AI feature workbench
Prompt lab
Tune a prompt, run realistic product cases, and check quality before publishing a new model-backed workflow.
Suite score
90%
Avg latency
817ms
Estimated cost
$0.054
Prompt draft
Version 7, edited for support escalation.
Available variables
Use these tokens in the prompt body.
{customer.name}
{account.plan}
{policy.refund_window}
{recent_events}
Refund edge case
Customer bought a seat add-on 33 days ago and asks for a refund after downgrading.
Generated answer
Thanks for sharing the order details. The add-on is outside the 30-day refund window, so I cannot promise a cash refund. I can help apply account credit for the unused time or route this to billing review if there was a billing error. Tone: supportive. Model: GPT-4.1 mini. Run #14.
Quality
91%
Latency
820ms
Cost
$0.018