The 'flashlight not a blocker' distinction is the right call. Curious to know - how do you handling false positive rate in practice?
In our experience with LLM-based code analysis, the signal-to-noise ratio is the thing that determines whether teams actually use the tool or just forget about it after a week.
I think the blocker is that engineers do not want to take responsibility for the design, and the designer doesn't feel confortable with claude code. But this is a gap that will close soon.
In our experience with LLM-based code analysis, the signal-to-noise ratio is the thing that determines whether teams actually use the tool or just forget about it after a week.