Hello! I recently set it up and configured Agentforce Coworker to work with our Salesforce data, Slack, and our website (via Data 360). After setup and a single day of testing, I found that I used nearly 12,000 Einstein Requests (no other consumption of other credits). My concern is that we'll run out of our 200K allocated Einstein Requests in no time.
Does anyone have advice for keeping credit consumption numbers low? If it makes a difference, we use NPSP and do not have plans to migrate to Agentforce Nonprofit at this time. As a nonprofit organization, I'd love to use this feature, but I'm not sure if I can justify the potential cost. I have a staff of 20 and am trying to determine what a budget might look like. Maybe I need to go a different path with the AI capability available in Salesforce?
I appreciate any and all advice in advance! Thanks!
Hi @Matt Devine
12,000 Einstein Requests in one day is definitely worth investigating before expanding the rollout. I’d first check Digital Wallet to identify exactly what is consuming the requests and verify your Agentforce Coworker licensing and user AI permissions.
Since this was only one day of testing, I’d also run a small pilot with a few users and track consumption per user/use case before estimating production usage. Since you’re using Data 360, check that usage separately as well.
For a nonprofit, I’d recommend measuring and optimizing usage first, then comparing the available licensing options to find the most cost-effective approach.
Hope this helps!