What’s New in Oracle Integration 26.04 by Niall Commiskey
Introduction
Building on the power of AI we already have in OIC, is the big focus of our 26.04 release.
AI Features released in 26.04
AI Assistant
This release brings several meaningful improvements to the AI Assistant, focused on simplifying integration development, improving performance, and expanding availability.
Smarter Editing with Auto Checkpointing
AI-assisted editing is now more seamless than ever. With auto checkpointing enabled, users no longer need to manually save integrations before applying AI-driven changes. The system automatically preserves progress, allowing you to iterate faster and with greater confidence. As an example if you are editing an integration using AI Assistant and on generation you didn’t like the content, system will rollback the specific generated activities to the previous state without forcing you to save the integration.
Faster Endpoint Auto-Configuration
We’ve significantly improved the performance of endpoint auto-configuration for supported adapters, to learn more about the supported adapters please refer to the note in this documentation link. This results in quicker setup times and a smoother experience when working with integrations.
What’s New in Oracle Integration RPA 26.04 by Sandhya Lakshmi Gopalan
The 26.04 release of Oracle Integration brings powerful new enhancements to Robotic Process Automation (RPA), focused on improving resilience, scalability, and operational visibility. These updates are designed to help organizations build more reliable automations while reducing manual intervention and downtime.
Let’s take a closer look at what’s new.
�� AI-Powered Self-Healing Robots
Robots are fragile and tend to fail due to minor changes in the UI. One of the most impactful additions in this release is AI-powered self-healing.
Robots can now intelligently detect failures during execution and automatically attempt recovery without human intervention. By leveraging AI, these robots can adapt to minor UI or workflow changes, significantly reducing automation breakages and maintenance overhead.
Key benefits:
• Increased automation reliability
• Reduced manual fixes and monitoring
• Faster recovery from transient issues
To take advantage of this feature in your Oracle integration instance, validate if the Enable AI Assistant option is enabled in the AI Settings page. This is enabled by default.
New Adapters and Connectivity Enhancements in Oracle Integration 26.04 by Madhav Poosarla
Oracle Integration continues to advance intelligent automation and enterprise connectivity with this release, delivering key enhancements across AI Native Actions and adapters. This update expands AI-driven integrations with custom model support in OCI Document Understanding and OCI Vision, enhanced generative AI capabilities with tools support, and expanded model options including OpenAI and xAI Grok. It also introduces the OIC AI Agent Invoke Native Action, enabling integrations to directly invoke AI agents and embed AI-driven decision-making into workflows.
This release also introduces new adapters—BigQuery, Databricks, MS Fabric, and ActiveMQ—extending analytics and messaging connectivity. In addition, multiple adapter enhancements improve security, connectivity, and runtime flexibility, including Multi-Key Header Authentication and dynamic REST endpoints in the REST Adapter, along with expanded capabilities across Microsoft SQL Server, Snowflake, Kafka, GCP Pub/Sub, SharePoint, NetSuite, Azure Event Grid, and the Shopify adapters. Certification updates are also included for the ATP, Kafka, RabbitMQ, and Shopify GraphQL adapters.
New Adapters
• BigQuery Adapter – Introduces native connectivity to Google BigQuery for loading, extracting, querying, and managing analytical data using outbound invoke connections.
• Databricks Adapter – Adds connectivity to Databricks SQL warehouses, schemas, and tables for database-style operations.
• ActiveMQ Adapter – Provides built-in connectivity to ActiveMQ Artemis brokers with support for message consumption (trigger) and message publish (invoke) patterns.
Intelligent Expense Automation with Agentic AI LiveLab with a new hands-on module. by Subhani Italapuram
What’s new:
✅ Calling Oracle Integration (OIC) tools from Fusion AI Agent Studio
✅ Creating intelligent agents step-by-step
✅ Designing and orchestrating agent teams
This LiveLab now provides a complete, real-world implementation of Agentic AI—combining AI services, enterprise integrations, and Fusion applications.
If you're exploring Agentic AI on Oracle Cloud, this is a great hands-on starting point.
Would love your feedback after trying it out!
AI Agent in Oracle Integration Cloud: The Future of Intelligent Automation by Biman Dey Sarkar
Enterprise integration has traditionally been about connecting systems through predefined workflows. While effective, these approaches often struggle when processes become complex, dynamic, or unpredictable.
