Why a Raw Model Isn't Enough#
On its own, an AI model does exactly one thing: you give it one input, it hands you one output, and then it stops. One step. No memory of the last one, no ability to take the next. It's a brain in a jar: brilliant, but stuck.
That's not the magic you feel in Claude Code or Codex. Those tools take dozens of steps on their own: reading your files, running things, catching their own mistakes, pulling what they need from memory or the internet, looping until the job is actually done. A raw model can't do any of that by itself.
That repeat-until-done cycle (read what's there → decide the next step → do it → check the result → go again) has a name. It's the agent loop, and it's the engine that turns a one-shot answer into finished work. Hold that picture. It's the heart of everything that follows.
And the best ones don't just act. They check their own work. Boris Cherny, who created Claude Code, says the most important thing for getting great results is giving the AI a way to verify its own work: a feedback loop that, in his words, can 2–3× the quality of the final result. That self-correction is a harness feature, not a model one.
The whole story is the gap between "answers a question" and "does the job." A chatbot answers. A useful AI product does the job. And it's not the model that closes that gap. It's everything wrapped around it.
If the model is the easy part and what's built around it is the hard part, the obvious question is: what is a harness?
So What's a Harness?#
Picture a wild horse. It's raw power it's nearly useless until you harness it: reins to steer it, blinders to keep it focused on the road, a saddle so it can carry weight.
A model is the horse. The harness is the software wrapped around it. It adds the hands (tools), the memory, the reins (guardrails), and the loop that lets it take many steps. That combination (not the horse alone) is what does real work.
Here's the equation that matters: an agent = a model + a harness. The agent is the working thing you actually use: a model with a harness wrapped around it. The model is the raw intelligence. The harness is what puts it to work. LangChain (a popular toolkit for building these systems) frames it bluntly: the harness is everything that isn't the model itself, and that "everything else" is where almost all of the engineering, and the magic, actually lives.
There's a name for the work of building one, too. Mitchell Hashimoto (a veteran engineer, co-founder of HashiCorp) calls it harness engineering: "anytime you find an agent makes a mistake, you take the time to engineer a solution such that the agent never makes that mistake again." So a harness is what that work leaves behind: continuous improvement turned into software. Every lesson about how the AI fails gets built into the wrapper so it stops failing that way.
What's Inside a Harness#
At the center of the harness, we have the loop, the engine that keeps calling the model until the job is done. Plus a kit of 7 parts that allows us to steer the model's behavior:
The tools. Without them, the AI model can only provide “talk”. In other words, it can only output text, images or audio. With them, it can interact with the outer world, such as reading files from your computer, executing code, searching the web or editing a document. This is the single most important part: the ability to act.
The memory. The AI forgets everything between sessions, so the harness gives it files to write to and read back: its long-term memory and to-do list. The files are what let it remember anything at all and pick up where the last session left off. The simplest memory implementations are based on files, but depending on the complexity of your use case, you may need a more sophisticated solution based on vector or graph databases.
The context. The context window is what the LLM sees at a time, in each iteration of its loop. The problem is that it's limited to 128K, 256K, up to 1M tokens. As the context windows grow, the model starts to get confused and produce incorrect results. Problem known as "context rot." The role of the harness is to keep the context window sanitized by adding/removing components at each iteration. Ideally, you want to keep the context with exactly the right information that gets the job done. No more, no less.
The sandbox. It’s a safe room where the AI can make a mess (run things, break things) without the risk of touching anything real in your business, such as deleting files, accessing sensitive data or even running malicious code on the computers from your private network. The goal is to give the agent exactly as much access as it needs, no more, no less, to get the job done. Otherwise, during its agentic loop, it can always decide to go rogue just to achieve its goals. It’s very common to start looking around for API keys to access data from your database or other services.
The guardrails. A big part of guardrails is the permission layer, which sets the rules for what the AI may do on its own: what runs freely, what needs your okay first, and what's automatically denied. These need to be carefully balanced to avoid asking the human to accept each command (which adds a ton of friction, forcing the user to babysit the agent) while still asking for user input at essential points, such as deleting a file or changing one that's not versioned.
The orchestration. For complex jobs, 1 AI acts as a project lead, delegates to a team of specialist AIs, each handling a piece and then pulls the results together. A caution from experience: don't reach for the multi-agent systems too early. I once split a job across 5 or 6 specialist AIs, and a single, well-set-up one beat the whole team.
