Agent Harness Engineering Concepts › What an agent harness is 12 of 12 steps written
01 — part 1, conceptsconcept

What an agent harness is

An agent harness is everything around the model call: the tools it may use, the text it gets back, the checks on what it claims, the window it works in, and the record of what it did.

The model is the part you did not write

A working agent is a model inside a program. Almost none of that program is the model, and almost all of it is yours.

The model is the part you did not write tools error text verifier context recovery trace model A model B a vendor wrote this swap the model… …and every ring stays That is why the harness is the thing you can measure: hold the model fixed, change one ring, and the difference can only have come from the ring. Six rings. Every one of them is code you own.
The model at the center, the harness around it. Swap the model and every ring stays exactly where it was.
That is not a metaphor about ownership. It is the reason this volume can measure anything at all.

Why this is the useful place to work

Prompt changes are the obvious lever and they run out. A better prompt cannot invent a tool that does not exist, cannot tell the model about a failing case the error message did not name, and cannot stop a model that has announced success while wrong.

The harness can do all three.

The experiment this makes possible

Because the harness is code, you can hold the model fixed and vary the harness. That is the only comparison in this subject that is actually clean: change the prompt and the model together and you cannot attribute the difference to either.

Every figure in this volume comes from that experiment. One scripted, deterministic model; six switchable layers; the same task run again with one layer removed.

A scripted model is what makes the comparison clean and it is also what makes it narrow. Nothing here predicts how a real model behaves under any of these layers, and step 12 says so first among the limits.

The six layers, named once

layerwhat it decidesstep
tool surfacewhat actions exist, and how easy they are to name correctly3
error textwhat the model learns from a failure4
verifierwhether a claim of success is believed5
context budgetwhat survives when the window fills6
recoverywhat happens when the same thing keeps happening7
observabilitywhether you can reconstruct any of it afterward7

Part 2 takes one at a time. What each one buys is a measurement, not an argument, and it is deferred to Part 3 where the three tasks can be compared.

What to take from this step

  • The harness is the part of an agent you wrote, and it is where the remaining leverage is once prompting runs out.
  • Hold the model fixed and vary the harness. It is the only clean comparison available.
  • Six layers, and none of them is about wording.