GenAI Field Guide

Under the hood (just enough)

The harness is the product

Every chat assistant is a language model wrapped in a harness: a product layer that adds the system prompt, tools (search, code, files, connectors), memory and projects, safety filters, and compaction. The harness is at least as important as the model for what you experience.

≈2 min
You Harness · the product System prompt + tools Model Predicts the next token Memory + safety Projects · filters ·compaction
You talk to the harness. The harness talks to the model. Two products on the same model can behave very differently.

Where to look when something surprises you

Symptom Usually the…
It refuses a phrasing or insists on a format Preamble (vendor or organization instructions)
It "can't see" a file or a calendar Tools and connectors the harness exposes
It forgot something from early in a long chat Compaction rule of the harness
It "remembers" something you never told it in this chat Memory or project feature re-sending saved text
It reasons worse on a hard problem than another product The model itself, finally