Monitoring/Limit of AI Token Usage for ARCS AI Agents
Hello Experts
We are currently performing prompt testing of Oracle ARCS AI Agents in our non-production environment and are looking for guidance on monitoring AI token consumption before moving to Production. Specifically, we would like to understand :
- Is there a defined token usage limit for ARCS AI Agents/Assistants?
- If so, what are the applicable limits?
- Are there any alerts or notifications available when token usage approaches established limits?
Before deploying these agents to Production, we would like to establish an appropriate monitoring approach to ensure visibility into token usage and avoid unexpectedly exhausting available token allocations.
The ARCS AI agent in currently using model GPT OSS 120(Basic)
Tagged:
0