Article six of my personal coding constitution: the rules exist for a reason, and the override is the documented escape hatch, not a habit. The mechanics that keep the override from rotting the rest of the constitution into theater.
Article five of my personal coding constitution: every action that mutates state must leave evidence. The trail isn't for the auditors. It's the thing that earns me the right to keep going.
The multi-agent demos make it look like running several agents in parallel multiplies your output. The git-worktree pattern shows the actual shape of what works, and exposes the trick the multi-agent framing is using.
The atomic-unit metaphor in software isn't decoration. It's a working design pattern: small immutable typed primitives (atoms) compose into larger functional units (molecules). What makes the metaphor useful, versioning, lineage, composition rules, and what makes it a marketing trap.
If your self-service form has eighty-nine questions on it, you haven't designed a decision surface, you've handed off a configuration job. The five-not-eighty-nine test: can the business owner read the surface in five minutes and know what they're choosing? Here's how to apply it.
Three quarters of incident debugging time used to come from not knowing what the AI did. Logging every tool call into a queryable store changed that, small infrastructure investment, outsized return.
Destructive operations get a second look. Soft-delete by default. Backup before mutation. The bias is toward keeping the thing, and that bias gets stronger, not weaker, when an agent is the one running the command.
When something is broken you get three attempts to fix it before you must stop and re-plan. Why 'just one more try' is the failure mode, and why the rule matters most when an agent is the one trying.
The first article of my personal coding constitution: every change starts with a tracked issue, not a commit. I had to write this rule down for myself before I'd live by it. Then I had to write it down again for the agents I work with.
Tech debt was the unfunded liability of an engineering team for two decades. Context drift, the slow erosion of what the AI tools think you're doing, is the equivalent for AI-augmented teams. Same shape, different substrate.
Deployment frequency, lead time, change-failure rate, MTTR. The DORA framework worked for a decade because it measured the right things. AI-augmented engineering is bending those metrics in interesting ways and exposing the next thing to measure.
A month past the OPA-renaissance piece, with more shops actually shipping agent-policy stacks. Worth getting concrete about what the production deployments look like, the patterns, the policy bundle structure, and the interfaces that survive contact with reality.
