- Oracle Integration 25.04 delivers AI-powered innovation, secure identity propagation, enhanced security measures, deeper multi-cloud connectivity, and new adapters to streamline integrations and accelerate automation.
- This release introduces AI-powered capabilities that simplify development and improve efficiency:
- AI-driven Document Understanding automates document processing for improved accuracy and efficiency.
- ATP Adapter’s “Select AI for SQL“ generates SQL queries from natural language prompts, reducing manual effort.
- FHIR Adapter’s AI-powered Search enhances healthcare data discovery for seamless interoperability.
- A major highlight of this release is Identity Propagation, enabling secure user identity transfer across systems. Adapters for REST, Oracle ERP Cloud, Oracle HCM Cloud, and Oracle CX Sales and B2B Service now support JWT User Assertion, ensuring end-to-end security and compliance in cross-application workflows.
- Alongside identity propagation, this release brings significant security and adapter enhancements to improve flexibility, automation, and protection:
- Custom OAuth Policy Obfuscation enhances security by masking sensitive credentials, such as client_secret, preventing plain-text exposure.
- Fusion Applications Adapters (ERP, HCM, and CX) now support JWT User Assertion security policy for invoke connections.
- Amazon SQS Adapter now supports inbound polling, enabling seamless event-driven integrations.
- Microsoft Dynamics 365 CRM Adapter introduces custom query parameters for more advanced data retrieval.
- HubSpot Adapter now triggers integrations based on multiple property changes for greater workflow automation.
- Shopify Graph QL Adapter expands multi-domain functionality, allowing seamless operations across multiple Shopify stores.
- FTP Adapter enhances legacy compatibility with NLST command support for optimized file polling.
- Confluent Adapter introduces dead lettering for failed message handling and mTLS security for encrypted communication.
- Microsoft Outlook Adapter now supports query parameters and pagination for scalable email retrieval through the Microsoft Graph API.
- We’re also expanding connectivity with new adapters:
- AQ JMS Adapter: Integrates Java Messaging Service (JMS) with Oracle Advanced Queuing (AQ) for robust, message-based workflows.
- Agiloft Adapter: A partner-developed adapter for seamless data synchronization and workflow automation with Agiloft Knowledge Base (KB).
AI Features
Oracle Integration 25.04 introduces advanced AI-powered capabilities to enhance automation, efficiency, and intelligent decision-making. These features include Document Understanding for seamless document processing, ATP AI integration for optimized database performance, and FHIR AI enhancements to improve healthcare data interoperability. Together, these innovations enable smarter and more efficient integrations across various industries.
Document Understanding -AI-Driven Automation for Document Processing
With this release, Oracle Integration introduces a new native action for Document Understanding, leveraging OCI AI-powered capabilities to automate document processing with enhanced accuracy and efficiency. This new feature streamlines workflows by reducing manual data extraction efforts across various business processes.
Key Capabilities
- AI-Powered Data Extraction: Automatically identify and extract critical details from supported document types.
- Seamless Integration: Integrate extracted data into financial, healthcare, and identity verification workflows.
- Future Expansion: Support for additional document types, custom models, and expanded AI capabilities planned for future updates
Supported Document Types
- The initial release supports the following key document types:
- Invoices: Extract supplier details, invoice numbers, amounts, and payment terms.
- Receipts: Identify purchase details, merchant names, and transaction amounts.
- Driver’s Licenses: Capture personal identification details, issue/expiration dates, and license numbers.
- Passports: Extract name, nationality, date of birth, and document validity.
Use Cases
- Healthcare Document Processing: Automate patient data extraction from medical forms, insurance claims, and prescriptions, reducing administrative workload and improving patient care. For example, hospitals can automate the processing of insurance claims, reducing administrative workload and speeding up patient approvals.
- Accounts Payable Automation: Automatically extract and process invoice data into Oracle ERP, minimizing manual effort and improving financial operations.
- Expense Management: Capture receipt details and integrate them into financial workflows for reimbursement approvals.
- Identity Verification: Use driver’s licenses or passports for customer onboarding and compliance checks.
ATP Adapter Enhancement – Support for AI Generated Queries
The ATP adapter in this release includes the addition of a new operation “Select AI for SQL” in the invoke role. To perform this operation, users can write a query in natural language. The adapter processes the natural query prompt, does the required mapping, and accesses the Large Language Models (LLM) to generate the SQL query.
Before you begin, you must register a profile in the ATP Database and get access to the required database tables. To know more, see Prerequisites for Creating a Connection. Next, enter the natural prompt in the adapter’s configuration wizard. Click Generate Query and view the query created.
If the natural language prompt is conditional, then the generated SQL query contains binding parameters. You must provide value to these parameters to fetch the desired results, For example, if the natural language prompt is “Get tasks for a specific project with a given status,” then you must specify value for #project_id. Refer to the images below for more details.
- Lastly, you can Validate and test the query and retrieve the desired information skipping the overhead of drafting queries.
- Note: The natural language prompt that you input must be clear, should include schema and table details, and validate foreign key relationships for accurate results. See Prerequisites for Creating a Connection
FTP Adapter Enhancements – Support for NLST Feature
The FTP Adapter now enables legacy system users to use NLST feature in lieu of the list command, thus ensuring seamless inbound polling for customers.
