Pacific Design/ artificial intelligence

section 04 · status: live · 5 entries · updated 2026-08-27

AI Agents

The current frontier of applied AI: models given tools, memory and a goal, running in a loop. What an agent really is, how tool calling works, the protocol that standardized it, when many agents beat one, and how to evaluate systems that act.

live · the agent loop — reason, act, observe, repeat

  1. What makes an agenta model in a loop with consequences
  2. Tool use & function callingthe model asks, your code acts
  3. MCP: a standard for toolsone protocol between models and everything
  4. Multi-agent systemsa team of models, at a price
  5. Evaluating & containing agentstrust the state, not the summary