--- title: "AI prospecting agent with n8n: where it is wrong" description: "An n8n agent sourced, enriched and scored my prospects every morning. What it taught me best was one concrete case where a confident AI can be completely wrong." url: "https://gilabs.fr/en/blog/agent-n8n-prospection/" lang: "en" author: "Yann Gilliot" published: "2026-06-19" tags: ["n8n", "Automation", "Generative AI", "Build in public"] --- # I built an AI agent for my own prospecting: here is where it gets it wrong By [Yann Gilliot](https://gilabs.fr/en/about/) ยท published on 2026-06-19 An n8n agent sourced, enriched and scored my prospects every morning. What it taught me best was one concrete case where a confident AI can be completely wrong. ## The short version - The n8n agent runs four steps every morning: read the CRM and LinkedIn connections through the official API, enrich with public company data, score each contact with a model, draft a message. - The scoring model only received the job title and the company name, not the LinkedIn headline: it ranked IT services firms and AI consultancies at 85 out of 100, meaning direct competitors. - Without the right context an AI does not fail quietly. It shows a score that inspires confidence and rests on nothing relevant. Documenting my AI systems in production sometimes means documenting my own tools. Here is one I built for myself: a prospecting agent meant to save me time every morning. What it taught me best was not what it automates well, but one specific place where it gets things wrong, confidently. ## What the agent does, every morning Running on n8n, the agent operates on its own through four steps: 1. It reads my CRM and pulls my LinkedIn connections through the official Member Data Portability API, with no scraping involved. 2. It enriches each company with public data (the French business registry, activity signals from official insolvency filings). 3. It scores each contact with a language model, based on my prospecting target. 4. It drafts a personalized outreach message for each contact it keeps. On paper, all that was left for me to do was review and click send. ## Where the AI got it wrong, with confidence The scoring model only received the contact's job title and company name, not their LinkedIn tagline. The result: it ranked profiles who do exactly my job at the top of the list, scoring them 85 out of 100. IT service companies, AI consulting firms. My "best prospects," according to the score, were in fact my direct competitors. Without the right context, AI does not fail quietly. It fails confidently, displaying a score that inspires trust while resting on nothing relevant. ## What this changed in how I work Since noticing this, I now systematically review the top of the ranking before sending anything. I manually remove profiles that have no business being there. I rewrite the messages the AI drafts poorly. It is the same lesson as on the [document AI pipeline I put into production](https://gilabs.fr/en/work/document-ai-pipeline/), where no batch reaches the database without human validation: artificial intelligence does not remove the need for human judgment, it moves that judgment to exactly the point where it matters most. Industrializing AI is not about trusting it everywhere. It is about knowing precisely where it fails, and keeping a human in control at that exact point. That is the whole idea behind the [AI proposes, deterministic logic disposes](https://gilabs.fr/en/blog/ia-propose-deterministe-dispose/) pattern. ## The real fix was not the AI, it was the method This case also illustrates why I always start an automation project by doing the process by hand, before writing a single line of automation. It was by observing my own sorting criteria manually that I spotted what the scoring model could not see. I go into this build method in detail in [why I spent weeks automating nothing](https://gilabs.fr/en/blog/concierge-dabord-code-ensuite/). Topics: n8n, Automation, Generative AI, Build in public ## Take it further Would a repetitive process of yours deserve the same agent? 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)