Tool Call
A tool call is a request from a model or agent to use an external function or service.
Category
AI Agent Runtime
These terms describe the request, the token budget, short-term state, and cached memory a system may use.
How to recognize this theme
Words used when a model is being called inside an app.
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.
Prompt Ceiling
A prompt ceiling is the practical limit on how much instruction text can be sent at once.
Working Memory
Working memory is the short-lived state an agent keeps while it is handling a task.
Memory Cache
A memory cache stores reusable state so an app can reuse recent context or embeddings.