How do you measure whether an agent is actually saving time instead of moving work around?

Source quality beat model size for us. Clean knowledge + tool scopes fixed more hallucinations than switching models.

We ran a 3-week pilot with a similar brief. The biggest gap was ownership after launch — if ops cannot edit prompts and tools without engineering, it dies. Pick the platform your weekly owner can actually maintain.

Agree on rollback and permissions before demos. We lost a week because the agent could write CRM fields with no audit trail. Make “field-level history” a go/no-go in the RFP.

Budget-wise, usage pricing looked cheaper until support volume spiked. Model a bad week, not an average day. That alone flipped our shortlist.

We compared two vendors on the same 20 tickets. Accuracy was fine; escalation quality was not. Score human handoff and confidence thresholds harder than model branding.

Document what “done” means for the workflow. We shipped an agent that “worked” but still required a human to close the loop every time — zero net time saved.