So, when you hear “AI will change everything”, it’s normal to be skeptical and a little nervous. This blog series is here to cut through the hype and give you a practical mental model for where AI fits in OpenEdge solutions—without ever handing your business logic (or your data integrity) over to a probabilistic black box.

This post is a practical introduction and safety-first mental model—not a deep dive into AI model architectures, but identify low-risk, high-value places to apply AI without compromising data integrity.

What is Artificial Intelligence (AI)?

Let’s start by saying that the term Artificial Intelligence is broad. The focus of Artificial Intelligence right now is the category called Generative AI (GenAI)—software that can read, write, summarize, and reason over language. This class of AI can summarize long documents, explain code, answer questions, draft content, and transform unstructured information into something more useful. Under the hood, these systems are powered by Large Language Models, or LLMs.

This post introduces some key AI concepts and fits them into how OpenEdge developers already think about systems. As a first step, let’s align on some key terminology used in AI systems.

Artificial Intelligence (AI)
A broad field of computing focused on building systems that can perform tasks that normally require human intelligence. These tasks include understanding language, recognizing patterns, learning from experience, solving problems, and making decisions. Instead of being explicitly programmed with step‑by‑step instructions for every situation, AI systems use data and algorithms to adapt their behavior based on examples. In practice, AI powers things like fraud detection, speech recognition, and predictive analytics, helping software systems make informed decisions or assist users more effectively, while still operating within defined goals and constraints set by humans.

Machine Learning (ML)
A subset of artificial intelligence that focuses on building systems that learn from data instead of being explicitly programmed with fixed rules. In machine learning, models are trained on examples so they can identify patterns and make predictions or decisions when presented with new data. Over time, as they are exposed to more data, these systems can improve their results without manual reprogramming. For example, a spam filter learns to identify junk mail based on thousands of emails identified as spam.

Generative Artificial Intelligence (GenAI)
A class of machine learning systems that can create new content—such as text, code, images, or documents—based on what it has learned from existing data. Instead of following fixed rules or just analyzing information, GenAI looks for patterns in large datasets and uses those patterns to produce realistic, human‑like outputs. When given a prompt, it predicts what output best fits the request based on probability, which means the results are often useful and coherent but not always perfectly accurate and requires human oversight to validate correctness and reliability.

Practically speaking, GenAI generates output by predicting what text (or code) is most likely to come next based on your prompt and its training data. That makes it great at language-heavy work—drafting, summarizing, explaining, and extracting key details—but it also means the output can be confidently wrong. Treat it as an assistant, and validate anything that matters.

Large Language Model (LLM)
A type of GenAI that is designed to understand and produce human‑like text. It is trained on large collections of written material—such as books, articles, documentation, and code—so it can learn how language is structured and how ideas are typically expressed. An LLM generates a response by predicting what words or tokens are most likely to come next based on the context, rather than retrieving a fixed answer. This allows LLMs to perform tasks like answering questions, summarizing documents, writing code, explaining concepts, and carrying on conversations. While LLMs are very good at producing fluent and relevant text, their outputs are based on patterns and probability, so they can sometimes produce confident but incorrect or incomplete information and should be used with appropriate validation in technical or business systems.

Prompt
The input you give to a large language model to guide what it should produce. It can be a question, an instruction, an example, or a combination of these, written in natural language. The prompt provides context and constraints, helping the model understand the task, the tone, and the level of detail you want in the response. Because an LLM generates output based on patterns and probabilities, small changes in a prompt—such as adding clarification, examples, or specific requirements—can significantly affect the quality and relevance of the result. In practice, prompts are how developers and users “program” GenAI systems, shaping their behavior without writing traditional code.

Why AI Is Becoming Relevant Now

AI isn’t new. We’ve all dealt with “smart” systems for years—think about chatbots and automated phone systems that can be very frustrating.

And no—enterprise software didn’t suddenly decide data integrity is optional, and developers didn’t become obsolete overnight.

What has changed is that modern models are finally useful in day-to-day work: they can summarize, classify, extract, and draft text with surprisingly high quality. They’re also very good at working with unstructured information at scale. For OpenEdge teams, that matters because so much effort lives in language-heavy tasks—reading legacy ABL, digging through logs, interpreting requirements, and keeping documentation current.

