The AI engineering stack we built internally - on the platform we ship

Cloudflare wired AI into the engineering stack. LLM traffic funnels through a proxy Worker and AI Gateway. It shipped Workers AI and the Agents SDK. Daily users hit 3,683 (93% R&D). MR throughput climbed to ~10,952/week. Workers AI handled 51B input tokens and cut a security agent's inference spend by 77%.