Indago Under the Hood

A peek under the hood

Haystac Indago™ is a state-of-the-art AI/Machine Learning(ML)/Deep Learning software platform that delivers clean, secure, and actionable information assets. It searches, crawls, profiles, classifies, extracts data points and secures sensitive information. And it does this on more than 600 file types and across virtually any repository, cloud drive or file share.

Please forgive all the bullets here.  We just wanted to quickly summarize for you what makes Indago very useful.

Proprietary elements

• Scalable clustering and labeling by dominant topics
• Scalable near-duplicate detection
• Summarization and dominant key phrases
• Scalable Multi-model, multi-class deep hierarchy classification
• Outlier/Novelty detection
• Real-time classification kernel selection and parameter tuning
• Scalable Contextual information extraction from noisy text
• Visual classification and capture

Leading-edge, not Bleeding-edge, AI content analytics

We developed AI that works, including a pioneering use of deep learning to radically improve classification. We also mix and match AI methods to discover which works best on a specific project.

• Neural-networks classification with transfer-learning 
• Unsupervised and supervised Machine Learning methods
• Proprietary Visual ML and anchored OCR for scanned images
• False-positive reduction/Novelty detection
• Fuzzy-rules data point detection and extraction
• Rules enhanced classification and Q/C
• Dupes/near dupes detection and analytics
• Automatic extractive summary
• Automatic sensitive data anonymization

Surprisingly Easy to Use (for such an advanced AI platform)

As we’re fond of saying, you do not need a Data Scientist to use Indago. We baked that intelligence into the platform.

• Automatic data profiling
• Full featured connectors
• Agent-less ingestion from any data source
• Interactive dashboard and menu-driven user portal
• Integrated data modeling feed-back and Q/C
• Distance from original near dupes mapping and analysis
• Faceted search, including keyword, Regex and contextual search
• Exclusive “more-like-this” search
• Extensive document (text and html), data-point and metadata viewer
• JSON export
• Standard and custom-reporting facility
• False positive reduction/elimination