Private AI for legal work. Client files stay in your firm's own workspace.

What your team can do

• Legal research with cited articles

  Ask a specialist assistant about the law. It works from your firm's reference library, which can include Vietnamese legislation, and cites the article behind each answer.

• Questions on contracts and case files

  Upload a contract or a case file and ask about it. The source panel shows the passage behind each answer.

• Notes from client meetings

  Upload a recording of a client meeting. It is transcribed on the server, then drafted into notes for a lawyer to edit and confirm.

• Redaction before documents go out

  The assistant finds names, ID numbers and other personal details. A person reviews each one, then exports a redacted copy.

• A channel for each matter

  Colleagues discuss a matter in a team channel and bring an assistant into the thread by typing @ and its name.

• A morning bulletin

  Start the day with a bulletin drawn from the public legal websites your team follows.

An example

A lawyer asks the land law assistant how many years are left on Mr. A's land. The assistant takes the term of use from the land use right certificate in Mr. A's case file, applies the Land Law 2024, Article 172, on land used for a definite term, and cites both sources. The answer combines the law with your client's own document, which a web search cannot do. The lawyer opens each cited passage in the source panel, checks the wording, and only then uses the answer.

How your data is protected

• Processed on the server. Documents, chats and recordings are processed on the server that runs your workspace, by AI models that run on that server. The exceptions are the outside connections described below.
• Your firm's own workspace. Your firm gets its own workspace, with its own application instance, database, document libraries and user accounts. Your documents are not mixed with another organisation's. This applies on the pilot server too, which can host other organisations' pilots, each in its own separate workspace.
• Your administrator controls outside connections. Web search and outside AI are switches, and we agree with you during setup which ones are on. With web search on, search queries made from a user's question are sent to a web search service to fetch public pages. Documents are not sent, but a query can contain words from the question, such as a name. Outside AI is off unless your firm chooses it, and only the accounts your administrator allows can use it. Before a message goes to outside AI, names, ID numbers and other personal details are automatically replaced with placeholders. What goes out is the conversation, including any document passages it contains, after this masking; the real values are put back into the answer on the server. The masking looks for personal details, not figures, and it catches common forms but is not perfect, so we agree rules with you on what staff may send.
• Who can access it. Each person signs in with their own account, and your firm's administrator decides who can use which assistants and features. In a workspace we host for you, and on the pilot server during a pilot, OpenExpertsAI's administrators can access the server to maintain and support it. Hosted workspaces are reached over HTTPS through a tunnel service; when yours is reached through Cloudflare, Cloudflare's network decrypts and re-encrypts the traffic on its way to the server, possibly outside Vietnam. On a server in your own office, your firm controls access.
• No training on your data. OpenExpertsAI does not use your documents or chats to train AI models.

Read more about security and data handling

Where a person stays in charge

Answers can be wrong. That is why each answer points to its source: the lawyer opens the cited article or passage and checks it before the answer is used.

The workspace does not give legal advice on its own and does not replace a lawyer's sign-off. Meeting notes stay drafts until a lawyer edits and confirms them, and a person reviews every detail before a redacted copy is exported.

Try it for a month

1. A short call about the work that takes your team the most time and the data that needs protecting.
2. We set up a private workspace for your firm, load your documents and add accounts for your team.
3. Your team uses it on real work for one month. During the pilot, the workspace runs on a server OpenExpertsAI operates.
4. You choose where it runs: a workspace we host for you, or a server in your own office.

If you stop after the pilot, we delete your workspace and data and confirm it in writing. See how a pilot works

See also

• For health clinics
• For laboratories
• For research teams
• FAQ