Dear makers, do you keep somewhere the AI decision logs and what do you do with them? Say I have a AI chat and I ask it - create me this and that and they I use the results for something that brings bad user experience. Do you keep a log for the decision tree or the process and why?
Apart from your own use, is there a Law somewhere in the world that requires you to do that?
Thanks!
31 views
Replies
Best
Hey Bogo! Great question.
I'm actually building something for this ... claude-guardian, an open-source tool that hooks into Claude Code and automatically captures decisions you make during coding sessions. It stores them per-project in SQLite and surfaces them before the AI does something conflicting.
It also has a dashboard where you can see every captured decision, how many times it was surfaced, and whether it was AI-curated ... basically an audit trail for AI-assisted decisions. With regulations like the EU AI Act pushing for AI decision logging, this kind of tooling will probably become standard.
Still early but happy to share more :) Here are some shots:
Replies
Hey Bogo! Great question.
I'm actually building something for this ... claude-guardian, an open-source tool that hooks into Claude Code and automatically captures decisions you make during coding sessions. It stores them per-project in SQLite and surfaces them before the AI does something conflicting.
It also has a dashboard where you can see every captured decision, how many times it was surfaced, and whether it was AI-curated ... basically an audit trail for AI-assisted decisions. With regulations like the EU AI Act pushing for AI decision logging, this kind of tooling will probably become standard.
Still early but happy to share more :)
Here are some shots: