"Pets vs. Cattle" in the Agent Age

Sign in<br>Subscribe

Agents are the new SaaS. I’ve been deploying more and more agents across enterprises, individual family offices, and in my own personal life.<br>All That Is Old Is New Again<br>It feels like mobile in 2010. The future is here, it’s just not distributed yet. Just as I was puzzled when companies call themselves a “mobile” or “cloud” startup then, I pause when someone tells me they are creating an “agentic” startup today. “Aren’t almost all new software companies today agentic in some way?” I have to remind myself that not all everyone today talks to AI more than they talk to humans. Those of us on the edge already are living in the future.<br>All that is old is new again - both opportunities and challenges. Wrangling these new, strange, and amazing pieces of technology that we agents feels like wrestling with Philip Pullman’s living daemons at times. However, eventually these too will become boring technology:1<br>I’m starting to see an old trope reemerge again in the AI Agent Era: the devops adage of “pets vs. cattle.”<br>Pets vs. Cattle<br>“Pets vs. Cattle” is a famous analogy used in cloud computing coined by Randy Bias2 and devOps to explain two different types of server management:<br>Pets<br>Pets as a concept treats servers like beloved household companions. They are given individual names like “morton-mail-server” and are carefully nurtured.3 If a pet server gets sick or crashes, it’s all hands on deck. DevOps manually steps in to immediately nurse it back to health, patch it, or troubleshoot the specific issue.<br>The advantage is a tailored, fine tuned service matured with intimate knowledge of the owner. The disadvantage is a single point of catastrophic failure that is unique and has no immediate, identical replacement.<br>Cattle<br>Cattle as a concept treats servers like a herd of livestock in a pasture. They are identified by generic tags or IDs. They are replicable, anonymous, and disposable. If one server fails or has a hardware issue, you don’t spend time trying to mend it. You “take it out back” to terminate it and automatically provision a replacement.4<br>The advantage is resiliency through redundancy. Your herd can survive with any one or several servers going down. The disadvantages complexity. Raising a single pet is an act of understanding and love. Managing 10,000 head herd is a business operation. It’s simultaneously one for which you need specialized expertise, and which no one person may fully understand when a systemic infection devastate the herd.<br>Anthropomorphized Agents<br>This same analogy can be repurposed for emerging agentic systems:<br>Pets vs. Cattle for the Agent AgePet Companions<br>On one end, my personal chief of staff agent is a pampered pet. Hundreds of hours spent setting up, tweaking, tailoring, maintaining, and evolving hundreds of skills, crons and customizations. I know it like an intimate companion from its pragmatic, but slightly humorous personality mark down Soul.md to the SSH drop quirk when I over run git update timeouts. It’s become such an intimate part of my daily workflow that when it goes down (or anthropic changes its subscription policy), I have AI withdrawal and scramble to bring my other half back to life.<br>Semi-Fungible Staff<br>In the middle, I’ve deployed similar chiefs of staff and function specific agents running internal operations for a number of family offices and mid-market enterprises. It’s a small herd numbering in dozens instead of thousands. I still know the name of every single one of them. Each has its own memory, context, tools, and environment, carefully crafted to its master and corralled by its wrangler (me) down to its own unique icon and personalized name. Each has its own unique personality, and failures still trigger phone calls, but nobody will try if we have to cull a few misbehaving individuals as long as we have timely, suitable replacements.<br>Herded Workflows<br>On the other end of the spectrum, I’ve been working with a few enterprises to deploy cattle agents for their customers at scale. With thousands to tens of thousands of agents running externally, you cannot afford to babysit individual pets in the business operation. Any bug, misuse, or flaw is an EBITDA destroying matter liable to become systemic. In their simplest form, these are really stateless or ephemeral state scheduled workflows with calls to LLMs. These workflows are built to very similar to traditional software of the past. Reputable, reliable, deterministic(ish).<br>Tradeoffs Deploying Agents in Production<br>Engineering how to get the best of both worlds is an increasingly interesting challenge unique to the Agent Age:<br>Agent Uniqueness = Value<br>There is no functional value to a pet server’s uniqueness. Today “pets vs. cattle,” is an overhead trade-off decision: we know most of the best practices to build redundant fleets of cloud server containers and software and organizational systems overhead to fit services to that model. For the most part, we want...