Category

Agent Building Blocks

These are common building blocks for making agents more useful and more testable in real workflows.

How to recognize this theme

Concepts used when an AI system plans steps and calls tools.

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 Use

Tool use is when an AI agent invokes external functions or services (like search, code execution, or databases) to complete tasks beyond pure text generation.

Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) combines search over a document store with generation so outputs can be grounded in retrieved context.

Planning

Planning is the process of decomposing a goal into ordered steps and selecting actions, which can improve reliability for multi-step agent tasks.

Eval Harness

An eval harness is a repeatable test setup that measures an AI system's behavior on representative tasks, helping detect regressions and failures.