Automating regulatory diligence for cosmetic brands: 75% saved
Cosmetic brands and their suppliers answered regulatory questions by assembling evidence by hand from email, supplier portals and ERP systems. For a European RegTech start-up, Twistag designed one data model for raw materials, suppliers, formulations and regulatory documents, then built four agents that work from it. Time per regulatory inquiry fell by 75%, and revenue grew roughly 3x in the year after launch.
- 75%less time per regulatory inquiry
- 3xrevenue growth in the year after launch
- 3 of 10top European cosmetic brands live on the platform
- Client
- European RegTech start-up
- Industry
- Software & platforms
- Practices
- AI & Agents
- Timeline
- Multi-year, ongoing
- Stack
- OpenAI, AWS Lambda, PostgreSQL, Next.js
Compliance answers, assembled by hand.
Twistag built a regulatory and supplier-diligence platform for a European RegTech startup, cutting the time spent on a customer regulatory inquiry by 75% and reaching production at three of the top ten European cosmetic brands. The client's customers were assembling compliance evidence — REACH, CLP, food-contact rules, allergen disclosures, supplier provenance — by hand from documents scattered across email, supplier portals and ERP systems, with sales reps losing whole afternoons to it. Twistag designed the platform's data model first, then built four composable AI agents that reason over it. Revenue grew roughly 3x in the year following launch.
European regulatory obligations on cosmetic brands and their ingredient suppliers have grown faster than the teams handling them. A single product launch can require evidence spanning REACH, CLP, food-contact regulations, allergen disclosures, supplier provenance, and dozens of customer-specific compliance forms — each assembled by hand from documents scattered across email, supplier portals and ERP systems. Sales teams spent whole afternoons answering customer regulatory inquiries instead of selling. R&D waited weeks on supplier data to finalise formulations. Procurement chased the same vendor information every quarter. The cost was inefficiency, and deals lost to faster competitors and launches delayed by paperwork. The client is a European RegTech startup serving the cosmetic industry and is not named publicly.
One data model, four agents.
The data model first.
One source of truth for raw materials, suppliers, formulations, regulatory documents and each customer's compliance requirements. It was the first deliverable, and everything the agents do resolves against it.
Four agents on one schema.
An inquiry agent answers customer questions from the document store, citing sources and flagging what needs a person. A diligence agent keeps supplier documents current, a formulation agent surfaces compliant combinations for R&D, and a procurement agent runs routine orders. Sharing a schema, each can use the others' work.
Models that can be replaced.
Models sit behind a provider layer and were swapped twice during the engagement without the product changing shape.
Answers in under an hour, with sources.
Customer regulatory inquiries that took a sales or compliance rep three to four hours now resolve in under an hour — 75% less time per inquiry — and a meaningful share never reach a human at all. The platform is live at three of the top ten European cosmetic brands, with several more in pilot. Revenue grew roughly 3x in the year following launch. The inquiry agent's source citations are what made the compliance team willing to send an answer without opening the underlying documents themselves, and the platform now carries the diligence, formulation and procurement workflows on the same schema.
The agents are independently useful and far more useful together — which is the architecture decision that turned a feature roadmap into a product.
- OpenAI
- AWS Lambda
- PostgreSQL
- Next.js
Twistag built a regulatory and supplier-diligence platform for a European RegTech startup, cutting time per customer regulatory inquiry by 75%.
