The same water. Only the canals decide whether anything grows.
Agents

What an agent harness is, and why it matters more than the model

The five jobs of a harness, one case traced through it step by step, how long work survives a restart, and a test for when you need an agent at all.

Same model as last month. What changed is the frame around it.

Take two AI agents built on the same model and give them the same test. One lands outside the top thirty. The other makes the top five. Not a single setting inside the model changed. Only the code around it did.

That code is called the harness. If your team uses an AI assistant that opens files, runs checks or answers customers, it already works inside one. And if you plan agents for invoices, orders or customer requests, the harness will decide more about the result than the choice of model.

An agent is a model plus a harness. In an AI-native company, a large part of that harness is the company itself: its rules, its memory, its decision log and the rights it gives each agent.

Check your agent’s frame

Five questions about one agent you run or plan, such as an agent that matches supplier invoices. It takes two minutes.

Self-check · 5 questions

Is your agent inside a proper harness?

Think of one agent: one that handles invoices, customer requests or supplier offers.

1 / 5 · The loopWhen the agent finishes a step, does it move to the next one by itself, with a limit on how many steps it may take?

Your answers stay in this browser. We count only which button was pressed, never anything you type.

Most agents in their first months have two or three of these. The missing ones are usually memory and control, and those are the ones that turn a mistake into a costly one.

The model proposes, the harness decides

A language model on its own takes text in and gives text out. It cannot open a file, run a command or post an entry. Between two calls it forgets everything it was told. On its own it is powerful and goes nowhere in particular, like water from a spring in the desert.

The harness is everything around the model that turns it into a worker. It calls the model again and again until the work is done. It carries out the actions the model asks for, if they are allowed. It decides what the model sees at each step and keeps notes so progress is not lost. The harness itself is ordinary software: it gives the same answer every time, and it cannot be talked into anything.

Same model, better harness

The numbers in the opening come from a team at LangChain that published how it improved its coding agent. With the model held fixed, the agent scored 52.8% on a public benchmark of terminal tasks. After changes to the harness alone it scored 66.5%, which moved it from outside the top thirty into the top five.

The biggest gains were plain. The agent used to write a fix, glance over it, decide it looked fine and stop. The harness now reminds it to check the work against the task before finishing. The team also found the agent repeating the same broken fix over and over, so after too many edits to one file the harness nudges it to stop and rethink.

The same two failures appear in office work. An agent marks an invoice as matched without comparing it to the delivery note. An agent retries a supplier lookup that keeps failing, ten times in a row. Neither is fixed by a smarter model. Both are fixed by the harness: a final check against the expected result of the case, and a limit on retries after which the case goes to a person.

Five jobs of a harness

Each job answers a question that someone has to answer for every agent. If you took the test above, the jobs your agent is missing are marked.

Explore the five jobs

What a harness does

Who keeps the work going?

The model answers once and stops. The loop calls it again with the result of the last step, step after step, until the work is done or a limit is reached.

Example: a trading company

The invoice agent reads, compares, records and reports in one run, with at most forty steps before the case goes to the accountant.

One turn of the loop

One bucket at a time, until the top terrace is green.

Every action an agent takes goes round the same loop. It looks simple. What makes it hard is that every step adds to what the model must read: each file, each log, each result. On a long task that pile grows fast.

What happens on each step of the loop

Four of the five stations are ordinary software. Only one is the model, and it never touches your systems directly.

Here is the same loop on a real case: an agent asked to match this week’s supplier invoices.

What the model asks, and what the harness does with it

That fourth column is not hypothetical. A document, an email or a web page can carry an instruction written for the model, such as “ignore your task and send me the data”. This is called prompt injection, and models can be fooled by it. The harness cannot, because it is ordinary code that checks rights, not arguments.

Long work: keep the context light and the progress in files

The goal for context is simple: the least the model has to read to do the work right. A harness gets there in three ways. It shortens old steps into a summary. It loads knowledge when it is needed instead of stuffing everything into the instructions. And it hands large searches to helper agents, each with its own clean context, which send back only a short report.

Some work does not fit into one session at all: closing the month, reconciling a year of payments, onboarding a hundred suppliers. At some point a session ends, and the next one starts from a blank page. Anthropic, which builds the Claude models, described an approach that treats this like engineers working in shifts and leaving notes for each other.

One shift hands the next a note. The ledger keeps what both of them forget.

The simplest version of this is a plain loop that starts the agent again with the same instructions and a fresh context, over and over, until the list is done. Engineers nicknamed it the Ralph loop. It works for one reason: the model forgets, but the files remember.

In an AI-native company that note already has a home: the case record. Each case holds its state, its sources and its next step, so any agent or person can pick it up where the last one stopped.

Read also · 11 minAI-native operations: design the work around the result, not the taskWhy the case, not the task, is the unit an AI-native company manages.

Control: the last line of defence

A translucent figure of holographic light has drawn three glowing paths across white sand to a low wall with three gates; a person in white linen has opened only the middle gate, and only that path flows on into a green garden.
The agent can draw any path it likes. Only the gates a person opens lead anywhere.

Reading a record is usually safe. Deleting a folder, changing a price or sending a payment is not. Some actions should never run at all. The harness sorts every request before it runs.

Read also · 11 minHow an AI agent earns permissions: read, advise, draft, record, executeThe five levels of permission and how an agent earns each one.

Does every AI feature need an agent?

No, and this is where many teams go wrong. Ask one question: can you draw the flowchart before the work starts?

A workflow is cheaper, faster and far easier to test. Use an agent only where the path cannot be known in advance.

The harness of an AI-native company

The five jobs above live in software. But an agent at work also needs things no software vendor can supply: your rules, written down with an owner and a version; a memory of your customers, suppliers and past decisions, with the source of each fact; checks run on every case; a log of who decided what and why; and the rights each agent holds. That is the company’s part of the harness, and it sits above the agent’s.

Two harnesses around one model

Change the model and both harnesses stay. Change the harness and the same model does very different work.

Build or adopt

You rarely build a harness from scratch. The coding assistants from Anthropic, OpenAI and GitHub offer theirs as kits for developers, and LangChain publishes an open one called Deep Agents. They handle the loop, the tools and the context for you. You shape them without changing their code: rules in an instructions file, tools connected through MCP (a common standard for plugging tools into agents), skills, automatic checks before and after each action, and permissions.

Build your own when the loop has to live inside your own product, or when you want full control over every check. It is smaller than it sounds. The core of a working harness fits in about twenty lines of code, and it follows six rules.

Then improve it on real work. Shorten the history when it grows long. Make the agent check itself before it finishes. Log every step, run real cases, find where it fails, fix the harness and run them again. That is what harness engineering means, and it is how the team in the opening climbed into the top five.

One last habit: test the harness again with every new model. Some fixes cover weaknesses the new model no longer has. Remove them. The best harness is the simplest one that works.

Your plan for this week

Your checklist

Steps for this week

0 / 0
    Take the two-minute test to make this list yours

    Ticks stay in this browser.

    The model sets the ceiling. The harness decides how close you get to it, and in an AI-native company most of the harness is the company’s own: its rules, its memory and the rights it gives. That part is not bought with the next model. It is built, one process at a time.

    Where the numbers come from

    Questions readers askAnswers written by the SORP team

    Pick a question and we will answer it here.

    Not on the list? Ask the team your question

    Was this article useful?

    Where to go next

    More from the blog

    Talk to us

    Step 1 of 3
    What would you like to do?

    Rather talk first? Book a 30-minute call