What Work Should We Actually Give Coding Agents?
As coding agents become increasingly capable, the important question isn't simply whether an agent can implement something. It's whether we should give the agent the autonomy to do it.
How development changes when agents become active participants in planning, implementation, testing, and delivery.
The infrastructure, constraints, and feedback systems that make coding agents reliable.
Designing the information, tools, and environment agents need to do useful engineering work.
Security architecture for systems that can modify code, invoke tools, and make engineering decisions.
As coding agents become increasingly capable, the important question isn't simply whether an agent can implement something. It's whether we should give the agent the autonomy to do it.
AN ONGOING SERIES / BUILDING AN AGENTIC-FIRST SDLC
An iPhone app that puts a cooling-off timer between you and selected contacts, with encrypted storage that stays on your device.
Explore the project →