A Mental Model That Actually Holds Up

For OpenEdge developers, the most important thing to know is that modern AI systems do not actually understand your application. They don’t know your business rules or what data is authoritative—they generate responses based on learned language patterns.

Rule of thumb: let AI suggest and summarize; let OpenEdge validate, enforce rules, and commit. If a mistake would break data integrity, auditing, or transactions, AI shouldn’t be the decision-maker.

For OpenEdge developers, there are two distinct ways that AI can be used: development and runtime.

Development: use AI to boost productivity and improve code quality while you build and maintain OpenEdge systems—explaining legacy ABL, drafting documentation, scanning logs, generating test ideas, and tightening error handling and security patterns.

Runtime: use AI alongside your app to interpret unstructured input (questions, notes, emails) and help users read and understand authoritative results. OpenEdge should still validate inputs, enforce business rules, and perform all updates and commits deterministically.

AI can help interpret intent (for example, “show overdue invoices for Acme”), OpenEdge turns that into validated, parameterized inputs, runs the query deterministically, and then AI summarizes the results. Avoid patterns where AI invents filters, infers rules, or triggers updates/commits.

AI Relevance for OpenEdge

As mentioned earlier, AI is most useful in two distinct ways: development and runtime. During development, AI can act as a productivity booster for engineers by helping generate ABL code snippets, draft unit tests, create or update documentation, explain legacy procedures, and even suggest how existing business rules should be applied or refactored. Used this way, AI accelerates understanding and reduces manual effort, while developers remain fully in control of data integrity and design decisions. AI can also improve code quality by acting as a continuous, context‑aware reviewer and assistant throughout the development lifecycle rather than as a replacement for developer judgment.

At runtime, AI plays a different role: it can sit alongside OpenEdge applications to help access and interpret structured data more effectively — supporting natural‑language queries, summarizing query results, or retrieving relevant records based on intent rather than rigid filters. AI lives outside your core ABL logic, usually as an external service you call through PASOE or another integration layer. It can suggest, explain, or summarize, but OpenEdge still validates inputs, enforces business rules, and commits transactions.

Concrete examples for OpenEdge Developers

• Dev-time: explain a legacy ABL procedure, identify risky FIND FIRST patterns, suggest stronger error handling, or draft comments/docstrings for internal procedures and classes.
• Dev-time: generate a first-pass unit-test checklist from a spec (“what edge cases should we test?”) and map it to your existing harness/framework.
• Ops: summarize OpenEdge/PASOE logs (startup, agent, stack traces) into “probable cause + next checks” while linking back to the exact log lines used.
• Runtime (read-only): translate natural language into validated parameters (dates, customer IDs, status codes), then run the query deterministically—for example, “get the top 10 revenue customers for the past 12 months.”
• Runtime (user experience): summarize result sets returned by OpenEdge services into a short narrative (for example, “top 3 drivers of backorders this week”) without changing any underlying data.

In all cases, AI augments your work rather than replacing it: OpenEdge remains the source of truth for rules and data, while AI helps developers and users interact with that system more naturally and efficiently.

Summary

This post introduced the core GenAI terms and a safety-first way to think about using AI with OpenEdge: use AI for language-heavy assistance (explain, summarize, draft, extract), and keep OpenEdge responsible for validation, business rules, and transactions. In Post 2, we’ll take a deeper dive into the main components of GenAI and walk through practical applications you can adopt immediately—plus guardrails to keep your systems reliable.

Learn more about Progress OpenEdge and its AI capabilities.

What Progress Agentic RAG and OpenEdge MCP Server Deliver Together

• AI that understands the full context of your business by reasoning across structured and unstructured knowledge already inside your OpenEdge-powered business.
• AI that acts securely by using MCP governed access to control AI’s actions, preserving the integrity of business rules and protecting your intellectual property.
• AI that accelerates outcomes by providing clear, grounded explanations that reduce the time spent searching, reconciling and interpreting information across different kinds of documents.

Unlocking the Value Hidden Inside Your OpenEdge Applications

Knowledge inside OpenEdge applications is highly distributed, from database transactions and ABL logic to contracts, documentation and support history. Manual search, reporting and investigation approaches cannot interpret this information or explain why something happened in a timely and meaningful way. Progress Agentic RAG shifts from retrieval to reasoning by identifying relevant information, invoking appropriate tools, querying structured data and synthesizing complete explanations to deliver clarity in seconds instead of hours.

