Domain-tunable concept extraction
Entity, concept, and sentiment models tune to customer vocabulary and subject matter. The result is relevance that generic search engines cannot match.
OpenText • Content services
OpenText Knowledge Discovery
Knowledge Discovery is the IDOL-based cognitive search and text analytics product for extracting meaning from unstructured enterprise content. Merito designs the analytics pipelines.
Merito sells OpenText Knowledge Discovery (IDOL lineage) and delivers cognitive search, text analytics, concept extraction, and privacy-preserving classification over controlled content.
- Best for
- Legal analytics and eDiscovery leaders, Financial investigation and fraud analytics leaders, Intelligence and defense analytics owners
- Hosting
- SaaS
- Time to value
- First analytics use case live in as little as one week for narrow scope. First analytics use case live in three to five months. Full content-classification program in six to twelve months depending on taxonomy scope.
- Security posture
- ISO 27001, GDPR, SAML SSO
- Last reviewed
- 2026-04-26
What it is
OpenText Knowledge Discovery in the enterprise stack
OpenText Knowledge Discovery is the product most customers know as IDOL. It is a cognitive search and text analytics engine designed to extract meaning from unstructured content and documents, emails, transcripts, multimedia, and social feeds. Knowledge Discovery is not a chat AI; it is a deep analytics surface that powers investigation, discovery, and classification workloads at enterprise scale.
The product's defining property is domain-specific modeling. Concept extraction, entity recognition, sentiment analysis, and classification tune to the customer's vocabulary and subject matter. For regulated customers (legal, financial, pharma, government) that specificity matters; generic search engines cannot replace Knowledge Discovery's trained models.
Knowledge Discovery complements Content Aviator rather than replacing it. Aviator is a conversational grounded-AI surface. Knowledge Discovery is the deep analytics surface underneath. Programs running both use Aviator for user-facing retrieval and Knowledge Discovery for analyst-driven investigation and classification.
Ideal use cases
- Legal document analytics and eDiscovery investigation
- Financial fraud and market abuse detection from unstructured sources
- Intelligence analytics over multi-source content
- Contact center transcript analytics and sentiment
- Privacy-preserving content classification for compliance programs
What it is best at
Where OpenText Knowledge Discovery earns its seat
Multi-source analytics at enterprise scale
Ingestion spans documents, email, multimedia, social, and database content. The analytics layer works across sources, not just within a single repository.
Proven across high-stakes analytics workloads
Legal, defense, intelligence, and financial services programs have used IDOL for decades in investigation and discovery workloads where accuracy matters.
Core capabilities
OpenText Knowledge Discovery capabilities, grouped by outcome
Cognitive search
Ranked retrieval using concept and entity models rather than keyword matching alone.
Concept-based search
Queries ranked by semantic proximity in addition to keyword match.
Entity recognition
Named entity extraction (people, places, organizations, custom entities) for facet-driven search.
Multi-language support
Processing across multiple languages with consistent ranking.
Text analytics
Deep text analysis for classification, sentiment, and concept extraction.
Classification
Automated content classification against customer-trained taxonomies.
Sentiment analysis
Tone and sentiment scoring across content sources.
Summarization
Extractive summarization for long-form content.
Ingestion and integration
Broad content ingestion across document stores, databases, and specialized sources.
File and document ingestion
Broad file-format support through KeyView (File Content Extraction).
Database and API ingestion
Connectors for databases, message queues, and enterprise APIs.
Multimedia analytics
Speech-to-text, image recognition, and video analytics for multi-modal investigation.
Where it fits in the stack
How OpenText Knowledge Discovery connects to the rest of your landscape
OpenText Content catalog (native)
Native- OpenText File Content Extraction (KeyView)KeyView feeds clean text from diverse file formats into Knowledge Discovery.
- OpenText Content Management, Documentum, Core Content ManagementKnowledge Discovery indexes content across OpenText repositories.
- OpenText eDiscovery and Legal SolutionsDeep integration for legal discovery and investigation workflows.
Enterprise sources (certified)
Certified- Microsoft 365, SharePointConnectors for Microsoft content sources.
- Enterprise message archivesIngestion from common enterprise email and chat archives.
Custom integrations
Custom- Customer-specific data sourcesAdapters for proprietary content stores, databases, and pipelines.
- Analyst workbenchesCustom analyst UIs consuming Knowledge Discovery APIs.
Deployment and implementation
How it rolls out
- Hosting
- SaaS (North America, EMEA, APJ)
- Implementation complexity
- High
- Typical time to value
- First analytics use case live in as little as one week for narrow scope. First analytics use case live in three to five months. Full content-classification program in six to twelve months depending on taxonomy scope.
