# An AI research pack for asset managers and investment teams Canonical: https://opendataroom.com/guides/asset-manager-research-pack Updated: 2026-10-17 A useful research handover contains the evidence needed for a defined question, a source register and clear dates. A permissioned MCP connection can let an approved AI app consult that pack. It does not replace an investment process, regulated recordkeeping or a full diligence data room. ## How OpenDataRoom helps Market: Asset managers and internal investment committees Committee discussion can begin with source-linked questions rather than rebuilding the research context. 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. - [Reusable private packs](/guides/control-data-access-ai): Keep the selected documents together for repeat questions and later reviews, within the displayed retention period. - [Source access for your AI](/guides/ai-document-connection): Let a compatible AI list, search and read the supplied text. Ask it to cite the file and passage so you can check the answer. - [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. ### Example Fictional example: proposal: proceed subject to a revised downside case and confirmation of financing terms. ### Workflow impact Committee discussion can begin with source-linked questions rather than rebuilding the research context. ### Bring these documents - IC memo draft.pdf - Scenario assumptions.xlsx - Decision questions.docx ### Prompt for your own compatible AI Using only this approved pack, committee discussion can begin with source-linked questions rather than rebuilding the research context. Start with this source question: What must be resolved before this recommendation becomes a decision? 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? Committee discussion can begin with source-linked questions rather than rebuilding the research context. The practical task is to committee discussion can begin with source-linked questions rather than rebuilding the research context. ### Which documents should I include? For the example on this page, start with IC memo draft.pdf, Scenario assumptions.xlsx, Decision questions.docx. 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. ### Can the ledger tell me whether an investor intends to proceed? It can show the tool requests received through an authorised connection, the source references requested and the response preparation outcomes. Those records can inform a useful clarification or follow-up. They do not prove that the investor personally read a result, that an AI relied on it, or that an investment decision was made. An AI app may issue several requests automatically. ### 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. Define the decision and permitted audience 2. Separate evidence, calculations and assumptions 3. Retain source dates and unresolved conflicts 4. Use an approved receiving AI environment 5. Keep authoritative regulated records in qualified systems ## Fictional example documents These are invented teaching documents, not customer evidence. ### IC memo draft.pdf Fictional proposal: proceed subject to a revised downside case and confirmation of financing terms. ### Scenario assumptions.xlsx The example downside assumes a six-month delay. Working-capital treatment is not specified. ### Decision questions.docx No committee vote is recorded. Open questions concern liquidity and financing availability. ## A source question What must be resolved before this recommendation becomes a decision? Illustrative answer: The downside and working-capital treatment need clarification, and financing needs confirmation. The memo is a proposal; no vote or approval is recorded. ## Organise the decision, not just the folders For an illustrative property review, separate the original asset brief, market evidence and analyst assumptions. Identify the question, the period covered and the source of each material figure. Keep a later analysis distinct from its original sources. ## Preserve uncertainty A modelled valuation is not an observed transaction price. A marketing statement is not independent evidence. Include unresolved conflicts and missing inputs so an AI-assisted review can identify gaps rather than silently fill them. ## Choose a deliberately limited disclosure Use a separate pack for each permitted review scope. Do not include raw client positions, personal investor records or material outside that recipient’s authority merely because it is in the same project folder. ## Use source references in the review Ask the AI to identify the file and passage behind a finding. Compare that answer with the request ledger where useful, while remembering that a prepared server response does not prove the AI used it. Original file versions and request metadata serve different purposes. ## Know when you need another system Legal holds, formal diligence Q&A, document-level entitlement management and regulatory archives are not supplied by this service. The private library and each time-limited hosted copy have separate retention deadlines. ## Sources and further reading ## Related workflows - https://opendataroom.com/guides/fund-update-ai - https://opendataroom.com/guides/data-sovereignty-ai-access - https://opendataroom.com/guides/control-data-access-ai 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=investment-committee-evidence-pack