This approach transforms OpenEdge from a system of record into a system of intelligence. Years of pricing logic, compliance rules, workflows and historical decisions become accessible through natural language questions. The solution also unifies structured information with documents and policies, creating a more accurate and comprehensive understanding of events. As teams gain clear answers grounded in data and context, productivity rises and inconsistency decreases. Support teams resolve issues faster, finance teams validate anomalies without switching systems and new employees can ramp up more quickly.

The OpenEdge MCP Server strengthens this intelligence by enabling AI to interact with your application in a secure and governed way. Instead of bypassing business logic, AI agents call approved procedures that enforce existing rules. This protects your intellectual property, maintains the reliability of operational logic and supports a safe foundation for future AI expansion. By combining the reasoning of Progress Agentic RAG with the governed execution of the MCP Server, ISVs gain a powerful set of tools for sustained modernization and differentiation from new competitors entering the market. As markets shift toward intelligent and proactive systems, this combined capability helps OpenEdge applications deliver deeper insights and new value without rewriting trusted code.

Conclusion

Your OpenEdge application can contain decades of valuable intelligence. Progress Agentic RAG and the OpenEdge MCP Server unlocks that intelligence by turning what once required multiple different technical searches across structured and unstructured data into one natural language question.

To learn how these technologies work together and explore the full architecture, read the complete white paper here today.

One standout theme was data anonymization, a real and growing industry pain point. As organizations manage thousands of databases while facing strict regulations like GDPR, anonymizing sensitive data is critical, but often manual, complex and time‑consuming. The hackathon showed how AI can help OpenEdge customers automate this process, reduce compliance risk and introduce modern capabilities without rewriting existing applications.

We had the opportunity to sit down with the second‑place winning team—lead Razvan Stetcu, along with Stăncuta Porumb and Sergiu Vescan from Wayfare—to learn more about their project, the challenges they faced, and what they discovered by combining OpenEdge with AI.

The Hackathon Challenge: Bringing AI into an Existing Product

For Razvan, the motivation to join the hackathon was clear from the start.

“I’m always excited when I need to implement something that will use AI.”

Rather than building something entirely new, the team chose to enhance an existing Wayfare product called DBlur—a data anonymization tool designed to help organizations comply with GDPR and other privacy regulations.

The challenge? Scale.

“When you have hundreds of tables and a lot of fields inside, it’s a lot of work to check each table and decide what needs to be anonymized,” Razvan explains.

That made DBlur an ideal candidate for AI augmentation.

The Idea: AI‑Driven Suggestions for GDPR Compliance

The team’s goal was to use AI to suggest which database fields should be anonymized, dramatically reducing manual effort while keeping developers firmly in control.

Using Progress Agentic RAG, the solution analyzed GDPR and compliance rules uploaded as PDFs, extracting guidance from unstructured documents to recommend anonymization rules for a given database schema. This approach helped identify sensitive fields efficiently without relying on rigid, rule‑based logic.

Instead of starting from scratch, developers can review AI‑generated suggestions, adjust them as needed and then proceed with anonymization.

“The purpose was to review what AI selected, add or remove a few fields if needed, and then just move forward,” Razvan says.

Importantly, the AI does not act autonomously. Human validation remains a core part of the workflow, helping avoid mistakes and ensuring compliance.

How OpenEdge Powered the Solution

OpenEdge played a central role in the project’s architecture.

“DBlur’s backend is in Progress OpenEdge,” Razvan explains. “The frontend is React, and for the AI we used Progress Agentic RAG.”

With OpenEdge handling backend logic and database operations, the team focused on integrating AI where it added the most value—field identification and decision support—without re‑architecting the application.

The result was a modern, hybrid architecture: OpenEdge remains the system of record and core business logic engine, while AI services deliver intelligent analysis and recommendations. This model enables organizations to enhance existing OpenEdge applications with AI without disrupting proven systems or requiring large‑scale migrations.

The Hackathon Experience: Fast‑Paced and Collaborative

The team described the hackathon as intense, fast‑paced, and highly collaborative.

“The idea was very nice. Building something that uses AI, building the team and the fact that we managed to communicate and understand each other from the very first step,” Razvan says.

Time constraints were the biggest challenge. Early on, the team explored a different idea before realizing it was too ambitious.

