Route each AI request by cost, speed and model health
Also listed as: Dynamic best-fit LLM provider orchestration
What is it?
Xelence plans to pick the AI model for each request automatically from the models approved for that environment, weighing cost, speed and each model's current health. This builds on the backup-model fallback in Xelence 10.0. Each choice will be recorded with the reason it was made.
Why does it matter?
No single AI model is best for every task, and sending every request to the same model can mean paying too much or waiting too long.
A better balance of AI quality, speed and cost, and less dependence on any one AI provider.
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
Administrators decide which providers and models are approved for each environment, and automatic selection stays within that list. The model used for every answer is recorded so it can be reviewed.
Start thinking about
- Which AI providers or models has your organization approved?
- For your AI uses, which matters most: quality, speed or cost?
- How should your team review and re-approve AI features when a provider retires a model?
Terms used on this card
- 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.
Items shown as planned are subject to change based on customer priorities for specific features and enhancements.