2 posts tagged with "Best Practices"

Most agent skills fail for a boring reason: we edit prompts, rerun once, and call it “better.”

Anthropic’s latest Skill Creator update pushes a more engineering-style loop: test first, measure behavior, then refine. If you build internal agent workflows, this is the shift that actually matters.

This post rewrites the official announcement into a developer workflow you can run every week.

Most teams do not fail with agents because of model quality.

They fail because they pick the wrong workflow pattern too early: too much orchestration, too many moving parts, and no clear reason for the complexity.

Anthropic’s recent guide on common agent workflow patterns is useful, but this post rewrites it for developers building production systems.