Prodigy - OpenText Core Transformation Publication Service Integration and Automation

Common Integration Use Cases Between Prodigy and OpenText Core Transformation Publication Service

1. Publish approved labeling guidelines and annotation standards to distributed teams

Data flow: OpenText Core Transformation Publication Service ? Prodigy

Organizations can use OpenText to transform controlled policy documents, labeling instructions, and annotation standards into consistent PDF, HTML, or other publishable formats, then distribute them to Prodigy users as reference material. This is useful when multiple data labeling teams, vendors, or subject matter experts need the same approved guidance for image, text, or document annotation tasks.

Business value: Reduces labeling errors, improves consistency across teams, and ensures that annotation work follows the latest governed standards.

2. Generate training datasets from managed content for AI annotation projects

Data flow: OpenText Core Transformation Publication Service ? Prodigy

Managed documents stored in OpenText can be transformed into annotation-ready output formats and sent to Prodigy for labeling. For example, regulated forms, contracts, claims documents, or product manuals can be rendered into a standardized format before being imported into Prodigy for entity tagging, classification, or document understanding tasks.

Business value: Speeds up dataset preparation, reduces manual conversion effort, and helps AI teams work with consistent source material.

3. Publish validated AI outputs back into controlled document channels

Data flow: Prodigy ? OpenText Core Transformation Publication Service

After data scientists and reviewers validate labels in Prodigy, the approved outputs can be exported and passed to OpenText for transformation into formal reports, operational documents, or compliance-ready publications. This is especially relevant when labeled data is used to generate audit evidence, quality review summaries, or model training documentation.

Business value: Creates a controlled handoff from AI experimentation to business documentation, improving traceability and governance.

4. Support regulated content classification and metadata enrichment workflows

Data flow: Prodigy ? OpenText Core Transformation Publication Service

OpenText can provide source documents that need classification, while Prodigy can be used to train and refine models that identify document types, sensitive content, or business metadata. Once labels are validated, the resulting model can help classify incoming content in OpenText workflows, and OpenText can publish the classified content into the correct format or channel.

Business value: Improves document routing, reduces manual review effort, and strengthens compliance handling for regulated content.

5. Create labeled datasets from published customer communications

Data flow: OpenText Core Transformation Publication Service ? Prodigy

Customer letters, policy notices, statements, and other published communications can be rendered by OpenText into a standardized format and then imported into Prodigy for annotation. Teams can label intent, sentiment, document sections, or compliance elements to build NLP models for customer service automation, correspondence analysis, or document intelligence.

Business value: Enables reuse of existing business content for AI training and accelerates development of text analytics models.

6. Build a human-in-the-loop review process for document generation quality

Data flow: OpenText Core Transformation Publication Service ? Prodigy ? OpenText Core Transformation Publication Service

OpenText generates published documents, which are then sampled and reviewed in Prodigy for issues such as missing fields, incorrect formatting, or content classification errors. Review results can be fed back into OpenText workflows to improve templates, transformation rules, or publication logic.

Business value: Improves output quality, reduces rework, and helps document operations teams identify recurring publication defects.

7. Accelerate AI model training for document-centric automation initiatives

Data flow: OpenText Core Transformation Publication Service ? Prodigy

Enterprises modernizing document-heavy processes can use OpenText to extract and publish standardized document outputs, then use Prodigy to label those outputs for downstream AI use cases such as document classification, field extraction, or exception detection. This is effective for insurance, healthcare, legal, and financial services organizations with large volumes of managed content.

Business value: Shortens the path from content management to AI model development and supports automation of document-intensive workflows.

8. Maintain audit-ready annotation and publication records

Data flow: Prodigy ? OpenText Core Transformation Publication Service

Annotation decisions, reviewer comments, and final label sets from Prodigy can be published into OpenText as controlled records, while OpenText can provide the source documents and final published artifacts for audit trails. This creates a complete chain from original content to labeled dataset to published output.

Business value: Strengthens governance, supports audit requirements, and provides traceability across AI training and document publication processes.