Try AI models and agents safely before they reach production
Also listed as: Developer sandbox for LLM models
What is it?
Xelence 10.0 will give developers a playground, a practice space where they can try AI models, agents and workflows in a development environment. AI connections, settings and versions are kept separately for each environment, so a tested version can be promoted step by step through test and acceptance environments to production.
Why does it matter?
Testing AI ideas directly in working environments is risky, and without a clear promotion path it is hard to be sure that what runs in production is what was tested.
Faster, safer experimenting with AI, and more confidence that what goes live matches what your team tested and approved.
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
Where people stay in control
Your team decides when a version is promoted to the next environment. Each environment keeps its own published version, so nothing reaches production until someone publishes it there.
Start thinking about
- Which AI ideas would your team most like to try first?
- What test data could be used in a development environment without exposing personal information?
- Who should approve moving an AI feature from testing into production?
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.
- Environment
- A separate copy of your solution used for one stage of work, such as development, testing or production. Production is the live system that staff and constituents use.
- Large language model (LLM)
- The kind of AI model that understands and writes text, used behind AI assistants and agents.