Skills

The same task, two radically different approaches. One says “write code to orchestrate the LLM.” The other says “write markdown to teach it.” Both produce agents that reason, use tools, and complete complex work. Knowing when to reach for which is the skill that matters in 2026. The SDK Way: Agents as Code Agent SDKs — OpenAI Agents SDK, Claude Agent SDK, LangGraph, CrewAI — let you build agents programmatically. You register tools as functions, write instructions, and the SDK runs the loop: prompt the LLM, execute tool calls, feed results back, repeat. ...

Part 2 of Two Roads to AI Agents. This time we build something real. In Part 1, we drew the line between Agent SDKs (code orchestration) and Agent Skills (markdown knowledge). Now let’s blur it. We’ll build a pipeline that turns any article into a narrated MP4 — and at each step, I’ll label whether we’re writing SDK code or Skill knowledge. The finished product: say “make me a video about TCP/IP” to Claude Code, get a 1080p narrated video back. ...