AI writes more PRs — Sonar's answer: agentic validation that reviews, fixes and auto-merges
AI Engineer · youtube · 2026-10-09
At AI Engineer World's Fair 2026, Gitar co-founder Ali-Reza Adl-Tabatabai (now Sonar) argues AI means more, bigger PRs and more bugs, making CI and code review the bottleneck: teams must slow down or rubber-stamp. His answer is agentic validation — an agent that does noise-free review, explains CI failures, catches flaky tests, autofixes until green, and auto-approves/merges by user-set rules, with teams building trust step by step toward full automation. Architecture includes a control plane, custom harness, and LLM proxy; combining agents with program analysis in SonarQube beats either alone.
More from coding & agent
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23
- Capy 0.5.0 lets Claude Pro/Max subscribers reuse their plan quota, adds OIDC cloud access — garrytan · 2026-10-23
- You.com CEO Richard Socher: legacy code is human slop, let AI clean it up — RichardSocher · 2026-10-23
- Let agents design a single-line glance component so you can track them from the sidebar — blixt · 2026-10-23