The largest single lever over the quality of a model’s output is not the model, the sampling settings, or the length of the prompt. It is how completely the instruction defines what a good answer would be. An instruction that leaves a decision open does not leave it unmade. The model makes it, silently, on your behalf, and you find out which way…
A language model has no memory of you. It has no memory of the last thing it told you, no running notion of the task, no internal notebook that persists from one call to the next. What looks like memory is an illusion reconstructed on every request. The single place that illusion is assembled is the context window, and that window…
The defining mistake in multi-agent design is building an orchestrator that does work. It feels natural: the orchestrator is the smartest, most context-rich component in the system, so why not let it handle the hard parts itself and delegate only the scraps? Because the moment the coordinating agent starts executing, it stops being able to coordinate well. Its context fills with the…
The reliability of an agentic system is mostly settled before the model runs a single step. It is settled in how the work was cut. Hand an agent a large, monolithic goal and it has to invent the structure the goal lacks: it has to decide on its own where one piece of the job ends and the next…
When an agent reaches for the wrong tool, the instinct is to inspect the code: a broken function, a malformed schema, a name that should have been clearer. Almost none of that touched the decision. By the time any tool executes, the model has already settled on it, and it settled by reading natural language. The thing that actually drove the choice is the…
A language model, on its own, cannot do anything. It can produce text, and that is the entire extent of its reach. It cannot read a file, query a database, send a message, or check whether the claim it just made is true. The most capable model ever built, handed a goal it understands perfectly, can still only respond by writing words about it. The leap from…
An agent is not a clever prompt or a powerful model. It is a loop. Strip away the framework, the tool catalog, and the system prompt, and what remains is a cycle that repeats: the model reads its situation, decides on one action, that action runs, and the result is folded back into what the model reads next time. Perceive, reason, act, observe, and then perceive again. This loop is…
Three words get used as if they were a single rising scale of sophistication: chatbot, workflow, agent. The implication is that a chatbot is a simple thing, a workflow is a more capable thing, and an agent is the advanced version of both. That framing is wrong, and the wrongness is expensive, because it leads teams to reach for the label that sounds most…
The word agent has become the default aspiration. New systems are framed as agentic before anyone has asked whether they need to be, and “we built an agent” now carries a prestige that “we built a pipeline” does not. This is an expensive habit. For the large majority of production work, the correct architecture is the deterministic workflow, and the decision rests on a single question. Does the…