“At first we wasted like two days on an idea, and after that we changed it because it was too much work and we didn’t have enough time,” he admits.

Even so, the pressure helped sharpen their focus and they delivered a working solution by the end of the event.

Learning AI with OpenEdge

For some team members, the hackathon marked their first hands‑on experience combining AI with OpenEdge.

“It was the first interaction with AI—and especially with Progress,” says Stăncuta Porumb. “It was a nice experience, and I learned a few new things.”

Sergiu Vescan echoed that sentiment, highlighting the practical learning opportunity.

“I learned a lot of new things about the AI field,” he says, “and I had the opportunity to write Progress OpenEdge code to send POST requests to Agentic RAG, which was the first time in my life.”

What’s Next for the Project?

Future enhancements could include deeper automation, tighter integration with OpenEdge APIs and newer AI capabilities such as the MCP Connector for ABL and the OpenEdge MCP Server—both discussed as potential next steps toward production‑ready AI workflows.

Why It Matters

This hackathon project demonstrates a practical, business‑focused approach to AI adoption. Instead of replacing existing systems, the team used AI to augment an OpenEdge‑based application—saving time, improving accuracy and keeping developers in control.

It’s also a strong example of how OpenEdge continues to evolve alongside modern technologies like AI, enabling innovation without forcing teams to abandon the systems they already rely on.

As Razvan summed it up simply:

“It was a great experience.”

Discover What’s Possible with Progress OpenEdge

This project shows how organizations can use AI with existing OpenEdge applications to automate workflows and improve efficiency without rewriting their systems. With modern integration capabilities from Progress OpenEdge, developers can quickly add intelligent features while preserving core business logic.

• Get started with OpenEdge MCP Server to begin integrating AI into your applications
• Explore OpenEdge MCP Connector for ABL to extend AI‑driven workflows

OpenEdge 13.0 is the first release in the 13.x release series, delivering new capabilities quickly through a shorter‑lived innovation release that leads into the future long‑term supported release.

What’s New for Developers

For developers, OpenEdge 13.0 delivers language and tooling enhancements that make it easier to write modern, maintainable code and integrate with today’s technologies.

• ABL now supports both reading and writing numbers in scientific notation, eliminating the need for manual parsing routines when working with very large or very small values. Scientific notation is stored using existing data types—such as INTEGER, INT64 and DECIMAL—so existing limits, like the 50‑digit DECIMAL precision , still apply.
• User‑defined generics extend beyond the earlier generic collections model, enabling developers to define classes and interfaces with type parameters that are specified when the class is declared or instantiated, which reduces duplicate class definitions, improves compile‑time type checking and lowers technical debt in large ABL codebases.
• The AI coding assistant that previously shipped with OpenEdge 12.8 as a separate ChatGPT plugin for Progress Developer Studio is now built directly into the IDE, providing embedded AI assistance for generating and refactoring ABL code without switching between the IDE and a browser.
• For teams using OpenEdge alongside .NET, OpenEdge 13.0 is certified for .NET 8, enabling access to newer libraries and performance improvements today, while certification for .NET 10 is planned for the next LTS release.

Beyond PDSOE, the MCP Connector for ABL supplies ABL syntax context to external IDEs such as VS Code so that AI assistants and tools “understand” ABL better and can generate more accurate code, with support for OpenEdge 13.0 features planned shortly after release.

Database Improvements for DBAs

Database administrators see significant gains in backup performance, diagnostics and configuration control, all aimed at improving operational efficiency.

• Multi‑threaded backups accelerate backups for large databases by using multiple worker threads, with multi‑threading enabled by default for online and offline backups and configurable through PROBKUP to tune or disable as needed, reducing maintenance windows.
• Offline index checks with IDXCHECK can now run using multiple threads, validating records for each key and key order more quickly, which shortens downtime for integrity checks and improves readiness for recovery operations.
• Client database request statement caching configuration has been enhanced so DBAs can set the cache size, the default cache level for future connections and the number of connections used for shared memory planning through new database parameters accessible via PROMON.
• To prevent diagnostic data collection from overwhelming deployments, two new broker parameters help control volume: one limits how often repeated diagnostic events of the same type are recorded, and another reports detailed information only for the top offenders driving those events, such as lock table overflows.

Together, these enhancements help DBAs complete backups and diagnostics faster, collect more actionable telemetry and maintain healthier production environments.

