Hi Team,
We are evaluating AI Skills/Generative AI usage in Appian and would like to monitor token consumption for optimization and cost governance purposes.
I have a few questions:
thanks in advance.
Discussion posts and replies are publicly visible
This documentation solves lots of your questionshttps://docs.appian.com/suite/help/26.6/Appian_Release_Notes.html#monitor-and-track-ai-action-consumption-at-the-execution-level
sureshs276515 said:Is there a way to view the input tokens, output tokens, and total tokens consumed by an AI Skill execution?
In 26.6, you can track AI Actions Consumed at the execution level, not raw token counts.
sureshs276515 said:Does Appian expose token usage metrics at the AI Skill or process level?
Use MyAppian -> Adoption -> AI Usage Metrics usage to see AI Action consumption by feature across environments.
sureshs276515 said:What is the recommended approach to track and analyze token usage for prompt optimization?
Use Estimating AI Action Usage for estimation, and log AI Actions Consumed from the node output/test result for actual tracking.
sureshs276515 said:Has anyone built a custom monitoring/dashboard solution to estimate token consumption for AI Skills and Agents?
For AI Agents, use Monitor because it shows token usage per run; for AI Skills, build your own dashboard from logged AI Actions Consumed.