Concepts

Working models for thinking about autonomous engineering, technical delivery and the organisations around them.

Archive

2 entries. Dates reflect publication or the current working version.

  1. The Agent Never Logged OffPersistent AI agents are about to break one of security's oldest assumptions, that activity has boundaries. A case for continuous agent authority, authority leases and memory provenance.Concept · 20 min read
  2. The Agentic SprintA human-gated operating model for autonomous software delivery.Concept · 21 min read