an agent approval prompt must show to catch prompt injection — ComprehensiveShake76 · 2026-10-29
- GitHub commits hit 7.38B in September, 5x a year ago as agents flood in — rohanpaul_ai · 2026-10-29