French company data
INSEE Sirene
Identity, establishments and headcount for every French company.
Official site: www.sirene.fr
What it does
- Search companies by activity code, department, postcode, headcount band, size category, revenue range or collective agreement
- Resolve a SIREN to full identity, or a SIRET to a specific establishment
- Find a company's registered headquarters among its establishments
- Produce the avis de situation for an establishment
- Enumerate exhaustively from the SIRENE stock when a result set runs past the search API's ceiling
Where the data comes from
Two things about Sirene cost people real work.
Geographic filters match any establishment, not the head office. Ask for companies in département 75 and you also get the ones headquartered in Lyon with a Paris office. When you mean the siège, you have to say so.
Enumeration truncates silently past roughly ten thousand results. No warning, no flag, just a shorter list than reality — a market map that looks complete and is not. Past that point the connector reads the Sirene stock, which has no cap.
Why through Tulina
Most systems now publish their own way for a model to reach them, and that is a good thing — it is what Tulina connects to. The connection was never the hard part. Deciding who may use it, what it is allowed to return, and what the model knows before it asks: that is.
The keys stay in one place
Connect INSEE Sirene once. The credential is encrypted in a vault, never held in clear, and never pasted into a chat or a workflow file. A person uses their own key where they have one, their team's where they do not, the organisation's after that — so nobody is blocked and nobody is handed more access than they need. Revoke it once and everything running on it stops.
What leaves is filtered before it leaves
Roles decide who can reach INSEE Sirene at all. Beyond that, a policy on the connector itself decides what comes back: fields dropped, identifiers masked or hashed, people pseudonymised. The data is minimised at the source rather than after it has already reached a model.
Every call is on the record
Runs are logged for the organisation — what was called, by whom, when. That is what makes an automated action reviewable after the fact, and what a security review asks for first.
The run starts knowing your company
A direct connection gives a model access. It does not tell it how your company names things, which accounts matter, or what was decided last quarter. Tulina carries that across every tool, so the same request against INSEE Sirene returns something usable instead of something generic.
Processes that run on INSEE Sirene
Find doctors and clinics
A places census of doctors and clinics gets cross-referenced against France's practitioner registry and facility directory so nothing is missing from a city's real coverage.
Outreach based on government data
Every candidate's website is verified before a credit is spent, tiered by signal strength, then written one grounded opener that is checked for repetition.
Qualify inbound leads
Every new lead is matched to its legal entity, scored on real headcount and filed accounts, and written back before a rep opens it.