what does the 'last human code review' look like? to @itamar_mar, ceo and founder of @QodoAI, it looks like two agents talking to each other…

what does the "last human code review" look like? to @itamar_mar, ceo and founder of @QodoAI, it looks like two agents talking to each other, backed by a context engine specific to your organization. @QodoAI is building the AI code review and governance layer for that world, plus the context engine that gives those agents the judgment to review at a human bar. i sat down with @itamar_mar at our @aiDotEngineer booth, right after his talk "the last human code review." his argument: as we push for velocity, we stop reviewing code line by line, then diff by diff, and review eventually becomes a graph of your architecture where every PR lights up its blast radius. watch our full conversation here! 0:54 "the last human code review" 1:57 what code review looks like with no human in the loop 5:06 how human scars can inform agentic decisions 6:06 what an "artificial wisdom system" really is 9:44 qodo's real moat: their context engine 16:52 how to keep humans in control Media

Source: Itamar Friedman (X) | 2026-08-03