SmiKar launches Forage to bring archived SharePoint data into AI search
The new tool allows organizations to query old, low-cost storage using Microsoft Copilot without moving files back to active SharePoint sites.
The short version
- Forage creates a single searchable index for both live SharePoint documents and archived content.
- Users can ask natural language questions to AI, which provides answers with direct citations to source files.
- The tool integrates with Microsoft Copilot, allowing it to access archived data via secure authentication.
- It includes automated classification to identify sensitive data like bank details or health information.
- All AI processing happens within a dedicated deployment, meaning data is not sent to external AI services.
Why it matters
Companies often move old files to cheaper storage to save money, but this usually makes the data invisible to search tools. This tool lets businesses keep the cost savings of archiving while still being able to find and analyze that old data using modern AI.
Bridging the archive gap
Organizations often face a difficult choice when managing large amounts of data in Microsoft 365. They can keep everything in active SharePoint Online storage, which is expensive, or they can move inactive files to lower-cost Azure Blob Storage to save money. However, moving files to these archives typically makes them invisible to standard enterprise search tools and AI assistants.
SmiKar Software has launched Forage for Squirrel to solve this specific problem. Forage acts as a bridge that connects live SharePoint documents with content already moved to the Squirrel archive. This allows companies to maintain their storage savings without losing the ability to discover or interact with their historical information.
The platform creates a unified search experience that looks at the actual content of documents rather than just file names or metadata. It supports a wide variety of formats, including Word, Excel, PowerPoint, and PDFs. It even uses optical character recognition (OCR) to make scanned images and pictures within documents searchable for the first time.
AI-powered discovery and citations
One of the primary features of Forage is its ability to answer complex questions using natural language. Instead of manually browsing through thousands of files, authorized administrators can ask specific questions about supplier agreements, termination conditions, or project details. The system searches the relevant content and generates a structured response based on the findings.
To ensure accuracy, every statement provided by the AI includes a specific file number. These citations link directly to the original source documents, allowing users to verify the information immediately. For very large investigations, the system can analyze up to 5,000 matching documents at once, running the process in the background so users can continue their work.
The tool also provides a way to export these AI-generated analyses as PDF reports or CSV files. This makes it easier for teams to share findings with stakeholders who may not have direct access to the archive. By consolidating thousands of files into a single referenced response, the tool turns raw data into actionable intelligence.
Expanding Microsoft Copilot
As more companies adopt Microsoft Copilot, they need to ensure the AI has access to the full breadth of their institutional knowledge. Forage for Copilot specifically extends the reach of the AI assistant beyond what is stored in live SharePoint sites. It allows Copilot to retrieve information from archived documents and scanned files that would otherwise be unreachable.
The integration works by using Forage as an information retrieval layer. When a user asks a question through Copilot or Microsoft Teams, Forage identifies the relevant archived documents and supplies the text to the AI. This ensures that the AI's answers are informed by the company's entire history, not just its most recent files.
Security remains a core component of this connection. The system uses secure Microsoft authentication to verify permissions before any content is shared. Only employees with the correct permissions can see specific documents, and every search or retrieval is recorded in a tamper-resistant audit trail to maintain accountability.
Automated data classification
Managing data privacy requires knowing where sensitive information lives across an entire organization. Forage includes tools to automatically identify and categorize data such as bank account details, tax numbers, and health-related information. It uses configurable rules and text patterns to find these items in both live and archived documents.
The system also offers AI-assisted classification to help teams discover patterns. It can scan SharePoint sites and suggest categories, such as identifying a collection of invoices or technical reports. However, these are only recommendations; administrators must review and approve the suggestions before any classifications are officially applied.
For compliance teams, the tool also features a 'Files to Protect' capability. This allows administrators to select a specific sensitivity label and find documents that contain similar information but are currently missing a label. This helps ensure that sensitive data remains protected even as it moves through different stages of the document lifecycle.
Privacy and deployment
A major concern for many enterprises is where their data goes when it is processed by an AI. SmiKar designed Forage to operate within a dedicated deployment for each customer. This means each organization has its own separate database and search index, ensuring complete data isolation from other users.
The architecture is built so that archived documents stay in the customer's own Azure Blob Storage. When the AI performs an analysis or a search, the processing happens within the dedicated Forage environment rather than being sent to an external AI service. This design helps organizations maintain data sovereignty while still benefiting from advanced machine learning capabilities.
Forage is integrated directly into the existing Squirrel web portal, meaning there is no need for a separate application. It detects changes to documents incrementally to keep the search index current without needing to crawl the entire SharePoint environment repeatedly. This approach allows for a more efficient way to manage Microsoft 365 data without increasing storage consumption.
What to watch
- How many other third-party tools will offer similar 'archive-to-AI' bridges for Microsoft 365?
- How organizations will balance the use of AI-assisted classification with human oversight for regulatory compliance.
Try it
Check your organization's SharePoint archive to see if your old files are currently searchable by your standard search bar.
Sources and links
- OfficialSharePoint Online archiving platform smikar.com
- Officialsmikar.com/squirrel/forage/ smikar.com
- ReportingEIN Presswire: the article we sourced
First reported by EIN Presswire. Written by the SI Agent News Desk from the reporting above.Written with AI from the source above. Every number is checked against the source. Spot a mistake? Corrections.
Liked it? Say why
Add a line for other readers.
No account needed. We never show your email. Comments with links, ads or abuse are held and not shown. Your comment shows after a quick check.