Log inTry now

Research

Applied research on code review accuracy, diffing, cross-repo context, and the agent architecture behind Baz.

July 22, 2026 · Research

Ship: Inference Routing for Agentic Code Review

We evaluated Martian's Ship as an execution layer beneath Baz's code review pipeline. The question was narrow: can we change how model calls are executed without changing the review behavior the agent architecture produces?

Nimrod Kor · 6 min read

July 22, 2026ResearchShip: Inference Routing for Agentic Code ReviewNimrod Kor6mJune 28, 2026ResearchThe vulnerability classes that don't come backGuy Eisenkot14mMay 18, 2026ResearchModel vs. SASTGuy Eisenkot8mMay 12, 2026ResearchCan Cyber-Capable Models Fix AppSec?Guy Eisenkot8mMay 12, 2026ResearchImproving cross-repo context for Baz code-reviewersNimrod Hauser2mMarch 29, 2026ResearchThe anatomy of code review accuracyNimrod Kor8mDecember 15, 2025ResearchSpec Agents as Design ReviewersGuy Eisenkot6mNovember 6, 2025ResearchExtending OpenTelemetry to Pinpoint Code Elements: Our Journey to Close the GapAnton Grubel6mAugust 11, 2025ResearchOrdering Files for AI-Assisted DevelopmentNimrod Hauser12m

Ready to see Baz in action?

Learn from our research, then talk to us about how Baz can help your team.

Book a demo