Regulatory chat

A regulatory assistant for Loi Jardé, GDPR, ethics committees and ANSM

Ask your regulatory question, get a focused, sourced answer — without leaking real cases to a consumer ChatGPT.

Start for free7 days · no credit cardRead the blog

Regulatory chat

How it works

Tight scope, sober answers

One question, a French scope

Ask anything about RIPH qualification, CNIL reference methodologies (MR-001 to MR-006), ethics committee submissions, ANSM declarations, ICH-GCP.

The AI answers within scope

The assistant is constrained to French academic clinical research regulation. Outside that scope, it tells you so instead of inventing an answer.

Ephemeral conversation

No session is persisted by default: leave the page and the history disappears. Suitable for sensitive questions covered by professional secrecy.

What you get

Scoped assistance, not a generic ChatGPT

Restricted regulatory scope

The AI is instructed to answer only on Loi Jardé, health-data GDPR, ethics committees and ANSM — outside scope, it says so.

French and EU sources

Loi Jardé, French public health code, CNIL reference methodologies, EU Regulation 536/2014, ICH-GCP: the knowledge base is kept current.

Confidentiality by default

Hosted in France, no data used to train models. Your exchanges stay private to your account and are deleted automatically after 12 months. Designed for hospital use.

A corpus kept current

The regulatory corpus is updated as new material is published, and answers cite the binding texts they rely on.

Frequently asked questions

What you should know before using the regulatory chat

Is the regulatory chat available to every user?

It is included in every plan, Discovery trial included: investigators and research office teams alike can use it as soon as a plan is active on their account or their seat.

Are my questions stored?

Yes, so that you can find your history again: each conversation is visible to you only, you can delete it at any time, and it is erased automatically 12 months after it was created. None is used to train AI models.

Which questions will the assistant refuse?

Anything outside the scope of French academic clinical research regulation: clinical medicine, non-health law, taxation, prescriptions. The assistant says so explicitly instead of improvising.

How do you avoid hallucinations?

Every answer relies on a search through the official texts (French Public Health Code and Loi Jardé, EU regulations, CNIL decisions) and cites its sources. When the texts do not allow a confident answer, the chat says so rather than making one up.

A regulatory question? Ask it in a controlled context

Sign in to your Protocolis workspace and open the regulatory chat from your study — without leaking your case to a consumer AI.

Start for free7 days · no credit cardSee pricing