Stronger Security and Compliance for System Admins

System administrators gain stronger security controls and better alignment with regulatory requirements, particularly around cryptography and encryption.

• OpenEdge 13.0 introduces support for FIPS 140‑3, allowing organizations with an OpenEdge Advanced Security license to enable FIPS mode and configure the ESAM policy via the POLMAN utility, which is especially important for customers in regulated industries or those working with U.S. government entities.
• New ABL cryptography functions and attributes expand password hashing options, give administrators more control over hashing algorithms and enforce stricter error handling that prevents weak algorithms from being used, making it easier to detect and correct insecure configurations.
• Java Open Client applications gain enhanced configuration options to operate in FIPS‑aligned mode, including full control over certificate store details used to validate server certificates, which improves cryptographic practices even outside strict FIPS environments.
• The SQL engine now allows administrators to configure the encryption cipher for SQL column statistics in databases using Transparent Data Encryption (TDE), enabling online cipher changes without downtime, alignment with evolving security standards and closer adherence to internal policies and compliance mandates.

These capabilities help organizations strengthen their overall security posture while maintaining operational continuity.

How to Influence the Future of OpenEdge

The OpenEdge Ideas portal provides a direct channel to submit enhancement requests, vote on existing ideas and share real‑world usage insights, with every submission reviewed by the product team as input into future innovation.

There is also the OpenEdge Customer Validation Program (CVP) that gives customers early access to pre‑release software, quarterly objectives, sprint reviews and more, allowing customers to test new capabilities in their environments and provide feedback that can influence features before general availability.

OpenEdge 13.0 marks an important step toward secure, AI‑ready modernization for OpenEdge applications, combining language enhancements, operational improvements and stronger security capabilities.

Watch the webinar to learn more about OpenEdge 13.0.

That was the central takeaway from our recent webinar, “Progress Application Server (PAS) for OpenEdge Best Practices,” where Chad Thomson, Senior Principal Consultant at Progress, walked through what OpenEdge teams need to understand before, during and after a move from Classic AppServer or WebSpeed environments to PAS for OpenEdge.

From architectural differences and deployment planning to security, testing and performance tuning, the session emphasized one clear message: success with PAS for OpenEdge starts with setting the right expectations and being intentional from day one.

PAS for OpenEdge Is Not Classic AppServer—and That’s the Point

While PAS for OpenEdge replaces Classic AppServer and WebSpeed brokers, it operates very differently. PAS for OpenEdge is built on Apache Tomcat and communicates entirely over HTTP/HTTPS. That architectural shift introduces new considerations around request duration, concurrency, threading and network behavior.

Unlike classic environments where concurrency required multiple agents, PAS for OpenEdge uses multi‑threaded agents, allowing a single agent to service many concurrent ABL sessions. This enables greater scalability, but only when applications are designed and configured with that model in mind.

Treating PAS for OpenEdge as a “drop‑in replacement” without acknowledging these differences is one of the most common causes of migration challenges.

Start with Architecture and Deployment Planning

PAS for OpenEdge may look like a web server, but its role is closer to a broker replacement than a traditional UI tier. For most teams, that means starting where their classic AppServer brokers live today and working outward.

Key planning considerations include:

• Network paths and firewalls between clients and PAS for OpenEdge
• Required ports and transport protocols
• Existing broker definitions and client connection patterns
• Ancillary services and integrations that depend on AppServer or WebSpeed

A clear picture of the full application landscape, including external consumers and background processes, is critical to avoiding surprises later.

Configuration, Tooling, and Operational Differences Matter

Migration also means adopting new tools and processes.

Classic utilities like asbman, wtbman, and mergeprop do not apply in a PAS for OpenEdge world. Instead, teams must become comfortable with:

• PASMAN and TCMAN for instance management
• oeprop and secprop for configuration and security changes
• A broader set of configuration files, including openedge.properties and catalina.properties

Logging also changes significantly. In addition to ABL agent logs, teams must account for Tomcat logs, access logs, and Spring Security logs. Understanding where to look, and how much logging is appropriate for production versus troubleshooting, becomes a key operational skill.

