RAG (retrieval-augmented generation)
RAG (retrieval-augmented generation) grounds a model's answers in retrieved source material — documentation, configuration, examples — instead of relying on what the model memorized in training. Grounded answers can cite their sources, making them verifiable and aligned with the current state of the system they describe.
In NeoXam Agents
RAG is a Beta (V1) capability: retrieval over product documentation, configuration objects and business-rule example corpora, with deep links to the exact product screens. The approach was validated in the DataHub proof of concept that precedes the Beta assistant.
Related terms
See it at work
Data onboarding & configuration Q&A
Beta (V1)'How do I configure a Kafka feed?' — answered from documentation and live configuration objects, with deep links to the exact screens.
See how these concepts come together in a governed agentic platform for investment operations.
Explore the platform