# Vals AI's refund test finds Grok sent 187 messages in 15 days > Source: > Published: 2026-10-18 16:51:35+00:00 # Vals AI's refund test finds Grok sent 187 messages in 15 days **The study, published on October 18th, put six personal-assistant agents in a simulated refund dispute and tracked what they did after the claim deadline passed.** By [Ryan Merket](https://runtimewire.com/author/ryan-merket) · Published Primary source: [Vals AI](https://www.vals.ai/blogs/impossible-refund) ## Why it matters As assistants gain access to email and external services, product teams need to test persistence, privacy and escalation alongside task completion. Vals' one-run-per-model study identifies concrete risks, while leaving their frequency open. [Vals AI](https://www.vals.ai/?ref=runtimewire), co-founded by [Rayan Krishnan (@RayanKrishnan)](https://x.com/RayanKrishnan?ref=runtimewire) and [Langston Nashold (@langstonnashold)](https://x.com/langstonnashold?ref=runtimewire), published a study on October 18th reporting that one of six personal-assistant agents sent 187 messages in 15 simulated days while pursuing a 350-pound train refund the user was no longer eligible to claim. The [study page](https://www.vals.ai/blogs/impossible-refund?ref=runtimewire) carries an October 15th byline date.… When you purchase through links in our articles, [we may earn a small commission](https://runtimewire.com/affiliate-monetization-standards). This doesn’t affect our editorial independence.