The interfaces. The same harness is reachable from your phone, laptop, browser, Slack, or WhatsApp.
This is abstract until you notice you've already used several of these.
Every popular AI tool you are using is a harness. Claude Code, Cursor, Codex: the same kind of model inside, a different harness wrapped around it.
Here's what usually happens: when a product feels better than a plain chatbot (it remembers your project, fixes its own mistakes, actually finishes the task), that feeling is the harness doing its job. Two products can call the exact same model and feel worlds apart, purely because their harnesses are worlds apart.
And this isn't just a vibe. In one public test done by LangChain, they changed only the harness around a coding agent (same model throughout) and it climbed from roughly 30th place into the top 5 on the Terminal Benchmark used to evaluate agents.
Before we get to what this means for your company, let's clear up 3 words that get thrown around as if they're the same thing. They're not.
Three Words People Mix Up#
1. Prompt engineering = writing good instructions. Telling the AI clearly what you want.
2. Context engineering = managing what the AI sees (the context window). You want to keep it focused (only what’s relevant), because piling on clutter actively confuses the model (the context rot issue).
3. Harness engineering = building the whole system around the model: the tools, the memory, the guardrails, the loop.
So harness engineering is the last step: the whole AI application around the model. Which raises the real question for a decision-maker: should your company buy or build its own harness?
What This Means for Your Company#
Claude Code is a harness someone else built for general coding. It's superb at that. But it will never know your finance rules, your data, your guardrails or your customers. The moment your AI needs to do your job, a generic harness hits a wall.
Still, a harness you build becomes its own product, with its own bugs, issues and maintenance overhead. Owning the layer can give you an advantage, but it's an ongoing investment, not a one-and-done build. The real question isn't "can we build one?" It's "is this the layer where owning it is worth the upkeep?"
That's why most people I know, including myself, are customizing harnesses (via skills and MCP servers) intended for coding, such as Claude Code, for their own use cases, such as writing, video editing, or coupling them with Notion or Obsidian to transform them into their personal assistants.
But using coding harnesses for everything has one major drawback: they are optimized for coding, and the people building them will keep optimizing them for coding. This might lead them to behave more poorly with each version update.
Another huge drawback is that it's almost impossible to build your own product on top of them. They are amazing as internal tools, but once you want to stitch a UI on top of them or distribute them to your users, you hit another wall.
That's why we started seeing harnesses specialized for different domains, such as:
- Creative: Descript (video), Canva Magic Studio & Adobe Firefly (visuals), Figma AI (design)
- Legal: Harvey (drafting contracts), CoCounsel (reviewing contracts)
- Medical & Healthcare: Abridge & Nabla (generating clinical notes from doctor-patient conversations)
- Financial: I personally worked at ZTRON as a harness for financial advisors
- Productivity: Notion’s AI
But there is a middle ground between building and buying. As harnesses are being standardized, major frameworks such as Pydantic AI's Harness, Pi or LangChain's Deep Agents have recently entered the game. These frameworks differ from Claude Code because they are implemented in programming languages such as Python, TypeScript or Golang that provide the agentic loop, the 7 key parts and the option to easily add your own UI/UX and distribution. Thus, you don't have to worry too much about building the harness; rather, focus on building the business logic on top of it. Process similar to the good old days of software engineering.
You don't need to build a harness tomorrow. You need to know that the harness, not the model, is the part you'll eventually want to own, and to start asking, "whose harness is this, and what does it cost us not to control it?"
Harness in Conversation#
"We're still building out the harness around the model."
We have the AI. Now we're building the software that lets it actually do the job.
"That's a model problem, not a harness problem."
The AI itself is getting it wrong, versus we just haven't given it the right tools or memory yet. (Usually it's the second one.)
"We don't want to be locked into someone else's harness."
We want to own the layer that makes our AI ours, instead of renting it from a vendor.
"We should switch to an open-source harness."
Move off a closed tool like Claude Code to an open-source alternative you can see inside and bend to your needs, such as OpenCode or Pi.
Terms covered: Harness · Model · Agent · Loop · Tools · Memory · Context · Sandbox · Guardrails · Orchestration · Interfaces · Prompt vs. Context vs. Harness engineering.
Further Reading#
