Kozlov: AI agents require tightly coupling compute and state
Rita Kozlov · npm install Agents — with Sunil Pai and Rita Kozlov (VP AI) of Cloudflare · Mar 19, 2025 · at 3:06
Rita Kozlov, VP of AI at Cloudflare, explains the architectural components required to build resilient autonomous AI agents.
0:00 / 0:34exact quote · 34.5s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“An agent is really like LLMs and a bunch of workflows and coordination and orchestration and then extra, like some sort of services, right? Like you have kind of the brain of the operation, which is the LLM and it can come up with a plan. And then, but then it needs its executive arm kind of right to like go and make sure that things happen and that even if Failures occur that, like, something is communicating back to it, and this requires these, like, two bits of compute and state to be really, really closely tied together.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Rita Kozlov
Kozlov: Wave of 'agent-first' businesses will emerge without traditional UIs
“I think that we're going to see a wave of, you know, going back to, again, Sunil, your point about mom and pop shops, these businesses turn up that are agent first, and that's kind of the only interface to using them as opposed to, you know, UIs and APIs and o…”
Kozlov: Non-Kubernetes architectures are critical for cost-effective AI agent scaling
“It's easy to conflate long running with CPU intensive, and these are kind of not the same thing, and actually a lot of Specifically agentic workflows. A lot of what you're doing is you're waiting. You're waiting on human in the loop. You're waiting on LLM. You…”
Kozlov: Protocols like MCP will eventually replace browser-based AI agents
“Especially with people building agents, I think it's kind of funny because it's a bit, to me, the anthropomorphification of agents, where it's like, we humans use browsers, so my agent is going to use a browser, but eventually I think that will get replaced wi…”
Kozlov: Agent identity verification must be solved for agents to take off
“I think this problem is gonna have to be solved for agents to take off, quite honestly. I mean, I see what you're saying, but we do have to at some point then pass identity onto, like, if we go back to what we were talking about of, you know, I would love an a…”
Kozlov: Cloudflare Durable Objects remain widely misunderstood by developers
“There, there's still at least one thread a week that goes something like this. Hey, can someone describe durable objects? And then there are a hundred comments and no two of them are the same. And people walk away equally confused.”
Kozlov: Bullish on Model Context Protocol (MCP) as key to useful agents
“I'm very bullish on MCP. I'm really, really excited about it, but I think funnily enough, the term MCP is the thing that scares the normies away because it sounds so deeply technical, even though really it's the part that I think is going to Make agents intere…”