Google is enhancing its AI coding agent, Jules, with new functionality that reviews and critiques code while Jules is still working on it.
“In a world of rapid iteration, the critic moves the review to earlier in the process and into the act of generation itself. This means the code you review has already been interrogated, refined, and stress-tested … Great developers don’t just write code, they question it. And now, so does Jules,” Google wrote in a blog post.
According to the company, the coding critic is like a peer reviewer who is familiar with code quality principles and is “unafraid to point out when you’ve reinvented a risky wheel.”
For instance, it might flag a patch that passed all tests but introduced a logic error, a change that compiles but drops a required field, or code that works but is inefficient.
This capability is different from a linter or test because it doesn’t follow specific rules or validate specific assertions. Rather, it understands the intent and context of the code. “It’s closer to a reference-free evaluation method, judging correctness and robustness, without needing a gold-standard implementation,” Google wrote.
In the initial release, the critic evaluates Jules’ output in a single pass, but future iterations will make it a multi-step agent that can use tool calls or be triggered at certain points, like after subtasks or before planning.
