Ask questions of your program records in plain language
Also listed as: Hybrid reasoning over enterprise data
What is it?
Xelence plans to let staff ask questions of structured program records in plain language. It also plans to let AI combine those records with your documents in one answer, showing where each fact came from. This builds on the document search with sources in Xelence 10.0.
Why does it matter?
Much of what staff need is held in structured records, and answering a question across records and documents today means running reports or opening several screens.
Faster answers to everyday questions about your programs, drawing on both records and documents, with sources staff can check.
Generative AI Services and Xelence AI Engine work together. Building AI and running it explains which does what.
Getting it into your solution
- Needs an upgrade to the Xelence release
- Needs configuration
- Needs implementation work
Where people stay in control
Access rules decide which records the AI may read for each request. Answers show their sources so staff can verify them, and a trained person should review answers before anyone acts on them.
Start thinking about
- Which questions about your program records do staff ask most often today?
- Which records should AI never be allowed to read?
- Who would review AI answers, and what would a wrong figure cost in your programs?
Terms used on this card
- Large language model (LLM)
- The kind of AI model that understands and writes text, used behind AI assistants and agents.
Items shown as planned are subject to change based on customer priorities for specific features and enhancements.