How Nutshell Works

Nutshell AI runs after Squirrel's normal archive process. It does not change how Squirrel archives — only what is left behind in SharePoint after the archive completes. This article walks the pipeline step by step so you know where each part fits.

The five-step pipeline

1. Archive. Squirrel moves a document from SharePoint Online to Azure Blob Storage in your own Azure subscription, in line with your archive policy. File metadata is preserved.
2. Extract. If Nutshell is enabled, the archived document's text content is extracted for processing.
3. Summarise. The content is passed through Nutshell's AI engine using the configured mode and temperature, producing a structured summary.
4. Store. The summary is written into the stub file that Squirrel leaves in SharePoint in place of the original, and a copy is preserved alongside the archive in Azure Blob Storage.
5. Discover. SharePoint Search and Microsoft Copilot index the updated stub, so the archived document surfaces in relevant search results and Copilot responses.

If a user clicks the stub, the normal Squirrel restore flow brings the original document back. The summary just makes sure they can find the right document to ask for.

Retrospective summarisation

Because summarisation runs after archive, Nutshell can be turned on or off at any time. Enabling it later does not lock you out of older content: previously archived documents can be queued for bulk summarisation, so historical archives are made just as discoverable as anything archived going forward.

This is also useful when you want to change mode or temperature settings — you can re-run summarisation over a subset of past archives to test the effect before rolling the new setting out across the tenant.

Live view during processing

Every document currently being summarised is visible on the Active AI Summarization Jobs page in the Squirrel admin portal. The view shows filename, originating site, current state (Downloading, PendingAI, Processing), file size, and a per-file progress bar — so you can watch a bulk pass complete in real time.

Where the summary ends up

Two places:

• In the SharePoint stub — this is what SharePoint Search indexes and what Copilot reads. The summary is written into the stub's content so it looks like ordinary document text to Microsoft's indexing services.
• Alongside the archive in Azure Blob Storage — kept as a companion file so the summary survives even if the SharePoint stub is later deleted or replaced.

Both copies remain in your own Azure subscription. Nothing about Nutshell requires customer data to leave your tenant.

See also

• Summarisation modes — Brief, Standard, and Detailed.
• Temperature settings — creativity vs fidelity.
• Supported file types — what Nutshell can process.
• Stub files: before and after — what the stub actually carries.
• Monitoring active summarisation jobs — the live view.

Need help? support@smikar.com.