01
Where this one gets misread
The word covers everything from a fixed two-step script to a system choosing its own tools and its next move. Both get sold as agentic, and the difference decides how much can go wrong while nobody is watching.
Glossary
What is agentic AI?
Agentic AI is AI set up to pursue a goal over several steps, choosing its own tools and deciding its next move inside permissions a person has set.
Updated 21 Aug 2026
02
Questions to ask
Ask for a worked example on your own material, and the evidence needed to reproduce it.
- Which decisions does it make without a person?
- How far does a wrong step reach before something stops it?
- Where does a human confirm before a write action?
- What is recorded about the path it took?
03
How Marella uses the term
We use “Agentic AI” only where a product mechanism or an evaluation method backs it up, and we say when the behaviour depends on how a deployment is configured.
- Backed by a product mechanism or an evaluation method
- Deployment differences flagged
What this page does not prove
- B1A definition is not a claim about how the product performs.
- B2Vendor implementations vary.
- B3Test the term against a representative workflow.
Related pages
Test the claim on your documents
Pick a real piece of work, agree what a good answer looks like, then go through the results together.