DEV Community

Discussion on: What code review process do you use for AI-generated code?

Collapse
 
dtannen profile image
dtannen

I find a multi model review that runs in a cycle provides meaningfully better results. E.g. let's say claude wrote the code. I have gemini/gpt/claude all review it independently and then synthesize the results. I keep reviewing until the review output is no longer helpful / fixing issues. My human judgement is only needed to determine at what point the review output is counterproductive.

Collapse
 
manthanbhatt profile image
Manthan Bhatt

That is a smart approach. Cross-reviewing AI-generated code with multiple models seems like a practical way to reduce blind spots and catch different kinds of issues.

I also liked your point that human judgment is still essential, especially in deciding when more review stops adding value.

Would you be open to sharing your actual workflow or template for this? For example, how you structure the review cycle, what you ask each model to check, and what signals tell you it is time to stop iterating.

I think that would be really useful for people trying to turn this into a repeatable process instead of doing it ad hoc.

Collapse
 
dtannen profile image
dtannen

pretty straightforward-- here is 1 cycle:

  1. fan-out to all reviewers
  2. gather all responses and synthesize results
  3. implement changes
  4. go to 1

Github Repo

Thread Thread
 
manthanbhatt profile image
Manthan Bhatt

Thanks for sharing this.
I will check it out. This seems interesting