Build AI agents that draw on your own documents and show their sources
Also listed as: Agent development
What is it?
Xelence 10.0 will include an agent designer. There, your team builds an AI agent, AI that carries out a sequence of steps toward a goal, by choosing its AI model, instructions, skills and the knowledge it may draw on. Knowledge can come from your own documents, and the agent's answers point back to the passages they came from.
Why does it matter?
Building AI agents outside the platform means extra integration work, and answers from a general AI model can be too generic to use or hard to check.
Agents that fit into your solution, give answers grounded in your own documents, and are easier to secure, check and change.
Xelence AI Engine and Generative AI Services 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
Your team decides which documents each agent may draw on, and answers show their sources so staff can verify them. Early uses should be staff-facing, so a trained person reviews each answer before anyone relies on it.
Start thinking about
- Which tasks would you want an AI agent to handle first?
- Which documents would agents need, and are they digital and searchable today?
- Who on your team would build agents and review their answers?
Terms used on this card
- Agentic AI
- AI that can carry out a sequence of steps toward a goal, such as checking, deciding and acting, within limits people set, rather than only answering one question.
- AI skill
- A defined ability, such as looking up a record or summarizing a document, that AI agents can reuse across workflows.
- Large language model (LLM)
- The kind of AI model that understands and writes text, used behind AI assistants and agents.