--- title: "AI proposes, deterministic logic disposes" description: "AI in production is not AI that decides on its own. It is AI that proposes, to a system that has the right to say no. The three-layer architecture pattern behind it." url: "https://gilabs.fr/en/blog/ia-propose-deterministe-dispose/" lang: "en" author: "Yann Gilliot" published: "2026-07-15" tags: ["Architecture", ".NET", "AI Agents", "Reliability"] --- # AI proposes, deterministic logic disposes: the pattern that keeps AI production-ready By [Yann Gilliot](https://gilabs.fr/en/about/) ยท published on 2026-07-15 AI in production is not AI that decides on its own. It is AI that proposes, to a system that has the right to say no. The three-layer architecture pattern behind it. ## The short version - Three layers: AI proposes with a confidence score, deterministic business rules validate, a human settles what is left. - AI never writes to the database directly. A hallucination becomes a rejected proposal, not wrong data in production. - The useful question is not which model is used, it is what happens when that model gets it wrong. AI in production does not decide. It proposes, to a system that has the right to say no. Every AI system I have put into production shares this same three-layer pattern. ## The three layers of the pattern **AI proposes.** OCR, a language model, extraction: it reads the document or the input data, detects, extracts, and attaches a confidence score to every proposal it makes. It never writes directly to the database. **Business rules validate.** A deterministic layer, made of ordinary code, testable and auditable, checks every proposal the AI makes: expected formats, consistency against existing reference data, business thresholds. What passes these checks gets accepted. What fails is blocked before it reaches the system. **A human decides.** A confidence score that is too low, a business rule that gets violated, a case never seen before: the proposal goes into a validation queue, and a person decides. Every human decision is stored and fed back into the system, which improves with use this way, without heavy model retraining. ## What this pattern actually changes In this architecture, a model's hallucination is no longer a diffuse, uncontrollable risk. It is an explicitly handled case. An AI that gets something wrong becomes a proposal rejected by the validation layer, never wrong data reaching a production database directly. This is exactly how [the document pipeline](https://gilabs.fr/en/blog/pipeline-idp-production/) I delivered in a demanding industrial context runs day to day. It holds up over time not because the AI never makes a mistake, but because its mistakes structurally have nowhere to go without passing through a check. ## A detail that is not really a detail In a system like this, the part actually occupied by artificial intelligence is small. Everything that makes the system trustworthy comes down to ordinary software engineering: tested .NET code, a structured SQL database, explicit business rules, automated tests. That is what I build in a [.NET AI integration](https://gilabs.fr/en/services/dotnet-ai-integration/): AI inside the existing code, under its rules. ## The question worth asking I am often asked which model I use for a given project. That is almost never the most useful question. The question that actually matters is: what happens when this AI gets it wrong? Sometimes the answer allows full automation, as on [the Convention Online AI chain](https://gilabs.fr/en/blog/convention-online-ia-autonome/), where a mistake is fixed on the next pass. If the answer is not clear before the first deployment, the system is not yet ready for production. Topics: Architecture, .NET, AI Agents, Reliability ## Take it further What happens at your company when the model gets it wrong? For mid-caps and software vendors whose IT lives in .NET and SQL Server: AI developed inside your application (document extraction, agents, classification) with your business rules, your architecture, your code. Not another tool next to the IT system: a new capability inside it. I work in your repo, alongside your developers, to your team's standards. [.NET AI integration](https://gilabs.fr/en/services/dotnet-ai-integration/) **Book a 30-minute call**: [Calendly](https://calendly.com/yann-gilabs/30min)