Sandbox
A sandbox limits what an agent or program can access or modify.
Category
Agent Controls
These terms describe isolation, access, observability, and evaluation.
How to recognize this theme
Terms you see when tool-using systems need guardrails.
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.
Permissions
Permissions define which tools, files, or actions an agent may use.
Tracing
Tracing records steps or tool calls so runs can be inspected later.
Evals
Evals are test runs used to measure model or agent behavior on defined tasks.
Tool Calling
Tool calling is the act of invoking a function, API, or service from an AI workflow.
Sandbox
A sandbox is a controlled environment that limits what code or an agent can affect.
Memory
Memory is stored context that can help an agent reuse facts or preferences later.
Evals
Evals are repeatable tests used to measure whether a model or agent behaves as expected.