Eurologado — EU Cosmetics Compliance SaaS
100+ customers, AI-assisted regulatory dossiers
Key metrics
Context
Every cosmetics brand selling in the EU must keep a Product Information File (PIF) for each SKU. It is a legal obligation, and the cost of getting it wrong is the product coming off the shelf.
The challenge
The process is complex and error-prone, and has historically been run on spreadsheets and email chains. The hard part is not storing the document: it is guaranteeing the dossier is complete and consistent for every SKU — and being able to prove it.
The architecture
I designed and shipped the entire product as sole engineer: a NestJS API with an automated dossier generation pipeline, AI-assisted document creation, structured data validation and a Next.js dashboard for compliance teams.
Architecture flow
Product data
- One dossier (PIF) per SKU
AI drafts
- Assisted document creation
Structured validation
- Decides whether the dossier complies
- Flags what is missing
PIF dossier
- Complete and consistent
Compliance team
- Next.js dashboard
Engineering decisions
AI drafts, validation decides
The model helps write the document, but what decides whether the dossier is compliant is structured validation — because in a regulatory context the output has to be verifiable, not merely plausible.
Detecting what is missing, not just filing it
The system flags the gap instead of waiting for an audit to find it. Flipping that moment is the difference between a filing tool and a compliance tool.
Zero to 100+ customers, solo
Regulatory domain modelling, API, AI pipeline and interface — all delivered by one person, in a domain where understanding the rule is half the problem.