--- title: "AI chain with no human validation: setting the dial" description: "One pipeline requires human validation at every step. Another one runs all night with nobody watching. How to decide where to set the dial, based on the real business stakes." url: "https://gilabs.fr/en/blog/convention-online-ia-autonome/" lang: "en" author: "Yann Gilliot" published: "2026-06-17" tags: ["Automation", "Generative AI", "Architecture", "SEO"] --- # Zero human validation, and that is the right call: the Convention Online AI chain By [Yann Gilliot](https://gilabs.fr/en/about/) ยท published on 2026-06-17 One pipeline requires human validation at every step. Another one runs all night with nobody watching. How to decide where to set the dial, based on the real business stakes. ## The short version - convention-online.com produces all of its content through an autonomous AI chain: collection, descriptions in four languages, generated visuals, publication, with no human validation. - On a timesheet pipeline that feeds payroll I require the opposite, systematic human validation. Same technology, opposite stakes, opposite architecture. - The question that shapes the architecture is not which model to use, it is what happens when the AI gets it wrong. One [document pipeline](https://gilabs.fr/en/blog/pipeline-idp-production/) I delivered requires systematic human validation before anything gets written to the database. Auditability demands it: an error on a timesheet that feeds into payroll is expensive. Here is the other extreme, by deliberate design this time. convention-online.com is a worldwide directory of professional events. Its entire content is produced by a fully autonomous AI chain, with no human involvement. The context and outcome of the project are on the [Convention Online project page](https://gilabs.fr/en/work/convention-online/). ## What runs every night, with nobody watching Every night, four things happen with no human intervention at all: - Professional events are collected from the web, with automatic deduplication and cleanup. - A web-searching LLM enriches each entry. It identifies the official site and the organizer, then writes descriptions in four languages (English, French, Italian, Spanish). - Missing visuals are generated by an image model, on on-demand cloud GPU, with no dedicated infrastructure to maintain. - Everything is published to a multilingual, SEO-optimized site, updated continuously. The whole chain runs on a resilient scheduled service: if something fails, it resumes on its own, without intervention. ## The real decision was not technical The question that actually shaped the architecture was not "which model to use" but: what happens if the AI gets it wrong? On timesheets that feed into payroll, a mistake is costly and propagates. The answer is simple: a human validates, always, no exceptions. That is the [AI proposes, deterministic logic disposes](https://gilabs.fr/en/blog/ia-propose-deterministe-dispose/) pattern. On an automatically enriched event listing, a mistake gets corrected on the next pass, with no serious consequence. The answer becomes: it is fine to automate 100% of it. Same underlying technology. Opposite business stakes. Therefore opposite architecture. ## Industrializing AI is not a single dial This, to me, is where the real difference lies between an isolated AI project and a successful AI transformation. It is not about automating everything, nor about requiring validation everywhere on principle. It is about setting the dial correctly, business case by business case, based on the real cost of a mistake. This is exactly the work I do ahead of every [AI agents and automation](https://gilabs.fr/en/services/ai-agents-automation/) engagement. Map the processes, identify where a mistake is expensive and where it barely matters, then size the level of human validation accordingly. The outcome is never a binary choice between "fully automatic" and "fully validated," but a precise calibration, process by process. ## Sources and references - [convention-online.com, the platform described in this article](https://www.convention-online.com) Topics: Automation, Generative AI, Architecture, SEO ## Take it further Where should the human check sit in your own chain? The process runs, your teams supervise. Inbound documents read automatically, data entry eliminated, reporting produced without a thought, executed end to end in your Microsoft 365 tools and business apps, with human validation where it matters. When automation isn't enough, I build the application that's missing: business UI, back office, API. No stitching together no-code blocks when the job calls for real software. [AI agents and business applications](https://gilabs.fr/en/services/ai-agents-automation/) **Book a 30-minute call**: [Calendly](https://calendly.com/yann-gilabs/30min)