Document vault
Policies, quotes, applications, ACORDs, certificates, loss runs, carrier correspondence and proposals, filed against the client and policy they belong to. Full-text search, folders, versions and permissions.
← All platform
Vault · PrismArchive · extraction
Documents including the twenty years of paper in the filing cabinet.
Every agency has two document problems. The live one, where today's certificate needs to be findable in five seconds. And the buried one, where two decades of scanned client files sit in a folder as thousand-page PDFs that nobody can search. PrismAMS handles both, and it does the second one without asking you to hand us your client files.
- Page-level
- OCR incl. handwriting
- Auto-split
- Stacks into documents
- Zero-copy
- SharePoint source mode
- REST
- Extraction leaves the app
What's included
Everything in documents, shipped today.
PrismArchive bulk OCR
AIPoint it at the scanned paper. It reads every page natively, including handwriting, and returns searchable text plus structured fields.
Document boundary detection
AIThe hard part of scanned paper is not OCR, it is that a scanned client file is a continuous stack of many separate documents. PrismArchive finds the boundaries and splits one nineteen-page scan back into the fourteen or sixteen real documents it contained.
Entity index
Search the archive by person, email, phone or date. Emails, phones and dates are extracted deterministically rather than by a model, so they are exact and cost nothing to run.
Document intelligence & extraction
AIClassification and structured field extraction across document types, with the schema shaped per document rather than one generic blob.
Model comparison with real cost metering
The same file can be run through different models and diffed side by side, with the actual token spend recorded per run. You see what a given accuracy level really costs before committing to it at volume.
Extraction over REST
The structured output leaves the platform over a tenant-scoped, key-authenticated REST API. For an integrator that JSON is the product, so it is treated as a contract rather than an internal detail.
eSign & PDF tools
Send for signature, prepare fields, split, merge and edit PDFs without leaving the system or buying a second product for it.
How it works
Four steps, no export in the middle.
- 01
Your scanner writes to your own folder
Staff scan into a folder in your SharePoint, exactly as they do now. Nothing about the front of the process changes.
- 02
PrismArchive reads it where it sits
The file is read transiently over Microsoft Graph, scoped to that one site. We never copy the PDF into our storage.
- 03
Only the index is kept
We persist the OCR text, the extracted fields, the entities and a pointer back to the file where it already lives. The document itself never moves.
- 04
Your staff search the index
Find the document by person, phone, date or content, then open the original in place in your own SharePoint.
Why it's different
Your client files never enter our storage.
- Access is granted per site, not per tenant. We can open the one scan folder you point us at and nothing else in your Microsoft estate.
- The PDF is read in memory and never copied. If you switch the connection off, your documents are exactly where they always were.
- What we hold is an index and a pointer, which means offboarding is not a data-extraction project.
- A re-scan of the same file is detected and does not duplicate, so the folder can stay a working folder.
- The alternative on offer from most vendors is uploading your client files into their tenant. That is a different risk posture, and it is worth asking about.
FAQ
Common questions.
+What does my Microsoft admin actually have to grant?
An app registration in your tenant with the Graph application permission Sites.Selected, admin-consented, and then read granted on the single scan site. That permission model means the app can open that one site and has no path to anything else.
+Does this work if we do not use SharePoint?
Yes. Direct upload into the vault is the original path and is fully supported. The SharePoint mode exists for agencies that do not want their client files leaving their own tenant.
+How accurate is it on bad scans and handwriting?
Pages are read natively rather than rasterized, which holds up better on poor scans, and handwriting is read rather than skipped. Because the model is a configurable dimension with per-run cost metering, you can measure accuracy against cost on your own documents before rolling it out.
+It split one file into fifteen documents. Is that a bug?
Usually not. A scanned client file genuinely is a stack of many separate documents, most of them one page. Over-splitting looks wrong until you check it against the page images, and there is a comparison view for exactly that.
See PrismAMS for your agency.
30 minutes. We'll walk through your real workflows in a tenant set up for you. No slideware.