5 Ways to Build Data Collections in Indago
What Are Collections in Indago?
In Indago, a collection serves as your curated data universe for intelligence analysis and reporting. Think of it as a controlled repository where you gather, organize, and validate all the sources, like documents, articles, and data, that will inform your analysis.
The critical principle underlying Indago's collection system is that the AI only analyzes what's inside your collection—it never browses the open internet or pulls in unreviewed sources. When the AI doesn't have to guess or reach outside its defined context for information, it stays grounded in your quality-controlled data inputs. This controlled environment dramatically reduces the risk of hallucinations, ensures source transparency, and gives analysts confidence that every insight in their reports can be traced back to verified materials. Because you control what goes into the collection, you control the quality and reliability of what comes out in your analysis.
To build effective collections that power accurate, actionable intelligence reports, Indago offers five distinct methods for bringing data into your workspace.
1. File Upload
File upload represents the most straightforward method for bringing existing documents into your Indago collection. This approach is ideal when you already possess relevant intelligence materials, research papers, reports, or proprietary data stored on your local systems. Indago supports a comprehensive range of file formats, including PDF documents, Microsoft Word files, PowerPoint presentations, Excel spreadsheets, various image formats, and JSON files.
The platform accommodates both individual file uploads and batch uploading capabilities, allowing you to efficiently transfer multiple documents simultaneously. Each upload session supports files up to 20 megabytes in total size, though you can perform unlimited upload sessions to build comprehensive collections. Importantly, there is no practical limit on the number of sources you can maintain within a single collection, enabling analysts to create extensive intelligence repositories that scale with their research needs.
File upload proves particularly valuable when working with proprietary research or specialized datasets that aren't available through public channels. Analysts frequently use this method to incorporate internal threat assessments, historical case files, vendor reports, or sensitive documents that require careful handling.
2. Indago Search
Indago's built-in search functionality provides access to a curated database of over 140,000 indexed sources spanning 27 languages, including global news outlets, trade publications, government documents, and corporate records. This isn't web browsing. Indago Search draws exclusively from pre-validated sources, so it's a structured query against a vetted collection of trusted information sources maintained by third-party data providers.
The search interface operates on boolean logic with two key components: keywords and activators. Keywords function as AND statements—the more keywords you add, the narrower your search becomes, requiring all terms to appear in results. Activators work as OR statements, broadening your search to include content that matches any of the specified terms. This dual approach allows analysts to cast a wide net with activators while maintaining precision through targeted keywords. For example, searching for "rare earth elements" as a keyword while using "mining, extraction, processing" as activators will return articles that discuss rare earth elements AND contain any of those related terms.
Indago's Co-Pilot feature further streamlines the search process by suggesting relevant keywords and activators based on your query, then automatically executing the search on your behalf. Simply describe what you're looking for in natural language, and Co-Pilot will translate your intent into effective search parameters, run the query, and present results for you to review and collect. This takes the guesswork out of search strategy while maintaining the analyst's control over which sources ultimately enter the collection—ensuring that your data universe remains both comprehensive and intentionally curated.
3. Data Retriever Chrome Extension
The Indago Data Retriever is a Chrome extension that transforms how analysts capture open-source intelligence while browsing the web. Available for both Chrome and Brave browsers, this tool allows you to seamlessly collect content from any website and instantly add it to your active Indago collection. Whether you're researching threat actors on specialized forums, tracking corporate developments through news sites, or monitoring social media for emerging trends, the Data Retriever removes the steps between finding something useful and getting it into your collection.
The extension offers flexible capture options to match your research workflow. You can save entire web pages for comprehensive documentation or highlight specific text passages to capture only the most relevant information. When you activate the Data Retriever, simply select your target project and collection, and the content is added to your collection and ready to use. This selective approach ensures your collection remains focused and relevant, avoiding information overload while maintaining complete context around critical intelligence.
Automatic source attribution is built into every capture, addressing one of the most time-consuming aspects of intelligence reporting. The extension automatically records the source URL, publication date, author information, and timestamp of capture—creating a complete audit trail without manual data entry. This feature proves invaluable when working with social media content, where posts can be deleted or modified, as the Data Retriever preserves both the content and its original context.
4. RSS Feeds
RSS feeds (Really Simple Syndication) are automated content delivery systems that publishers use to distribute their latest articles, reports, and updates. When a news outlet, government agency, trade publication, or blog publishes new content, their RSS feed automatically pushes that information out to subscribers. Think of it as a direct pipeline from the publisher to your workspace—no manual checking required. For intelligence analysts who need to monitor specific sources continuously, RSS feeds eliminate the need to visit dozens of websites daily to check for updates.
In Indago, RSS feeds create a continuous automated stream of fresh content flowing directly into your workstream. Once you subscribe to an RSS feed by adding the publisher's RSS link, new articles from that source automatically appear in your Indago platform in the Feed folder as they're published, so they can be easily added to your designated collections from there. This means you can monitor critical sources like government agencies, regional news outlets, or industry publications without any manual effort. The content arrives pre-formatted and immediately searchable, ready for AI analysis alongside your other collection materials.
Combined with Indago's other collection methods, RSS feeds are particularly useful for long-term projects where consistent source monitoring matters more than one-time research.
5. API Integrations
For enterprise organizations with existing intelligence infrastructure, API integrations represent the most sophisticated method for building collections in Indago. This approach enables automatic data flow from licensed databases, proprietary intelligence platforms, and enterprise security tools directly into your collections without any manual uploading, exporting, or reformatting. Once an integration is configured through secure API connections, data streams continuously into designated collections, keeping your collections current without manual intervention.
API integrations are primarily designed for enterprise customers who need to connect Indago to their existing technology stack—whether that's commercial threat intelligence feeds, internal security databases, or specialized research platforms. This method cuts out the manual steps — downloading from one system, uploading into another — that slow enterprise workflows down.
Organizations should consider API integrations when they have recurring data requirements from the same sources, need to maintain data freshness across multiple collections, or want to scale their intelligence operations without proportionally increasing manual effort. This is particularly valuable for teams managing ongoing threat monitoring, compliance reporting, or strategic intelligence programs where the same types of data need to flow into Indago on a regular basis.
Build Better Collections, Get Better Reports
These five collection methods give analysts complete control over their data universe, ensuring every source is vetted, credible, and purposefully selected before AI analysis begins. The quality of your collection determines the quality of your report. Because Indago's AI only works with what's inside your collection, your reports maintain the highest standards of accuracy and reliability. The more intentional you are about building your collections, the sharper and more actionable your intelligence becomes. Ready to see it in practice? Book a demo to get started.