Modern software systems are increasingly automated. We automate deployments, infrastructure changes, scaling, incident response, and data pipelines. And now, with AI agents, we are starting to automat

Markdown supported · ⌘↵ to post
Evidence first fraud agents need a frozen graph snapshot per decision. I store the hop list with the verdict so a later review can replay the same edges.
Vlad Zoff
The replayability point is important. Once the decision depends on a graph or other external state, recording only the final verdict isn't enough because the evidence can change underneath it.
Keeping the relevant snapshot with the decision turns "this was approved" into something that can actually be reconstructed later.