# Control what AI can access in your files Canonical: https://opendataroom.com/guides/control-data-access-ai Updated: 2026-10-17 Control starts with the material you make available. Share a defined file pack, authorise its connection and choose when access ends. Review the requests received by the service. An access limit stops future retrieval; it cannot recall content an AI has already received. ## How OpenDataRoom helps Market: Companies, advisers and pack owners The owner chooses the material and future access window rather than granting access to a whole archive. Keep source documents organised in drops, like folders, and select named packs for each audience. OpenDataRoom manages access and request records; the recipient uses their own AI for analysis. Current AI tools return extracted text, not complete original files. - [Named recipients and separate packs](/guides/separate-packs-per-audience): Choose who can connect. Prepare separate packs when people are allowed to see different documents. - [Access deadlines and revocation](/guides/time-limited-ai-access): Choose a review window and stop future requests when it ends. Previously retrieved copies cannot be recalled. - [Reusable private packs](/guides/control-data-access-ai): Keep the selected documents together for repeat questions and later reviews, within the displayed retention period. ### Example Fictional example: An introduction deck is approved for prospects. ### Workflow impact The owner chooses the material and future access window rather than granting access to a whole archive. ### Bring these documents - Prospect disclosure approval.md - Adviser disclosure approval.md ### Prompt for your own compatible AI Using only this approved pack, the owner chooses the material and future access window rather than granting access to a whole archive. Start with this source question: Should both files go in the same prospect pack? Cite the file and passage. Distinguish supplied facts, assumptions, missing evidence and contrary evidence. Do not infer human reading or investment intent from request records. Check the sources and the receiving AI app before using the pack for the real assignment. ## Frequently asked questions ### What would this change in my workflow? The owner chooses the material and future access window rather than granting access to a whole archive. The practical task is to the owner chooses the material and future access window rather than granting access to a whole archive. ### Which documents should I include? For the example on this page, start with Prospect disclosure approval.md, Adviser disclosure approval.md. Use the approved versions relevant to the task and include source dates, definitions and any known gaps. Review the prepared text and disclosure scope before sharing. The fictional examples illustrate the structure; OpenDataRoom does not supply or verify your underlying research. ### Does OpenDataRoom perform or verify this work for me? Your own compatible AI works from the material you choose. For this task—the owner chooses the material and future access window rather than granting access to a whole archive—you or the responsible reviewer must check the answer against the originals. OpenDataRoom provides document access and request records; it does not certify the evidence, perform an independent review or approve the result. ### How does the recipient connect, and who gets access? Choose your own AI or invite the intended email recipient. For a private invitation, the recipient verifies the authorised email and completes the required approval flow, then adds the connection in a compatible AI app’s settings. Forwarding an invitation alone does not authorise a different email. Permission covers the selected pack; create separate packs when audiences may see different documents. ### Can I keep the files and end someone’s access? Your wallet contains source drops, like folders. Each named pack shares selected files or passages from one drop. The source drop and its access packs have separate deadlines. You can keep the source until its displayed retention deadline while ending a recipient’s future access. Choose a sharing window, revoke it earlier when needed, and approve an extension deliberately. Expiry cannot recall material that an AI app or recipient has already retrieved. ### What happens when I update or remove a file? After you review and accept a drop update, fresh authorised requests receive the current versions of files already selected for their packs. This does not force an AI to fetch the files again or refresh its existing chat context. New files do not join those packs automatically. Review changed selected passages explicitly. Removing a file or its permission stops future retrieval, and access-change notices are queued for affected recipients. Provider acceptance is not proof of inbox delivery. This cannot erase content already retrieved. ### What if my files or AI app are not supported? Check the compatibility guide and try the public service-information sample first. An app must support the required MCP connection and authorisation; pasting a URL into ordinary chat does not install it. Use supported text-based files and inspect the preparation report. Originals are retained in encrypted storage, but the current AI tools return extracted text, not complete original files. Charts, images and layout are not faithfully delivered by those tools. Image-only scans and standalone images are refused; no OCR, audio transcription or spreadsheet recalculation is provided. Current pilot limits are listed on the pricing page. ### What information is recorded about use of the pack? The ledger records requests received by the service, authorised connection references, requested source information and preparation outcomes. Recipients can also deliberately submit a request, comment or note after approving the exact text. The owner sees that message, the verified connection identity and time in Recipient inbox for up to 90 days, unless deleted sooner. Received does not mean read or answered; no agent or automatic research is started. It does not record the entire AI conversation. Search text is supplied by the AI and may differ from the human question. An AI can reuse retrieved material without making another request. Literal search can miss relevant material; neither a search nor a file request proves that the AI reviewed the entire pack. Owners can investigate no-match searches before deciding whether to clarify wording, repair extraction or add information. A no-match result alone is not proof that a document is missing. ### Who can read my files in the hosted connection? Private-library file names and contents are encrypted in the browser with your wallet key. A hosted AI connection uses a separate access copy that you approve and that the service can decrypt for authorised retrieval. The receiving AI gets the content it retrieves and applies its own data policies. An optional desktop connector can decrypt locally, but it requires installation and is not a universal mobile connection. Review the security and compatibility pages before choosing a route. ## Before you share 1. Which pack is needed for this task? 2. Who may connect, and through which approved app? 3. When should access end? 4. What does the recipient’s AI retain? 5. Which request records do you need to keep? ## Fictional example documents These are invented teaching documents, not customer evidence. ### Prospect disclosure approval.md An introduction deck is approved for prospects. ### Adviser disclosure approval.md A detailed financial note is approved only for appointed advisers. ## A source question Should both files go in the same prospect pack? Illustrative answer: No. Create separate packs for the different disclosure scopes. ## Start with a pack, not your whole archive Choose the files needed for one task. If you want different people to see different documents, prepare separate packs. In the current OpenDataRoom service, permission applies to the pack; there is no per-document permission editor inside a pack. ## Give the connection a job and a window For example, share an approved investment memo and financials with a prospective co-investor for a review this week. Keep unrelated deals and restricted documents out of that pack. A signed-in member can connect their own AI; external recipient verification also needs the email service; delivery and client compatibility must be checked for the receiving environment. ## Change assistants without changing the principle The private library separates saved files from your choice of AI and from each hosted access window. It has a displayed retention deadline, so it is not an indefinite archive. In either case, use a compatible remote MCP app and authorise only the material required. ## Know where control ends The receiving AI processes the retrieved content under its own service terms and configuration. OpenDataRoom does not see the complete conversation, cannot revoke copies already received and does not guarantee that a response influenced the AI’s answer. ## Sources and further reading ## Related workflows - https://opendataroom.com/guides/data-sovereignty-ai-access - https://opendataroom.com/guides/ai-document-connection - https://opendataroom.com/guides/time-limited-ai-access Admission is by invitation. Join the waiting list: https://opendataroom.com/signup Check compatibility and the separate public service-information sample: https://opendataroom.com/compatibility ## Try the fictional example https://opendataroom.com/example-demo.html?example=separate-packs-per-audience