Tag: agents
All the articles with the tag "agents".
-
Declarative Development: Tests First, Code Second
Coding agents are good at iterating towards a result, provided we define that result independently. Tests, contracts, and feedback loops make it easier to detect when an implementation has drifted from our intent.
-
Two Security Boundaries for AI-Assisted Development
A sandbox limits what an agent can damage while it works; it cannot tell you whether the resulting code is safe to ship. AI-assisted development needs separate controls for the runtime and the artefact.
-
Building a Personal Brain OS for Your AI Agent
An agent does not need your entire knowledge base in every prompt. It needs a structure that reveals the right instructions, memories, and source material when the work calls for them.
-
Teaching Your Agent Standard Operating Procedures
Skills can encode Standard Operating Procedures without loading every instruction upfront. One activation experiment shows why descriptions, evals, and hooks still matter.
-
The Great Agent Tooling Debate
MCP offers discovery and a standard interface; CLIs offer composability and familiar controls. I compare their costs and explain why my default is CLI-first, not CLI-only.