Concepts
Working models for thinking about autonomous engineering, technical delivery and the organisations around them.
Archive
3 entries. Dates reflect publication or the current working version.
- Building a Persistent AI Engineering AgentHow to build an agent that picks up a ticket, works across six repositories for days, survives restarts and produces reviewable pull requests. Make the work persistent, not the model.
- 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.
- The Agentic SprintA human-gated operating model for autonomous software delivery.