Understand AI systems visually.
An interactive atlas of agent architectures, safety patterns, evals, context systems, and coding agents — drawn as living diagrams instead of prose.
Five collections
56 PLATESAgent Harnesses
Fourteen recurring architectures, from a single forward pass to agents that run for days.
Safety & Security
Agents possess authority. Ten ways untrusted text borrows it — and the boundaries that stop it.
Agent Evals
Outcome checks, trajectory review, and judges you can actually trust.
Context & Memory
What earns a place in the window, and how memory brings the right things back.
Coding Agents
Test loops, parallel worktrees, and why more agents aren’t automatically better.
How to read the atlas
Every diagram uses the same visual grammar. Color is reserved for meaning: neutral by default, blue when something is executing, red where trust ends, green when it’s verified. Press ⌘K to search any concept.