Forage Questions and Answers
6 min read · Last updated · Page version 15
Does Forage delete anything?
No. Forage does not delete anything. It only reads SharePoint, the archive and Squirrel's records.
In Settings there is one action that removes data, and it is worth being precise about. Delete them permanently applies to a document type an administrator has switched off. It removes Forage's copy of the text, its search entries and its record that those documents were examined. The documents in SharePoint and in the archive are untouched. A reason is required and is recorded.
Where is our content kept, and does any of it leave?
Forage keeps the text it reads, and its search index of that text, inside your own deployment. No document content is sent anywhere outside it, and none goes to any external AI service: Forage AI, the one AI model Forage uses, runs inside your own deployment.
Each customer has its own deployment, with its own database and its own search index. There is no shared index and no path for one customer's query to reach another customer's data.
How does Forage decide what a document contains?
With transparent rules you write and can read: phrases, patterns, checksum validation and proximity. Nothing is inferred.
Every finding keeps the words that produced it, so you can see exactly why a document was labelled, and the same document always gives the same result. Scanned pages are read by optical character recognition that runs inside the deployment.
Where you ask for them, Forage AI, which runs inside your own deployment, can also suggest labels for the kinds of record it finds in the sites you choose. It suggests; it does not decide. Nothing is labelled until a person accepts a suggestion and switches its rule on.
Does Forage use AI?
In one place, and it stays inside. Forage sends no document content to any external AI service. Its one AI model, Forage AI, runs inside your own deployment and only suggests labels, when an administrator asks for them. Every label is applied by a transparent rule that a person has switched on, and Forage does not train a model on your content. No AI model reads, describes or summarises documents for users, and no AI decides what a document contains or which label it gets.
Do we need Squirrel?
Yes. Forage requires Squirrel and builds its picture of the estate from Squirrel's record. A site or file Squirrel does not record is not seen by Forage, and Forage is only as current as that record.
What can Forage read, and what can it not?
It reads PDF; Word, Excel and PowerPoint files including templates and macro-enabled files; older Office formats; Outlook and standard email messages; OpenDocument files, as LibreOffice and OpenOffice save them; the words on drawings (.dwg) saved in any version of the format from 1984 on and on exchange drawings (.dxf) (their text, title block values and notes, and the properties where the version keeps them, not the drawing itself); and rich text, plain text, CSV, HTML and XML.
It does not read video or audio, binary Excel workbooks, compressed folders, or design files other than the drawings above. A drawing (.dwg) saved in one of the first versions of the format, from 1982 and 1983, is listed and findable by its name and folder, shown as "Not read yet: drawing version", and counted apart from the files that could not be read. It never removes or bypasses a password or encryption, so protected files are recorded as protected rather than read. Words in pictures inside Office documents and on PDF pages are read with optical character recognition, in the same pass as the rest of the document, so its typed text and the words in its pictures become searchable together.
Older Word and PowerPoint files are read for their text but not their layout. Email attachments are listed by name rather than read inside the message.
See limitations for the full picture.
Can it read scanned documents, and in which languages?
Yes. Scanned PDFs and image files are read with optical character recognition, so scanned contracts and forms become searchable.
Forage recognises the script and orientation of each scanned page and reads it accordingly, so it also reads accented Latin-script text, Cyrillic-script text and rotated pages. Documents already read are not read again automatically. Handwriting is read poorly or not at all, and a page that mixes scripts is read poorly, with part of it lost.
Does it work with our Purview retention and sensitivity labels?
Search results show the retention label and the sensitivity label that Squirrel recorded for each file.
Forage never applies, changes or removes a label. It does not act on retention labels, and it does not use sensitivity labels in rules or as a search filter.
Who can use it, and who sees search results?
The Records section is used by Squirrel portal administrators. There are no narrower roles today, so anyone who can use the Records section can use every page in it, including search across all content, the rules and the settings.
Search results are not limited to what each person could open in SharePoint. Roles narrower than Full Administrator, and limiting a search to a case, are not yet available.
How does Forage keep up with changes?
Forage asks Squirrel what was added, changed or deleted, on a regular sweep rather than instantly. When a file is reported as changed it compares fingerprints and reads the file again only if the content really changed.
It can be no more current than Squirrel's own record. A file moved into a site without being changed may not be noticed by the sweep; a full re-check of the estate finds it, and is run deliberately.
How long will it take to read our estate?
It depends on the size of the estate and the deployment.
The Dashboard and Coverage pages show progress, and an estimated time to finish at the rate actually achieved. For an estimate against your own estate, ask SmiKar.
How do we find out more?
Contact sales@smikar.com.