Give AI agents more routine work to complete, within limits you set
Also listed as: Autonomous agents framework (Microsoft agentic AI)
What is it?
Xelence plans to let AI agents take on more routine, multi-step work with less step-by-step direction: recommending outcomes, updating records, and handing work to other agents. This builds on the agent foundation in Xelence 10.0, which uses Microsoft agentic AI technology. It depends on stronger assurance controls arriving alongside it.
Why does it matter?
Many routine, multi-step tasks still need people to carry out each step, even when the steps are predictable.
Less manual effort on routine work, freeing staff to focus on cases that need judgment.
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
- Changes how your team works
Where people stay in control
Each agent works within limits your team sets, such as which tools it may use and how many steps it may take. Out-of-policy actions are blocked, actions that change records are designed to wait for a person's approval, and everything an agent does is recorded for review.
Start thinking about
- Which routine, multi-step tasks would you consider handing to an AI agent?
- Which decisions and record changes must always stay with a person?
- How would your team monitor and review what agents do?
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.
Items shown as planned are subject to change based on customer priorities for specific features and enhancements.