AI Agents
Concept
Training & Inference
Models that act: plan, call tools, iterate — the 2025 product wave.
You're looking at a concept explainer: what this term means in plain English, and the records it ties together.
An agent loops a model through plan → act → observe: calling tools, browsing, writing files, correcting itself until the goal is met. Coding agents (Claude Code, Codex, Devin) proved it commercially; standards like MCP wire agents to the world. Agents multiply token consumption per task by orders of magnitude — the demand driver behind the inference buildout — and concentrate the safety questions, since acting models can do more than talking ones.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Related
Sources
Record reviewed as of 2026-01-15 — see Methodology.