Category

Agent Runtime Ops

These terms cover the runtime building blocks used to ground model outputs, choose tools, and measure agent quality.

How to recognize this theme

Vocabulary for how AI agents access tools, knowledge, and routing logic.

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 Calling

Tool calling is the pattern where a model selects and structures a call to an external function, API, or workflow instead of answering from text alone.

Retrieval-Augmented Generation

Retrieval-augmented generation, or RAG, combines search over relevant documents with model generation so responses can use fresher or domain-specific context.

Inference Router

An inference router is a system that directs a request to different models, hardware pools, or decoding settings based on cost, latency, or capability requirements.

Eval Suite

An eval suite is a structured set of tasks, datasets, and scoring rules used to measure whether a model or agent meets quality targets after prompts, tools, or models change.