(in effect as of October 2023)

Click here to request a report of our full suite of security measures.

security icon white

Rigorous security standards.

All data submitted to or generated with Kelsen undergoes a level of professional security controls that far surpasses that of any consumer-facing language models, like ChatGPT, GPT-3, GPT-3.5 or or GPT-4.

anonymous icon white

Data privacy is our primary concern

To ensure an industry-leading level of data privacy compliance, we have partnered with Private AI to deploy their cutting-edge machine learning technology to ensure that all personally identifiable information is kept under lock and key and is never viewed any language model.

encryption icon white

User data is encrypted at all times

Data is encrypted in transit and at rest with AES 256-bit professional-grade encryption protocols to ensure that user data is only viewable by the user. Not even Kelsen can access user data.


We go to considerable lengths to keep user data safe.

Kelsen has partnered with Private AI, to deploy their cutting-edge machine learning identification technology. This model relies on the latest advancements in machine learning to identify personally-identifiable information based on context, understanding text in a way that is similar to humans. This technology identifies over 55 different types of direct and quasi-identifiers in 49 different languages.

Importantly, this identification model is hosted on Kelsen’s server infrastructure, which means that the data never gets transferred to Private AI or any third parties.

To ensure informational security, all written data submitted to or produced in Kelsen software:

(i) is verified for over 55 different types of personally-identifiable information;

(ii) any personally-identifiable information found in the input data (such as names, dates, document numbers, addresses, countries, email, IP, monetary values, etc.) is automatically extracted and substituted for context-appropriate pseudonyms;

(iii) the correspondence keys linking the pseudonyms to the original information are kept on-premise, in an encrypted repository that is only accessible to the user and these data are never transferred to a language model; and

(iv) the pseudo-anonymized data is only re-identified with the original personally identifiable information in the last leg of the text generation process, after the output text has been generated by the language model, and before the data is served back to the user.

Presently, Kelsen employs four different AI models: one proprietary neural network (our Logical Thought Network), and two customized language models hosted on Kelsen’s cloud infrastructure, as well as one commercial language model for text augmentation, namely GPT-4, hosted on Microsoft Azure OpenAI Service.

Microsoft Azure OpenAI Service is controlled and hosted by Microsoft and it does NOT interact with any other services operated by OpenAI (eg.: ChatGPT, or the OpenAI API).

No. We do not use client data to fine tune or train any instance of any language model, including our own language models and/or commercial models like GPT-4 and others.

Anonymized and sanitized user data within specific user-managed Projects are only used to train Project-specific instances of our proprietary Logical Thought Network (LTN), a neural network, which does not communicate with those of any other Projects. When a Project is deleted, so is that Project’s instance of the LTN, along with all submitted data.

User’s prompts (inputs) and completions (outputs), embeddings and training data:

(i) are NOT available to other customers;

(ii) are NOT available to Kelsen or any third parties;

(iii) are NOT used to improve language models deployed by Kelsen or any third parties;

(iv) are NOT used to improve products or services provided by Kelsen or third parties;

All data is encrypted in transit and at rest in our system.

Kelsen encrypts all data in transit via SSL/TLS (Transport Layer Security) with the 256-bit AES (Advanced Encryption Standard) protocol, meeting industry standards for externally-facing systems.

AES 256-bit encryption with a rotational KMS (Key Management Service) is used to protect data at rest.

Encryption keys, including the right to revoke said keys, may be assigned to the company-designated administrators.

keys will be stored in an encrypted backup vault.

Communications with language models hosted on Microsoft Azure Cognitive Services (Azure) are encrypted and decrypted using FIPS 140-2 compliant 256-bit AES encryption.

Kelsen Draft is a cloud-based application.

User data is hosted and stored in Amazon Web Services (AWS) servers located in or near to the user’s physical location, in compliance with national data residency regulations, such as GDPR, PIPEDA, LGPD, etc.

For high-volume clients, cloud infrastructure and hosting may be changed to Microsoft Azure and/or hosted on the client’s own cloud infrastructure, on a case-by-case basis, to accommodate specific requirements and data management policies.

Sign up to our waitlist
and get early access
to Kelsen DraftTM

Starting on the 28th of August, 2023, users will be gradually onboarded to ensure capacity and the best possible user experience.

If you are interested in revolutionizing the legal drafting experience and becoming an early user, please join our waitlist

Expect to hear back from us soon!