Training
Whether supplying company-specific information measurably improves future behaviour and generalises beyond the example given.
What this capability means
Training is the capability for learning from company-specific information so later answers improve in the right way and still hold up when the same question is asked again in different words. A product with this capability can take supplied definitions, examples, or rules and use them on future questions, not just on the exact example it was shown.
Boundary: It does not judge a tool’s one-off answer quality before any supplied information, or general model knowledge unrelated to the company’s own information.
Scenarios that test this capability
A scenario is a real-world situation used to test a capability.
Benchmarks that include this capability
A capability has global identity and may be used by more than one benchmark.
AI Database Agents
Which AI database agent answers business questions about a live relational database correctly — in the company's own terms, and honestly when the data cannot answer?