|4 min read
Before Buying More AI Seats, Fix One Handoff
A CI alert becomes useful work when its revision, evidence and next owner survive the handoff; another prompt template does not supply them.
[AI & Data][Business & Strategy]
5 posts
A CI alert becomes useful work when its revision, evidence and next owner survive the handoff; another prompt template does not supply them.
Principles 6–14. How work moves through an agentic engineering team: the ticket as contract, AI distillation with human curation, three gates, verification before done, characterisation tests, the 1.2× capacity rule, the J-curve, and telemetry.
Principles 1–5. The five rules that everything else in the framework rests on: standardise the harness, make verification load-bearing, default to plan mode, pick the cheapest layer, reflect every task.
GitHub said 55%. Then they ran the enterprise RCT and got 8.69%. Faros's two-year telemetry shows throughput up 66% and incidents up 243%. The honest net is 1.2–1.5×. Plan your team capacity accordingly.
Most teams plateau at Stage 2 because they confuse 'we built skills' with 'we have a working AI engineering culture.' Here's the 5-stage diagnostic — and the moves that get you from Individual to Distributed.