AI makes mistakes, it's stochastic, here's how I manage those
AI is fundamentally probabilistic and will make mistakes. Seven ways I manage that, from human review to fresh-context judges to shrinking the blast radius of any single error.
DTC operator · AI builder
7 years scaling consumer brands. Now building AI systems. Writing at the intersection — for operators who want the structural view, not the ChatGPT-for-email take.
AI is fundamentally probabilistic and will make mistakes. Seven ways I manage that, from human review to fresh-context judges to shrinking the blast radius of any single error.
Here's my current AI stack: open source, a dedicated memory system, multi-agent access, spec judges, evals, and as much of the process in code as possible.
A git-owned knowledge base is markdown in a repo you control. A YC launch listed that as a hack. You want a record you can diff, refuse, and take with you.