From the target’s own pitch deck to a scored readout.

The pitch deck first. Zoe turns it into a Claim Ledger: a list of every claim the deck makes, one per row. Each claim is then checked against the systems the target connects. Other data-room files (PDFs or spreadsheets) are optional extra evidence.

Where the deck and the company’s systems disagree, or where the systems say nothing, Zoe writes the questions. You hold one call with the founder and upload the transcript. Zoe marks each answer as answered, dodged, or contradicted by the evidence, and the results feed the readout.

The Readout Package holds the Zoe Score across nine dimensions of operating health, the findings and how to read them, an IC memo written for your investment committee, a signed opinion when the evidence is strong enough, and an evidence appendix. You can also export the files you need for your IC pack.

Zoe runs on partial data. Any one connected system produces a useful readout, and each extra system sharpens the dimensions it feeds. A missing source is never hidden: the dimensions that depend on it are marked as reduced coverage, and the overall score is reported with its coverage. The Zoe Score carries a confidence percentage and a coverage tier, and Zoe signs the opinion only when confidence clears the bar. Gaps in the Claim Ledger also become questions for the Founder Call.

Each case runs in its own isolated workspace with its own encryption key, and data is encrypted in transit and at rest. The target accepts a DPA (data processing agreement) before connecting anything, and the acceptance is recorded. Data pulled from connected systems is used for the check and then discarded by default. When you close the case you choose: seal it, and the case data is destroyed at 30 days with a destruction certificate, or on the Portfolio package keep it open and monitor. See /security for the detail on each connector.

No, and that is by design. Zoe sends the target a secure link. Whoever holds the keys there (often the CEO, CFO or an admin) accepts the DPA and connects each system read-only, logged in as themselves. Read-only means Zoe can look, never change anything, and the target can switch it off. You never hold a password. Most investors run Zoe as a condition of moving to a letter of intent, the same way a quality-of-earnings review is.

Connected systems are read for patterns, not paragraphs: who communicates with whom, how often, how fast. Message bodies are never stored. Source code is outside what Zoe is granted. The documents you add to the case (the pitch deck, any data-room files) and the founder-call transcript are read in full, because that is what the claims are checked against. Every connector’s exact boundary is listed on /security.

About 90 days of history in its systems. Zoe needs enough activity to read patterns reliably. Younger than that and the confidence on the score gets too low to act on.

Yes. When you close the case you either seal it or, on the Portfolio package, keep the target’s connections live and monitor. Investors typically run it before the letter of intent, again at close, and quarterly after close. Operators run it quarterly to see whether their fixes are landing.