Your files, put to work

Prepare a startup file pack for an investor’s AI

Start with the question the investor needs to answer, then share the smallest useful evidence pack.

A pitch deck, selected supporting figures and a dated assumptions note can be more useful than an unstructured archive. The recipient chooses their AI and the analysis they want to run.

Updated 17 October 2026 · OpenDataRoom · Fictional worked example

Your workflow at a glance

Who it’s for
Funded startups raising Series A or later
The task
The founder prepares the evidence once for the intended review and can respond to requests with a clearer source trail
Bring these materials
Series A deck.pdfCustomer metric definitions.xlsxDiligence questions.docx

A fictional situation Fictional example: Cedar Studio describes 120 accounts as active at quarter end.

Before you share

  1. Match the pack to the fundraising stage
  2. Date the deck and supporting figures
  3. State assumptions beside the calculations
  4. Choose recipients and an access deadline
  5. Keep confidential diligence separate

How OpenDataRoom helps

The difference in your workflow

The founder prepares the evidence once for the intended review and can respond to requests with a clearer source trail.

Keep the source documents organised in a drop, like a folder. Create named packs for different audiences, approve their access and let each recipient use their own AI. OpenDataRoom manages access and request records; the recipient’s AI performs the analysis.

A fictional example, shown one step at a time. No files are uploaded and no email or AI call is made.

01Choose the useful files

Start with the evidence for this question.

Prepare the approved versions of Series A deck.pdf, Customer metric definitions.xlsx, Diligence questions.docx. Check the readable text and leave unrelated material out.

Bring these documents
Series A deck.pdf
Customer metric definitions.xlsx
Diligence questions.docx

Selected for this example · 3 documents

02Choose who gets access

Your pack. Your permission.

Use it with your own AI or invite a named recipient. Set a useful deadline. If people may see different documents, prepare separate packs.

Your sharing choices
Recipient
alex@example.com
Example access window
24 hours
Scope
Only this selected pack

Verify email · approve access

Illustrative settings. No invitation is sent.

03Connect the recipient’s AI

Connect once. Choose approved packs.

Add OpenDataRoom in a compatible AI app’s connector settings and complete authorisation. A reusable connection lists only the packs you explicitly approve. Sending a URL into ordinary chat does not install the connection.

In a compatible AI app
OpenDataRoomYour AI

Example connection address

https://example.invalid/mcp/your-pack
  1. Open connector settings.
  2. Add the real address from your pack.
  3. Complete authorisation.

The address shown here is deliberately inactive.

04Ask the question

Let the source material do useful work.

The recipient decides what to ask. Their AI can list, search and read the approved text; OpenDataRoom supplies access, not the AI model. The current tools return extracted text, not complete original files. Check the preparation report for material they cannot represent.

A question worth asking

Are all 120 active accounts paying customers?

Your AI consults the authorised sources.
Your ready-to-use prompt

05Check the answer

An answer you can trace back.

Ask for the source file and passage. Compare the result with the originals and keep assumptions or missing evidence visible.

Illustrative answer · not generated live

No. The example defines 90 paying accounts and 30 free trials. Keep the distinction in the review and request retention cohorts before drawing a growth conclusion.

Open the source. Check the wording, date and conditions.

06See what was requested

A clearer handover and follow-up.

Review the requests received through the authorised connection. Investigate gaps, offer a clarification or end future access when the task is finished.

Fictional request record
List the selected filesSelected pack
Prepared
Read a source excerptSeries A deck.pdf
Prepared

The record shows requests and prepared responses. It does not show the full chat or prove someone read an answer.

Look inside the example Fictional

These are invented teaching documents. The example demonstrates a workflow, not customer evidence or a verified outcome.

Read the 3 example sources

Series A deck.pdf

Fictional Cedar Studio describes 120 accounts as active at quarter end.

Customer metric definitions.xlsx

Illustrative definitions: 90 paying accounts plus 30 free trials. The figures are supplied example values, not recalculated formulas.

Diligence questions.docx

Open issue: the deck does not distinguish paying accounts from trials. Retention cohorts and signed customer references are absent.

More context for this workflow

Separate the introduction from diligence

An initial conversation and a formal diligence process need different material. Keep personal records, confidential contracts and sensitive cap-table detail outside an introductory pack unless they are needed and authorised. There is no universal list every investor needs at every stage.

Make the deck checkable

For an illustrative market-sizing review, include the source behind your customer count, the geography, pricing assumptions and time period. Label TAM, SAM and SOM consistently. For a team discussion, include the relevant founder experience only when useful to that recipient. These are examples, not mandatory investor requirements.

Give the recipient useful questions

Try: “Which assumptions determine the obtainable market?” or “Which claims in this deck need stronger evidence?” Keep facts, estimates and scenarios distinct. OpenDataRoom supplies access to your files; it does not validate a forecast or produce investment advice.

Read activity without over-interpreting it

A search for TAM or a request for founder background is a server-visible event. It is not proof of investment intent, a personal reading session or a decision. AI tools can request content automatically. A request ledger and page-by-page pitch-deck viewing analytics measure different things.

Keep the handover proportionate

The service provides a private library and time-limited hosted MCP copies. It is not a complete transaction VDR. It does not provide investor CRM, NDA execution, electronic signatures or regulatory archiving. Verify the recipient’s AI environment before sharing sensitive business information.

The useful detail

Questions about this workflow

What to prepare, how access works and what to expect from the result.

What would this change in my workflow?

The founder prepares the evidence once for the intended review and can respond to requests with a clearer source trail. The practical task is to the founder prepares the evidence once for the intended review and can respond to requests with a clearer source trail.

Which documents should I include?

For the example on this page, start with Series A deck.pdf, Customer metric definitions.xlsx, Diligence 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.

Now it’s your turn

Try the whole journey.

Choose the example files and move through the connection, question, answer and ledger. The tour advances every four seconds; tap a step or Pause to take over.

No real upload, email or AI call is made. The connection in this fictional demo is inactive.

The six static steps and example sources above remain available if the interactive tour cannot load.

A real MCP connection

Ask your AI about OpenDataRoom.

Public information only. This connection cannot access customer files.

Opening this sample records a unique launch reference. Its requests, search text and document metadata are kept for 30 days for the OpenDataRoom operator. Anonymous means unidentified—not unlogged. Do not enter personal or confidential information.