Agentic Code Review

O'Reilly Radar's Mike Loukides argues the real bottleneck for shipping AI-assisted code is no longer generation, it's review. He lays out why agentic review tools can catch the security, correctness, and style failures that human reviewers miss when diffs are being produced at ma

Loukides argues the traditional reviewer — a senior engineer skimming a PR — was designed for human-written code that already carries authorial context. With agents writing most of a repo's new code, review becomes a verification problem at population scale. He catalogs the failure modes reviewers should expect: prompt-injection leftovers, hallucinated APIs, license-incompatible dependencies, and tests that pass but don't actually exercise the changed code. His prediction: agentic review becomes a distinct engineering discipline rather than a feature of existing CI tooling, with tools like Verity, Graphify, and the Snyk Evo family positioned as early entrants.