Deep-dive guides on AI agents, agent orchestration, MCP, and developer tooling.
7 posts found
Agent traces have a runtime-decided shape, token-based cost, and cross-process tool hops that conventional APM was never built for — here is what OpenTelemetry's gen_ai.* conventions actually pin down, and where tracing an agent loop still breaks in production.
AI coding assistants aren't one architecture — they're three separable design decisions (how context gets assembled, how edits get applied, how execution gets contained) that every tool from Claude Code to Cursor answers differently.
In agent systems, instructions live across four surfaces — system prompt, tool schemas, tool results, and few-shot text — not one. Most prompt debugging still only looks at the first.
The three dominant multi-agent orchestration topologies each fail in a different, predictable way once you move past the demo — here is how to pick one based on where your task actually breaks, not which pattern sounds more sophisticated.
Most agent security advice targets prompt injection at the wrong layer. The real fix is architectural: separate untrusted tool output from privileged context, scope tool capabilities narrowly, and gate side-effecting actions behind confirmation.