Category

Agent Inference Stack

These ideas describe how agent systems control model calls, memory limits, and permitted actions.

How to recognize this theme

AI agent terms about routing, context, caching, and safety rules.

In a daily board, this category groups terms by their shared role. Look for four cards that describe the same mechanism, risk area, or workflow rather than four words that merely sound similar.

Educational context

These entries are vocabulary notes for learning. They are not project endorsements, token recommendations, exchange rankings, or trading signals.

Tool Router

A tool router is logic that chooses which external tool or function an AI agent should call for a task.

Context Budget

A context budget is the amount of text, instructions, data, or history that can fit into a model request.

Inference Cache

An inference cache stores reusable model outputs or intermediate results to reduce repeated computation.

Guardrail Policy

A guardrail policy defines constraints that help an AI system avoid unsafe, disallowed, or out-of-scope actions.