With AI Agent in Oracle Integration Cloud (OIC), Oracle introduces a new model—goal-driven, intelligent automation.
What is Agentic AI?
Agentic AI brings in intelligent agents that don’t just execute steps—they reason and decide.
Instead of hardcoding a workflow, you define a goal such as “validate and approve an expense” or “fix a failing connection." The AI agent interprets the request, understands the context, and dynamically determines how to achieve that outcome.
This is a major shift from “how to do" to “what to achieve."
How It Works in OIC
The architecture is built on a simple but powerful idea:
• The AI Agent acts as the brain, powered by LLM-based reasoning
• Integrations act as tools, performing actions like API calls, validations, or updates
When a request comes in, the agent evaluates the situation, selects the right tools, and executes them in the appropriate sequence. Unlike traditional flows, this sequence is not fixed; it evolves based on context and responses.
Building an Agent
Developing with Agentic AI in OIC is less about designing step-by-step flows and more about enabling reusable capabilities.
You start by exposing integrations as tools, then configure the agent with
• Clear instructions (prompt)
• Access to relevant tools
• A reasoning approach such as ReAct (iterative thinking) or Plan & Execute (structured execution)
Once deployed, the agent can handle variations in input and scenarios without requiring redesign.
Parsing SAP Spool Files in OIC Gen3 Using ATP & REGEX by Devkiran Tomar
Abstract
SAP spool outputs are often print-oriented fixed-width text reports and are not directly consumable by integration platforms like OIC. This blog presents a practical ATP-based REGEXP parsing framework that converts unstructured spool text into structured CSV format, enabling seamless downstream integration without SAP-side redesign.
Parse SAP Spoof File
Blog Benefits / Key Takeaways
• SAP spool files often export data in text format with all columns merged, making automation and integration tough for downstream systems.
• OIC can efficiently ingest such files from FTP/SFTP but may read all data into a single column due to lack of clear delimiters.
• Using Oracle ATP as a staging area, you can leverage SQL functions to split and parse the single-column data into meaningful fields/columns. Powerful string and regex functions in ATP make it possible to process and restructure the SAP spool data exactly as needed. Keeping transformation logic in SQL (ATP) makes this architecture easy to change, troubleshoot, and scale for new spool formats.
• Once split and validated, the data can be sent seamlessly to various target systems or applications (ERP, HCM, Analytics, EPM, etc.), enabling automated and reliable business processes.
Introduction
SAP spool files are generally generated by ABAP programs or custom SAP reports as output files within the SAP system. These files often serve as the basis for integrations, especially when business or audit-critical information needs to be transferred to other enterprise systems. However, spool files commonly come in text format with data merged in single rows or columns, which makes them less suitable for direct consumption by modern integration tools.
This blog demonstrates an approach to processing SAP spool files using OIC and ATP to enable robust, automated, and scalable data transformation and delivery.
Agentic AI in OIC – Overview and Introduction by Steve Tindall & Kishore Katta
Agentic AI is shifting expectations from “help me understand” to “help me execute.” In an enterprise setting, that execution must be grounded in real data, connected to your enterprise apps, and delivered with predictable, reliable action. In practical terms, agentic AI only becomes enterprise-grade when it can:
• Get the right data from your apps
• Take the best action safely by invoking secure, trusted, and reliable tools
• Follow repeatable patterns so outcomes are consistent and governable
In this blog, I want to introduce you to Oracle Integration’s new agentic AI capabilities and give you a quick overview tour of the UI via a demo video.
My friend and colleague, Kishore Katta, or KK, as he is known, has been working with a number of customers on a ‘Smart Invoice Validation and Processing Agent.’ Therefore, I am going to use that use-case as context for this blog. An agent in this scenario has the job of receiving new invoices from suppliers, validating the invoice and extracting details, comparing the terms of the invoice against the buying agreement/contract in place for that supplier, and then creating the invoice in the company ERP application. It also uses HITL for human approvals, if needed. Big shout-out to KK for building the agent and tools used in the demo. If you want to learn more about HITL and why it is a critical part of enterprise agentic AI, check out this blog.
