Skip to content
Azinove GroupAzinove
Back to projects

Published project · Portfolio record

Kappeler — CERFA Automation Tool

An AI-powered internal tool that compares mockups to quotes, checks RLP compliance via RAG, detects nearby Monuments Historiques, auto-fills CERFA forms, and generates cadastral plans.

Organisation
Kappeler Publicité (Jaikin SASU)
Category
AI & machine learning
Kappeler — CERFA Automation Tool

The project, in context

What the project record documents.

We separate context, challenge, contribution and recorded scope to make the account more precise.

The sections below reproduce the published project record. Any outcomes mentioned describe statements recorded for this project; they are not presented as independent measurement.

01

Published context

An AI-powered platform that automates the preparation of CERFA permit applications for Kappeler Publicité's outdoor signage projects. It pairs a retrieval-augmented knowledge base of French signage regulations with Claude AI to pre-fill, check and generate the administrative paperwork each installation requires.

Statement from the project record
02

Recorded challenge

Installing outdoor signage in France means filing CERFA permit forms whose fields, supporting documents and local rules vary by municipality. Preparing them by hand was slow and error-prone, and a single inconsistent field could delay a whole installation.

Statement from the project record
03

Described contribution

A Next.js/TypeScript app backed by a pgvector knowledge base of the relevant CERFA forms and regulations. A RAG pipeline surfaces the right rules per case, and Claude AI drafts and validates the fields, flagging inconsistencies before submission — the team exports a ready-to-file dossier instead of starting from a blank form.

Statement from the project record
04

Recorded scope and outcomes

Kappeler Publicité assembles CERFA dossiers in a fraction of the previous time, with far fewer corrections. Regulatory know-how that used to live in a few people's heads is now a searchable system, making permitting faster and more consistent across projects.

Statement from the project record

Technical record

Recorded technologies and capabilities.

These elements complement the operating context. They describe the published record without turning a tool list into a broad promise.

Technologies

Next.jsTypeScriptpgvectorRAGClaude AIOpenAI Embeddings

Recorded capabilities

  • Mockup-to-quote comparison
  • RLP compliance checking via RAG
  • Monuments Historiques detection
  • Auto-fill CERFA forms
  • Cadastral plan generation

Other published projects

Explore projects in the same category first, followed by other contexts approved for public presentation.

PricingOS - AI Pricing Strategy PlatformAI & machine learning

PricingOS - AI Pricing Strategy Platform

PricingOS.ai is the first AI-powered pricing system built for startup founders, developed for Ellmann Consulting GmbH (Hamburg). It guides businesses through a structured 9-step process to build their pricing foundation, train a personalised AI Brain over time, and continuously improve recommendations with stronger data. The platform works in three phases: Foundation (product, customers, competition, costs), Pricing Decisions (boundaries, model, strategy), and Your Pricing Brain (continuous AI learning and refinement). PricingOS.ai offers two plans: Starter (€49/month, up to 2 products) and Pro (€79/month, unlimited products with AI Brain chat). Both include a 14-day money-back guarantee. Powered by Ellmann Consulting, built by Azinove.

View project record

Your context

What system do you need to move forward?

Share the starting point, constraints and decision ahead. We will frame a useful first step.

Explore our servicesDirect conversation · No imposed scope · Risks surfaced early