How Progress Agentic RAG and OpenEdge Work Together to Unlock the Full Value of Enterprise Data
Recently, we hosted an Ask Me Anything: The Progress Agentic RAG Solution and OpenEdge Platform to help organizations bring AI into real-world, production-ready business applications.
The session featured insights from Eudald Camprubi (former CEO of Nuclia and now part of the Progress Agentic RAG team), Irfan Syed (Director of Quality Engineering at Progress), and Cameron Wright (Principal Consultant). Together, they broke down modern AI concepts, like retrieval augmented generation (RAG), agentic workflows and Model Context Protocol (MCP)—and showed how they translate into practical value for Progress OpenEdge customers.
If you missed the live session, here’s a recap of the key concepts, demos and audience questions.
The Challenge: AI Needs Both Structured and Unstructured Data
Many OpenEdge customers already run mission-critical applications built on highly structured data—tables, business entities and transactional systems that have evolved over decades. At the same time, businesses now rely heavily on unstructured data, including PDFs, manuals, reports, images and web content.
From a user’s perspective, this distinction doesn’t matter. When users ask a question, they want a single, accurate answer, regardless of where the data lives.
That gap between structured and unstructured data is exactly where Progress Agentic RAG comes in.
What Is Retrieval Augmented Generation (RAG)?
Retrieval Augmented Generation (RAG) is a way to ground AI responses in your organization’s private data, rather than relying on public internet knowledge alone.
Instead of letting a large language model “guess” an answer (which can lead to hallucinations), RAG works by:
Retrieving only the most relevant content from your internal data
sourcesSending that context to the language model
Generating answers strictly based on that retrieved information
This approach improves accuracy, protects sensitive data and significantly reduces hallucinations.
What Makes Progress Agentic RAG Different?
Progress Agentic RAG is an end-to-end, modular, agentic RAG platform built with quality at its core. Here’s what that means in practice:
End-to-End: Progress Agentic RAG handles the entire pipeline, from ingesting files in any format or language, to extracting text, tables and images, to delivering answers with citations and quality metrics.
Modular: Different teams need different answers. Legal, sales, marketing and support may all rely on the same data but require very different outputs. Progress Agentic RAG allows teams to fine-tune retrieval and generation behavior without code.
Quality-Driven: Built-in evaluation capabilities (including LLM-based judging) help customers measure groundedness, relevance, and overall answer quality before deploying AI solutions into production.
Retrieval Agents Orchestrator (RAO): Connecting Everything Together
To go beyond a single data source, Progress Agentic RAG includes a Retrieval Agents Orchestrator (RAO).
RAO can:
Break a user’s question into sub-queries
Decide which systems to query (documents, databases, OpenEdge
services, or even trusted external sources)Retrieve the right information from each source
Combine results into one coherent, traceable answer
Just as important, RAO includes short-term and long-term memory, enabling agents to stay on task and deliver more personalized user experiences over time.
Where OpenEdge MCP Server Fits In
To connect structured OpenEdge data into this AI ecosystem, Progress introduced the OpenEdge MCP Server.
Model Context Protocol (MCP) is an open standard that allows AI systems to securely interact with backend tools and services in a consistent way. With the OpenEdge MCP Server, organizations can:
Expose OpenEdge REST and PAS for OpenEdge services as MCP tools
Enforce security, access control, and rate limiting
Avoid direct database access by routing everything through governed
APIsIntegrate OpenEdge cleanly into modern AI workflows
The result is a secure, standards-based way to make OpenEdge business logic available to AI agents—without rewriting applications.
Demo Highlight: Bringing It All Together
In the session demo, the team showed how Progress Agentic RAG and the OpenEdge MCP Server work together using a fictional Mountain Sports application.
The solution:
Retrieved unstructured data from a scraped website and PDFs
Queried structured inventory and pricing data from OpenEdge via MCP
Fell back to trusted external sources when needed
Delivered a single, unified answer—complete with citations and
traceability
From the user’s perspective, it all felt like one intelligent application, even though the data came from multiple systems.
Common Questions
Does this require PAS for OpenEdge? PAS for OpenEdge is required to expose OpenEdge business logic as RESTful services, which can then be surfaced through the OpenEdge MCP Server.
Can this work with non-OpenEdge backends? Yes. While tightly integrated with OpenEdge, the MCP Server can work with any RESTful backend that provides an OpenAPI specification.
Can users see where answers come from? Absolutely. Progress Agentic RAG provides citations, traces agent behavior and exposes reasoning paths to support validation and trust.
How much human oversight is required? Human involvement is mainly needed during setup and tuning. Once configured, agent behavior, reasoning and output quality can be monitored without constant supervision.
Where can we continue the conversation and ask more questions? Join the Progress OpenEdge community on Discord to connect with experts, ask follow up questions, and share best practices: https://discord.gg/GzYABMCAj5
What’s Next?
Progress Agentic RAG and OpenEdge MCP Server are designed to help customers modernize existing applications, unlock enterprise knowledge and bring AI into production with confidence—not just experimentation.
Get started with Progress Agentic RAG today!
See the Full Demo and Discussion
The webinar recording includes detailed demonstrations, real customer scenarios, deep technical explanations, and dozens of practical Q&A answers.
Watch the on demand webinar recording: https://www.progress.com/campaigns/openedge/webinars/whatisrag-webinar
Jessica (Malakian) Newton
Jessica (Malakian) Newton is a Senior Product Marketing Specialist at Progress, focused on the Progress OpenEdge product. Jessica started her career at Progress as an intern in 2020 and has since developed into a full-time marketer, dedicated to guiding customers on how to maximize the value of their OpenEdge solutions. Outside of work, Jessica enjoys reading and writing.