What’s new in OIC 26.01
In OIC 26.01, you’ll see a new AI tab within an OIC project, alongside familiar concepts such as integrations and connections. The AI tab is where you build and manage agentic artifacts—specifically:
• Tools
• Agents
• Agent Patterns
• Prompt Templates
One-Click MCP Server Generation and Agentic AI Tools with Oracle Integration by Steve Tindall
The latest release of Oracle integration now includes capabilities to create Agentic AI Agents and publishing MCP Tools.
Executive Summary
• Oracle Integration now generates governed, trusted AI tools for any agent framework using a Model Context Protocol (MCP) server, with a single click.
• Customers can expose their existing integrations and automations as MCP servers to orchestrate complex, multistep processes with unified observability.
• With predictable MCP tools from Oracle Integration, your teams can scale agentic AI initiatives quickly, confidently, and with full visibility.
What if you could give any AI agent trusted, predictable access to business data, actions, and enterprise workflows with one click?
With Oracle Integration’s latest innovations, that’s now a reality for today’s AI leaders.
The era of simple chatbots is over. Forward-looking organizations are investing in agentic AI to combine sophisticated reasoning with safe, auditable actions across enterprise applications, data, and processes. The challenge is that scaling sophisticated agents for real business operations requires more than language skills. It demands deterministic, governed automation and orchestration, trusted integrations, and explainability for every step.
Oracle Integration bridges this gap.
• Now, you can publish any integration project as an enterprise-ready agent tool for any framework using the built-in MCP server generation feature.
• This Model Context Protocol (MCP) standard allows agents, whether built in Langchain, Fusion Agent Studio, Langflow, or elsewhere, to reliably discover, invoke, and describe orchestrated business automations.
These tools are not just simple task automations; they are trusted, auditable endpoints for agents to consistently execute business logic, invoke data flows, and coordinate human workflows, all governed by consistent guardrails.
How Oracle Integration Makes AI Agents Smarter
Smarter with Data:
Oracle Integration offers an ever-expanding library of adapters that connect AI agents to ERP, HCM, SCM, and other essential systems.
Smarter with Action:
Your automations, which orchestrate APIs, robots, business rules, and human-in-the-loop approvals, can now be securely exposed as structured agent tools.
AI-Powered Multilingual Text Extraction from Any Image with OCI & Oracle Integration Cloud by Ravi Gupta
Extracting text from documents whether they are decades-old newspapers, scanned images, or modern digital files presents inherent challenges. These challenges are further amplified when documents contain multiple languages or are of poor visual quality. Oracle Cloud Infrastructure (OCI) Document Understanding, combined with Oracle Integration Cloud (OIC), offers a highly effective, low-code solution to address these complexities.
This blog demonstrates how images of any age or format, containing multilingual text, can be seamlessly processed and fully extracted using OCI Document Understanding through Oracle Integration Cloud, with minimal development effort and without direct API management.
OCI Document Understanding Overview
OCI Document Understanding is an AI-driven service designed to extract text, tables, and structured data from document files such as images and PDFs. The service supports multilingual content and performs reliably even on low-resolution, aged, or scanned documents.
Oracle Integration Cloud further simplifies adoption by providing a built-in Document Understanding Adapter. This adapter abstracts all low-level API interactions and complex AI configurations, enabling developers to integrate advanced document processing capabilities rapidly and efficiently.
Solution Flow Overview
The following high-level integration flow is implemented in Oracle Integration Cloud:
Configuring a Customer-Managed Custom Endpoint by Antony Reynolds
Introduction to custom endpoints
Out of the box, Oracle Integration provides public endpoints managed by Oracle. Oracle Integration also supports both Oracle-Managed and Customer-Managed custom endpoints. A custom endpoint is a user-chosen hostname. Possible uses for a custom hostname include a vanity hostname, such as integration.mycompany.com. A common use of a Customer-Managed custom hostname is to support a Customer-Managed disaster recovery solution.
Oracle-Managed custom endpoints make use of the Oracle Certificate service to generate a certificate that is loaded directly into the Oracle Integration service instance. Oracle will also update the customer provided Oracle DNS service to point the hostname to the Oracle integration service instance.
Customer-Managed custom endpoints require the provisioning of a front-end device such as a load balancer or API gateway. This device will host the customer-generated certificate and the customer will set up DNS to point to this front-end device.
The table below shows some sample use cases together with which type of custom endpoint supports them:
|