- Prerequisites
- Defined analytics use case (eDiscovery, fraud, investigation, classification)
- Named taxonomy or classification scheme
- Content sources identified for ingestion
- Analyst audience identified for output consumption
- What Merito usually handles
- Merito handles Knowledge Discovery deployment, ingestion design, taxonomy and model tuning, and analytics pipeline configuration. Investigation ownership typically stays with the customer's analyst team; Managed Services and Staff Augmentation can extend the engagement when the program wants Merito-placed analysts.
Licensing and packaging
How it is bought
- Model
- Subscription
- What to expect
- OpenText Knowledge Discovery is subscription-licensed with packaging keyed to ingested content volume, analytics workload, and connector counts. Pricing depends on corpus size, processing rate, and specialized capabilities (multimedia, advanced classification). Merito sells Knowledge Discovery alongside the taxonomy tuning and analytics pipeline work that makes the license useful.
- Editions and modules
Knowledge Discovery standard
Cognitive search, concept extraction, and classification for enterprise content.
Best for: Programs running analytics workloads over unstructured enterprise content.
Knowledge Discovery with multimedia
Standard plus speech-to-text, image, and video analytics for multi-modal investigation.
Best for: Legal, intelligence, and compliance programs with multimedia evidence.
- Common expansion areas
- Additional corpus volume as content grows
- Multimedia analytics capabilities
- Specialized connector development
- Analyst workbench integration
- Managed Services for ongoing model tuning
Merito services
How Merito helps you win with OpenText Knowledge Discovery
Merito sells licenses and the delivery work around them. Pick the service that matches where you are in the lifecycle.
01
Knowledge Discovery Rollout
Ingestion design, taxonomy tuning, concept model configuration, and analyst workbench integration.
Explore service02DevOps Consulting
Analytics pipelines integrated with customer-specific data sources and workbenches.
Explore service03Premium Support
Named engineer, priority SLAs, and release-time coverage for Knowledge Discovery in production.
Explore service04Managed Services
Long-term run support including ongoing model tuning and corpus management.
Explore service05Training and Enablement
Role-based training for administrators, model engineers, and analysts.
Explore service06Staff Augmentation
Merito-placed analytics engineers and content classification specialists.
Explore serviceKnowledge Discovery licensing
Buy Knowledge Discovery from the partner that also tunes the taxonomy.
Merito sells OpenText Knowledge Discovery and delivers ingestion design, taxonomy tuning, analytics pipelines, and analyst workbench integration that turn IDOL output into real investigation value.
Merito point of view
Knowledge Discovery pays back on investigation workloads. For conversational retrieval, pick Content Aviator.
Merito has seen customers try to use Knowledge Discovery as a consumer-facing search experience and find it overkill, and try to use Content Aviator for deep analyst investigation and find it underkill. The products target different audiences. Merito's guidance and Aviator for user-facing grounded AI, Knowledge Discovery for analyst-driven investigation. Programs often run both.
Taxonomy tuning is the work. Generic Knowledge Discovery output produces generic results; the customer's domain-specific taxonomy and concept model are what deliver the lift. Expect taxonomy work to be a meaningful portion of the rollout timeline.
For legal and regulated investigation workloads specifically, the combination of Knowledge Discovery (analytics) with eDiscovery and Legal Solutions (workflow) could be the right stack. The two products are designed to work together.
What buyers usually underestimate
- Adopting Knowledge Discovery for user-facing retrieval use cases better served by Content Aviator.
- Skipping taxonomy tuning and expecting generic output to deliver value.
- Ingesting everything instead of scoping the corpus to the analytics use case.
- Treating Knowledge Discovery as a product that runs itself; it needs ongoing model maintenance.
- Not integrating with KeyView for file-format parsing; text quality degrades quickly.
Related from Merito
Continue exploring OpenText Knowledge Discovery on Merito
Related solutions
Related services
Related products
- OpenText File Content ExtractionKeyView parsing that feeds Knowledge Discovery.
- OpenText Content AviatorConversational grounded-AI surface that complements Knowledge Discovery's deep analytics.
- OpenText eDiscovery and Legal SolutionsDeep integration for legal discovery workflows.
- OpenText Content ManagementPrimary content source indexed by Knowledge Discovery.
- OpenText (vendor portfolio)OpenText hub and the full DevOps and Content catalogs.
Frequently Asked Questions
OpenText Knowledge Discovery FAQs
Consultation request
Talk to Merito about OpenText Knowledge Discovery
Share the analytics use case and the content sources in scope. A Merito analytics specialist follows up within one business day.
Analyst-first
Built for investigation, not chat
Knowledge Discovery targets analyst-driven workloads where accuracy and taxonomy depth matter more than conversational surface.
Taxonomy tuning
Domain-specific models
Merito tunes concept and classification models to the customer's vocabulary before go-live.
Next step
Pick the analytics use case first. Tune the taxonomy second.
A Merito Knowledge Discovery engagement starts with the analytics use case and the customer's domain-specific taxonomy.