The essentials in 5 points
- Two companies with the same model get opposite results. The difference is not the model, it is the harness.
- The harness is the software layer around the LLM: the model is the brain, the harness is the body (memory, reflexes, limits).
- A robust harness rests on five layers: identity, memory, tools, triggers, guardrails.
- More layers is not better. Over-harnessing makes the agent as unpredictable as under-harnessing.
- When choosing a provider: some sell access to AI, others build the harness. These are not the same product.
The short answer
When two companies use the same AI model and get radically different results, the cause is almost never the model. It is the harness: the software layer that wraps the model and decides what it sees, what it keeps, what it can do, and what stops it. The model is the brain, the harness is the body.
A robust harness is organized into five layers: identity (the persistent system prompt), memory (what survives context resets), tools (dedicated capabilities rather than a generic chat), triggers (what makes the agent act without being asked), and guardrails (what bounds its autonomy). The rest of this article details each one, the design trade-offs, and what changes when you choose a provider.
The model has become the easy part
There is a stubborn reflex in technical leadership: to believe that the quality of an AI deployment depends first on the choice of model. That was true two years ago. It no longer is. Frontier models are converging in capability and commoditizing in access. A careful reading of mature agentic systems leads to a clear conclusion: you could swap the underlying model for another and, with a little optimization, recover a comparable level of performance. What makes the difference lives in the orchestration, not in the weight of the neural network.
In other words, differentiation has left the raw model and moved toward memory and context. A tool like Claude Code is not first a terminal chat, it is an agent orchestration platform that presents itself as a chat. The value is in the harness. For a CTO, that shifts where attention and budget should go: less on picking between two models, more on the engineering that surrounds them.
The five layers of a harness
1. Identity. This is the persistent system prompt, re-read on every turn rather than once at startup. In the Claude Code ecosystem, it is the CLAUDE.md file: a few thousand characters that define the agent’s behavior, its working principles, its conventions. It is the highest-leverage configuration point in the whole system, because it changes the agent’s behavior without ever touching the model.
2. Memory. A model forgets everything between sessions and degrades as its context grows. Memory is what survives those resets: files read at startup and rewritten at the end of a session, a database for structured queries, a consolidated snapshot passed from one session to the next. Without this layer, the agent redoes every task cold and compounds nothing.
3. Tools. A useful agent is not a model that “chats with files,” it is a model equipped with dedicated capabilities: skills that codify domain expertise, connectors to internal systems, precise commands. A well-designed tool does more than expose data, it encapsulates a reliable procedure that the agent triggers at the right moment.
4. Triggers. A mature harness does not only answer when spoken to. Hooks and scheduled tasks make it act on its own: checking a repository at regular intervals, reacting to an event, restarting a loop. This is what turns the agent from an assistant you prompt into a system that works continuously.
5. Guardrails. Autonomy is not won by removing protections, it is won by placing them. Granular permissions, isolation of critical components, deterministic blocking of destructive actions, human review on sensitive operations (production, migrations, shared infrastructure). This layer does not depend on the model’s good will: it is a hard rule, it does not hallucinate.
The design trade-offs
Laying down the five layers is not enough, they have to be tuned. Three trade-offs recur in every deployment.
Loop or orchestration? A classic agentic loop lets the model decide when to stop, which suits exploratory tasks. An orchestrated plan that splits work across several agents suits broad, reproducible tasks. The real skill is no longer to phrase a better instruction, it is to architect the right loop.
Over-harnessing or under-harnessing? Too many skills, rules, and triggers bloat the context and make behavior unpredictable. Too few, and the agent wanders. The right balance is a short, behavioral identity prompt, not a wall of rules. Adding a layer has a cost, and it has to be justified.
Fixed or reassessed? A harness is never final. Every new model release moves the line of what still needs scaffolding. A stronger model makes unnecessary the structures you had built to compensate for its weaknesses. The discipline is to reassess the harness with each release and strip out the scaffolding that has become redundant.
What changes when you choose a provider
This is where the topic becomes very practical. In the market, two offers coexist under sometimes identical words. The first sells access to AI: a model, an API key, a chat interface, sometimes a convincing demo. The second builds the harness: the domain identity, the memory that compounds, the tools that encapsulate your expertise, the triggers that keep the system running, the guardrails that keep it under control.
The first delivers something that impresses in a meeting and disappoints in production, because nothing retains, nothing bounds, nothing evolves. The second delivers a delegable system. The question to ask a provider is therefore not “which model do you use?” but “how do you manage memory, where do you draw the line between automatic and human, and how does your harness evolve when the model changes?”. The answer to those three questions separates a demo from a deployment.
At Colombani.ai, this five-layer architecture is the backbone of every business AI agent deployment and the core of the Claude Code in Production course, Qualiopi-certified. The expertise brought to bear is certified by Anthropic (Claude Certified Architect), and the harness delivered is designed to stay under your control and evolve with every model release.
Sources
Have a project in mind?
Describe your situation. Straight answer within 48 hours.