How Clay runs 350 million GTM agents a month | Interrupt 26
Clay runs over 350 million go-to-market AI agents monthly, processing trillions of tokens per week.
“We run this over 350 million times a month. It processes trillions of tokens every week.”
Clay's head of AI detailed how the company scales 350M+ GTM agents monthly across four challenges: infrastructure (moving from Lambda to ECS with durable workflow execution), rate limits (a TCP/IP-like backpressure system yielding 4-10x throughput), cost (caching strategies for up to 70% savings and bounded retries), and quality. It matters as a concrete production blueprint for running AI agents at massive scale, with reusable lessons on inference maximization and cost control.