Agent Orchestration Is a Graph Problem, Not a Prompt Problem
Why linear agent chains waste most of their wall-clock, how to find the parallelism hiding in your workflow, and what actually breaks when you fan out to a fleet.
AI Agents
Your Agent Loop Doesn't Know When to Stop
An agent can always produce another answer. Whether the loop converges or burns money depends on four things, and none of them live inside the model.
Google's ADK Is a Runtime, Not a Graph: Notes From Eleven Agents
Eleven agents in, the framework choice that mattered wasn't ergonomics or graph syntax. It was whether the runtime had opinions about events, state, and transport. ADK does. Here is what that buys you in production.
Agentic Coding Is a Different Skill
The executive summary of a free, open-source playbook for Claude Code and Gemini CLI: the handful of ideas that earned their place after months of trial and error.
Agentic Mesh, or Just Another Mesh? Auditing the Lineage Argument
The mesh metaphor for agent systems inherits a lineage that's rewriting itself. A careful audit of where the load-bearing work actually is.