SharePoint is usually the largest and least searchable thing an organisation owns: an intranet, a dozen team sites, document libraries going back years, and a policy page that three departments each keep their own copy of. People stop looking and ask a colleague instead, which is how out-of-date answers spread. The SharePoint connector is part of askFinz Knowledge, which is still rolling out; here is what it will do, and what it will not.
Ask the intranet a question and get one answer
Instead of a results page across four team sites, get the answer with the page or document it came from named, so you can check it.
Search libraries and pages together
Document libraries and site pages hold different halves of the same subject. Reading both means the policy and the form that implements it come back to the same question.
Keep site permissions exactly as they are
Connecting a site does not widen access. Everyone keeps the reach they already had, per site and per library.
What is copied, and what is not
What crosses, and what stays in SharePoint
Read
site pages and document text from the sites and libraries you select.
Written back
nonenothing. No pages, documents, lists or metadata are changed.
Stored
a searchable copy of that text, plus a link back to the page or file.
Never read
sites you did not select, and anything the reader cannot already open.
What you will be granting
Read-only access to the sites and libraries an administrator approves, honouring the permissions Microsoft 365 already enforces on each one.
Setting it up
Planned — not available yetWhat connecting it will look like once the connector arrives.
- 01
An administrator approves the askFinz app for your tenant.
- 02
Select the sites and libraries to include. Unselected sites are never requested.
- 03
Decide whether to include lists as well as documents and pages.
- 04
Set the refresh interval.
Limits, honestly
- One-way and read-only. SharePoint stays the system of record.
- Answers reflect the last refresh, not the edit made a minute ago.
- Version history, the recycle bin and workflow history are out of scope.
- Scanned PDFs are read only where they already carry a text layer.
- Very large libraries index faster if you exclude archive folders.