From the team
Blog
July 7, 2026 by Jason Lin
Accelerating UAT with Agent Swarms
Agent swarms compress AI user acceptance testing by running thousands of synthetic users across real product flows, scoring failures, and producing deployment evidence.
July 4, 2026 by Toyon
Toyon Finds 3.19x More Bugs Than GPT-5.5
A July 2026 SM-100 run shows Toyon finding 83 of 100 benchmark bugs with GPT-5.5, compared with 26 of 100 for a reference agent baseline using the same model.
June 10, 2026 by Jason Lin
Test Your AI Before Your Customers Do
Toyon uses thousands of simulated users to find failures that scripted evals and manual testing miss.