Every AI. Inside your walls.

Pulse is a sovereign AI engine, installed on your premises, for professions where client files cannot be shared — accountants, lawyers, notaries. Running locally, nothing leaves. And when an external call is chosen, it leaves masked.

What if the AI is wrong?

Your liability is on the line for everything you sign. So every claim cites the document and the page — verification is instant. And when the answer isn't in your files: "not in your knowledge base".

Where does my client's file go?

Nowhere. Every execution leaves a signed, chained certificate, verifiable offline — your auditor can check it without trusting us.

The product

One engine, three bricks, one proof.

Your staff already paste excerpts of client files into public chatbots — not out of malice, but because it's useful. Pulse closes that gap: the AI installs on your premises, and client files never leave.

Situation AThe ban

The firm bans AI. It loses productivity to competitors who use it — and the leak continues anyway, quietly.

Situation BShadow AI

Excerpts of client files already leave through public chatbots, on personal browsers. Nobody knows, nothing is traced.

Situation CThe stalled project

The firm starts an AI project, someone asks where the data goes, and the project dies in committee. Six months lost.

Our answerWe don't sell an app. We sell the engine.

An application gets copied in three months. The engine that routes, protects, proves and grounds itself in your documents — the one your existing tools plug into — is much harder to displace. Built for accountants first; lawyers and notaries next.

Synapse is the mandatory gate for every AI call: it picks the model that answers, masks what must not leave, and counts what it costs.

RoutingBy complexity

The cheapest model actually capable of handling the request: a small local model to rephrase, a large one for a legal synthesis.

ShieldPII / PHI Shield

Names, emails, numbers replaced with stable pseudonyms before anything leaves, restored in the answer. A local model sees the original: nothing leaves the network.

MeterEvery call counted

Provider, model, tokens, cost, PII detected: everything is logged, line by line. "What left the building?" always has an answer.

The detail that changes everythingPseudonymisation is consistent

The same person keeps the same alias everywhere — debate, chat, document search — and two distinct people stay distinct. Without that, masking would lose the thread as soon as a file mentions three people.

A generic model doesn't know your files. Cortex ingests them, retrieves them, cites them — and flags when they contradict each other.

IngestionEvery format

PDF, Word, Excel, emails — and scans, read by local OCR. Drop a file in a watched folder: it gets indexed.

ChunkingAlong the real structure

Headings, sections, tables: every chunk knows which document and section it came from. That's what makes "2025 filing, p. 12" citable.

SearchHybrid, reranked

Semantic and keyword search fused, then reranked. A relevance floor forbids citing an off-topic passage.

Honesty"Not in your knowledge base"

When the answer isn't in your files, Pulse says so instead of making things up. And the AI reads while leaving a trace in the audit log, like any other user.

Reflex, the third brick: not a tool you have to open, but an engine that works overnight and presents the result in the morning.

Monday, 7 amThe attention note

Review the files modified during the week and produce an attention note, ready with the coffee.

A file arrivesIndexed, checked

Dropped in a watched folder: indexed, facts extracted, alert if it contradicts what's already known.

A client emailDraft ready

A draft reply grounded in the file, ready to review.

Three rulesLocked in the executor, not in a prompt

Nothing leaves without human approval. A missed slot catches up once, not twenty times. And when there's nothing to say, nobody gets notified.

The Gateway speaks OpenAI's protocol and Anthropic's: everything you already use keeps working — now metered, masked and proven.

votre-outil-actuel.py

# any existing OpenAI or Anthropic client

client = OpenAI(

base_url = "http://pulse.mon-cabinet.local/v1" ← the only line that changes

api_key = "sk_live_…"

)

model = "pulse-sensitive+cortex" ← local + grounded in your documents

# → cited answer, never left the machine · x-pulse-proof: prf_8a3c…

AddressThe model is an address

"pulse-auto", "pulse-sensitive", "agent:name+cortex": the engine's capabilities are chosen through the address — never imposed.

ProofSigned, chained

Every response carries an ed25519 certificate chained to the previous one, verifiable offline. Your auditor doesn't have to trust us.

Streamed = signedWhat you actually saw

The proof covers what was really displayed on screen, not a version reconstructed after the fact.

The offer, priced.

Step 1€0Assessment

the assessment — 30 minutes, on site or by video call, no commitment.

Step 2€2,900 excl. VATInstallation & training

installation and training, once.

Step 3€1,500 excl. VAT/yrLicence & support

the licence, support included, no commitment beyond the year.

You stop whenever you want: your documents are already on your premises, there's nothing to migrate. And if one machine isn't enough, we plug in a second one — nothing to reinstall.

Request the assessment — 30 min, free

P.S. — the Pulse Box, a preconfigured machine to plug in inside your walls, is under construction. No promised date: it ships when it works.

Who I am

My name is Dorian.

I build Pulse alone, from Nîmes, incubated at the CCI du Gard. I ship every week and I answer support myself: if you write to me, I'm the one reading.

I'd rather lose a sale than promise something the product doesn't do yet — it's less spectacular, but it can be verified.

Nîmes, FranceIncubated at the CCI du GardOne release a week

Before you sign up

The questions we get first.

Why not just ChatGPT Enterprise?

Because your data goes to a third party, you pick neither the model nor the cost, and nothing proves after the fact what was sent. PulseLABS routes, masks, sources and signs every call — and can run with no internet at all.

Can I start without installing anything?

Yes. You create an account, you get 60,000 tokens and a working workspace. Installing it on your own hardware only becomes useful the day you want nothing to leave the building.

If I move on-premise, do I rewrite everything?

No. Same API, same model addresses, same SDKs, same keys. You change the base URL and your integrations keep running.

What if the AI gets it wrong?

Every grounded answer cites the document and the page. Cortex flags when your own documents contradict each other, and says “not in your knowledge base” instead of inventing.

Who is behind this?

Pulse Software, a software company in Nîmes, France. The same person builds the engine and answers your messages — backed by the CCI du Gard incubator.

Contact

Start with an assessment.

Thirty minutes, on site or by video call, no commitment. We look at three things: what your team already uses, what's risky, and what an AI installed on your premises would change.

Request the assessment — 30 min, free Create account

or simply: contact@pulse-labs.fr — reply within 24 business hours, by a human