Topic
14 articles on Agents, written from production systems rather than documentation.
Normal testing asks whether the system works for people trying to use it. Adversarial testing asks what happens when somebody is trying to make it fail.
Long sessions fill the window and something has to go. What you drop, and what you replace it with, decides whether the system degrades or forgets.
Agents rarely crash. They loop, they stop early, and they confidently do the wrong thing, which is why ordinary error handling never catches any of it.
Conversation history, retrieved knowledge and learned state all get called memory. They have different lifetimes, and conflating them is why agents drift.
A second agent multiplies the coordination problem, not the capability. What decides whether it holds together is who owns the shared plan.
Instructions and data arrive in the same channel, so the model cannot tell them apart. No wording fixes that, because it is a property of the design.
Reason, act, observe, repeat is the shape almost every agent uses. Its weaknesses are structural, and they show up in the same three places every time.
When an agent misuses a tool, the instinct is to rewrite the prompt. Usually it's the tool's own signature that made the mistake available in the first place.
Most things called agents are workflows with a model bolted on. The line is whether the system picks its own next step, and everything difficult follows.
MCP gets described as USB-C for AI tools. The useful question is narrower: which parts of tool integration stop being your problem, and which never were.
Most problems described as agent problems are retrieval, a workflow, or a form. Agents earn their cost in a narrow band, and it pays to know where it starts.
Most teams only ever write servers. Building the client side is what shows you where the protocol stops and your own orchestration has to take over.
Whether it needs designing from scratch or rescuing from its own success, tell me what you’re building and I’ll tell you how I’d architect it.
Open to remote and hybrid work worldwide