Does the model still give a useful answer?

Yes. Values are swapped for stable tokens rather than removed, so the model keeps the structure it needs. The real values are restored in the response.

Is pseudonymized data anonymous?

No. Under GDPR it is still personal data, and sending it outside the EU is still a transfer that needs the right agreements. The firewall reduces exposure. It does not remove the obligation.

A tenant admin can, and the acknowledgment is recorded with who and when. Without that record, a request to an external or non-EU model is blocked.

Which data types does it find?

Names, emails, phone numbers, IBANs, card numbers and national IDs, across the message and the tool content, plus any patterns you add yourself.

What ends up in the audit trail?

How many entities were found and of which type. Never the values themselves.

Firewall

Keep personal data out of the model.

The firewall finds names, emails and account numbers in a prompt and swaps them for tokens before any model sees them, then restores the real values in the response. It runs on every request by default, and it is what makes reaching an external model defensible: the model sees tokens, never the raw values, and the transfer is on the record.

Start free Read the docs

detect · pseudonymize · restore

No personal data leaves Akumi.

The best model is often the wrong place to send a name.

To answer a real question, a prompt carries real data: a customer name, an email, an account number, a support ticket. Send that to an external model and you have made a transfer and widened your leak surface. Strip it by hand or with a few regexes and one missed field is a breach. Turn the protection off to ship faster and the gap is invisible until an auditor finds it.

How it works

Detect, pseudonymize, restore.

Every prompt runs through the firewall before routing. The work happens in the request pipeline, so the token map never reaches a provider.

01DetectFind the personal dataAn EU-hosted analyzer and your own patterns find names, emails, phone numbers, IBANs, card numbers and national IDs across the message and tool content.
02PseudonymizeSwap it for tokensEach entity becomes a stable token, so the model keeps the structure it needs to answer while the real value stays behind. The same value maps to the same token.
03RestorePut the values backThe token map lives in the request context, never sent to a provider. On the way back, tokens become the real values again, so your response comes out whole.

Entity types you can switch on, and the token each one becomes.

Why it is different

Pseudonymized is not anonymized. We say so.

The firewall shrinks what you expose and gives you a record of it. It does not make personal data disappear, and we will not pretend it does. The obligations stay yours, so we built the controls to meet them honestly.

Still personal data
Under GDPR, pseudonymized data is still personal data. Sending it to a non-EU model is still a transfer that needs the right agreements. The firewall reduces exposure. It does not remove the obligation.
Gated, never silent
Turning the firewall off takes a tenant admin acknowledgment, recorded with who and when. A single request runs un-firewalled only when that record exists.
Fails closed
If a request is not firewalled and has no acknowledgment, routing to an external or non-EU model is blocked, not waved through.
Provable
Each request meters on its own line and writes a metadata-only audit trail: how many entities, of which type, never the values. Hand the reviewer the log.

Protection

It keeps the answer.

Pseudonymize, do not destroy

Stripping data breaks the answer. The firewall swaps values for tokens and restores them after, so the model has what it needs and your response comes back complete.

On by default

Every request is firewalled unless a tenant admin turns it off and records why. Privacy by design, not a setting you have to go find.

The key to external models

An external or non-EU model is blocked at the egress guard unless the request is firewalled or carries a recorded acknowledgment. The firewall is what opens that door safely.

FAQ

Questions people ask about the firewall.

Does the model still give a useful answer?: Yes. Values are swapped for stable tokens rather than removed, so the model keeps the structure it needs. The real values are restored in the response.
Is pseudonymized data anonymous?: No. Under GDPR it is still personal data, and sending it outside the EU is still a transfer that needs the right agreements. The firewall reduces exposure. It does not remove the obligation.
Can we turn it off?: A tenant admin can, and the acknowledgment is recorded with who and when. Without that record, a request to an external or non-EU model is blocked.
Which data types does it find?: Names, emails, phone numbers, IBANs, card numbers and national IDs, across the message and the tool content, plus any patterns you add yourself.
What ends up in the audit trail?: How many entities were found and of which type. Never the values themselves.

Start here

Turn it on before the first token.

Create a key and the firewall is already on. Route anywhere you are allowed, with personal data tokenized on the way out and restored on the way back.