A plan from Claude comes back as text. Useful text, mostly in the right order, but still a long Markdown document I'm supposed to read top to bottom in a chat window before I let an agent run with it.For a short plan, that's fine. For a real one (a dozen-plus tasks, a dependency graph, a test...
Monday morning, I ask Claude Code to review a plan. I get this:| Conflicts | Gaps | Verdict | |------------------|------------------|-------------------| | Auth ADR breach | No NFR for p99 | major-conflicts | Friday night, same plan, slightly different phrasing...
Part 1 described what gets produced and in what order: requirements feed event storming, event storming feeds bounded contexts and aggregates, those feed RFCs, ADRs, C4 diagrams, and backlog items. This part covers how each step actually runs.There are two failure modes for AI-assisted...