General Info

An agent makes six model calls to answer one question. Asking what temperature the agent runs at assumes there is a single answer. There are six, and a well-built agent may deliberately use different values for different calls. The Short Answer Temperature is a parameter of a model call, not a property of an agent….

A prompt change has no compiler, no type error and no failing test by default. The application keeps returning successful responses while task quality quietly declines. That silent failure mode is the whole reason the templating layer deserves to be real infrastructure rather than string concatenation scattered through your codebase. Platform details reflect the landscape…

Two different questions get asked together here, and they deserve separating. The first is which prompting patterns agents actually use. The second is which libraries implement them. The patterns have been stable for a while. The tooling has not. Framework details reflect the landscape as of mid-2026. This space moves quickly — verify current capabilities…

A tool definition is an unusual artifact. It is read by two completely different consumers — a runtime that validates it as a schema, and a language model that reads it as prose and decides whether to use it. Most tool design problems come from writing for only one of those readers. First, a Clarification…

You correct an agent. It acknowledges the mistake, adjusts, and gets the next answer right. It feels like teaching. Tomorrow the same agent makes the identical mistake, because nothing was taught. The model that answered you is byte-for-byte the model that will answer tomorrow. The Short Answer No. An agent does not train the model….

You type eleven words and press send. What arrives at the model might be eight thousand tokens, of which your eleven words are the last few. Everything else was assembled by the agent in the milliseconds between your keystroke and the request leaving. The Short Answer No. Your raw prompt is almost never what the…

An agent checks the weather, queries a database, and writes a file. It looks like the model is doing things. It is not — the model cannot do anything. It produced some structured text saying what it would like done, and an entirely separate piece of software decided whether to comply. The Short Answer The…

You tell an assistant your name, and twenty messages later it still uses it. That looks like memory. It is not. The model forgot your name the instant it finished replying, and remembers it now only because your entire conversation was sent to it again, from the beginning, along with your latest message. The Short…