Skip to main content

Action space

The set of distinct actions an agent can take by itself, one per tool it can call (send email, run code, make a purchase, modify a database, post publicly, spend from a budget). The most important thing to enumerate about an agent; you cannot bound what you have not listed.

Defined in 2 GAGE programs, which carry 4 distinct definitions of it. The wording above is taught in AI Governance: Applied Mastery.

How each discipline defines it

The same term does different work depending on who is using it. These are the definitions as each program teaches them, unedited.

AI Governance: Applied Mastery

The set of distinct actions an agent can take by itself, one per tool it can call (send email, run code, make a purchase, modify a database, post publicly, spend from a budget). The most important thing to enumerate about an agent; you cannot bound what you have not listed.

Agentic AI Governance: Applied Mastery

The full set of actions an agent is capable of attempting, whether or not each one is currently permitted. Bounding measures shrink the action space; checkpoints govern specific instances of actions that remain inside it.

Agentic AI Governance: Applied Mastery

What an agent can actually do in the world (send, book, cancel, write, transact, escalate) as distinct from text it merely produces for a human to act on; formally defined in (see Topic 2.1).

Agentic AI Governance: Applied Mastery

The full set of tools, permissions, and transactions an agent can execute, first enumerated in (see Topic 2.1) and rated for reversibility in this topic.

Where it is taught

The exact lessons this term appears in. The first 7 topics of every program are free with a free account.

Terms it appears with

Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.