What if AI agents skipped language entirely to communicate?

Instead of passing text between subagents, Ramp's research team found a way to pass KV cache directly — skipping token space entirely. Same accuracy, fewer tokens. Alex Shevchenko, Head of Applied Research at Ramp, breaks down how it works and why it matters for multi-agent systems. This clip is from Max Agency, a #podcast about how the best AI agents are actually being built. Hosted by Harrison Chase, CEO of LangChain, each episode goes deep with the builders designing, deploying, and learning from real agent systems in the wild. From architecture decisions to evals, tooling, and failure modes, Max Agency is for people who want to understand what it really takes to build useful agents.