See how much your AI features are used and what they cost
Also listed as: Cost & token monitoring
What is it?
Xelence 10.0 will record the tokens used by each AI call. Tokens are the units of text that AI services count and usually charge by. AI usage and cost will show on operations dashboards alongside quality, speed and reliability. Figures can be viewed by AI use case and by environment, and Xelence is designed to support token or cost limits on AI calls.
Why does it matter?
AI services are usually billed by usage. Without clear tracking, costs can grow unnoticed and are hard to tie back to a feature, a program or a test environment.
Clearer visibility of AI use and spending, earlier warning of unexpected growth, and better information for planning AI budgets.
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
Start thinking about
- Who in your organization should review AI usage and cost, and how often?
- Would you want AI usage broken down by program, use case or environment?
- What limits or alert levels would you want for AI spending?
Terms used on this card
- Token (AI)
- The unit of text that AI services count, and usually charge by, when they read a question and write an answer.
- AI use case
- A specific business task where AI helps, built so it works alongside your forms, rules and workflows.
- 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.
- Tracing
- Recording each step a request takes through the system, so support teams can see exactly where something slowed down or failed.