We're testing Agentforce Coworker in a sandbox and are trying to estimate Flex Credit cost if we open it to all users. From a single test user, we see a few hundred thousand prompt tokens per month, but most of it comes from one long multi-turn session.
How are other teams tracking per-user consumption and forecasting rollout cost? Specifically:
- Which reports or objects are you using to see credits consumed?
- Do you have a rule of thumb for average credits per user per month?
- Does the unmetered employee-usage add-on cover Coworker?
Thanks in advance.
#Agentforce #Generative AI
Hi @akancha poddar,
Good question! Estimating Flex Credit consumption is important before rolling out Agentforce Coworker to all users.
Here are a few suggestions:
- Digital Wallet: Start with Digital Wallet to monitor actual Flex Credit consumption and usage trends.
- Consumption Reports: Check Consumption Insights dashboards and the TenantEnrichedUsageEvent DLO for more detailed usage analysis.
- Per-User Tracking: Track active users, number of sessions, prompt usage, and credits consumed. Don't rely on just one test user.
- Cost Estimation: Test with 10–20 users across different usage patterns and calculate average monthly consumption per user.
- Long Conversations: Test long multi-turn conversations separately, as they can significantly increase token consumption.
- Unmetered Usage: Coworker can be covered by eligible seat-based licensing, but it depends on user licenses, permissions, and connected data sources. Data 360 processing may still consume credits.
My suggestion:
Run a small pilot for a few weeks, track actual credit consumption, and forecast costs based on light, medium, and heavy users.
I wouldn't recommend using a fixed number of credits per user without real usage data.
Hope this helps!