Testing Is Not Optional—It’s the Strategy

Successful PAS for OpenEdge migrations require more than functional validation. Teams must:

• Stress test for concurrency
• Test realistic production workloads
• Test failure scenarios
• Validate behavior under load and during shutdowns

Defaults are rarely correct for real‑world applications. Only through testing can teams determine the right number of agents, sessions, and Tomcat threads for their specific workloads.

Just as importantly, Chad encouraged teams to target production early, using production‑like settings even in development environments, to avoid last‑minute surprises. And if you do test, test again.

Security Must Be a First‑Class Citizen

Security should not treated as an afterthought, it should be as foundational.

PAS for OpenEdge is secure by default, but teams must explicitly enable the transports and features they need. HTTPS is always available, and encryption in transit should be implemented early, not postponed until go‑live.

The session strongly recommended:

• Treating TLS/HTTPS as mandatory
• Leveraging Spring Security for authentication and authorization
• Integrating with enterprise identity providers such as LDAP, Active Directory, OAuth2, or OIDC
• Avoiding custom password handling in ABL code whenever possible

Reverse proxies were highlighted as a best practice for both security and flexibility, allowing organizations to protect PAS for OpenEdge instances while enabling URL rewriting, load balancing and routing.

Migration Is Also an Opportunity

Handled thoughtfully, the move to PAS for OpenEdge can result in:

• More scalable deployments
• Stronger security posture
• Better operational visibility
• Cleaner, more resilient application architectures

Final Takeaway

Migrating to PAS for OpenEdge is not just about getting off classic AppServer or WebSpeed, it’s about adopting a modern, scalable and secure runtime for OpenEdge applications.

Teams that succeed are the ones that plan deliberately, test relentlessly, embrace PAS for OpenEdge architectural model, and treat security and operations as core design considerations, not afterthoughts.

PAS for OpenEdge rewards preparation. And when approached with the right mindset, it becomes a foundation for the next phase of OpenEdge application growth.

Watch the webinar recording to dive deeper into PAS for OpenEdge migration best practices and real‑world guidance.

Progress Labs Discord is a user-driven space where OpenEdge customers, partners and developers come together to share ideas, explore what’s new and learn from real‑world experiences across the OpenEdge user community, AI and developer tooling. It’s designed to be informal, collaborative and hands‑on, complementing existing Progress communities with a faster, more conversational way to engage.

Why Join Progress Labs?

Learn from Real‑World Experience

This is a place to swap patterns, share lessons learned and talk through real implementations. Developers and Progress teams alike all bring different perspectives, making the conversation practical and grounded.

Build with the Community, Not In Isolation

Progress Labs is about collaboration—a place where you can share feedback and connect directly with others working on similar challenges. As more people participate, the community continues to evolve based on what members care about most.

A Space to Explore, Contribute and Connect

Progress Labs isn’t a replacement for the Progress Community. It’s an additional space to explore ideas, experiment and engage in a dynamic way.

The Progress Community is the best place to go for varied product content like product announcements, how-to articles, searchable knowledge banks and trainings, to more user-generated content like code shares and community forums, that you can keep referencing over time. When you’re looking for authoritative information, official updates or resources you can easily find again, the Progress Community is your home base.

Progress Labs on Discord is all about real‑time conversation and collaboration. It’s where OpenEdge customers, partners and developers gather to share ideas, explore what’s new and learn from experimentation that’s happening right now. The vibe is informal and community‑driven.

Whether you’re an OpenEdge developer or simply curious about what others are building, you’re welcome to jump in, introduce yourself and join the conversation.

Join Progress Labs on Discord and be part of what’s next.

That was the core message of our recent webinar, “Application Transformation – A Cultural Shift,” where Progress experts Chris Longo, Service Delivery Manager for OpenEdge Applications in North America, and Jagdish Pai, Principal Consultant and Modernization Team Lead, explored what application transformation truly looks like in 2026.

From defining business objectives and embracing continuous improvement to leveraging AI‑powered tooling like the OpenEdge MCP Connector for ABL, the session highlighted how organizations can modernize confidently without disrupting what already works.

Modernization Starts with Business Objectives, Not Technology

Modernization is a business‑first initiative. Before touching code or architecture, organizations need clarity around their long‑term objectives.

A true cultural shift requires alignment across developers, IT leaders, business stakeholders, and end users. That starts by asking the right questions:

• How do we deliver data that drives better business decisions?
• How can we shorten development cycles while improving quality?
• Are our workflows efficient, intuitive, and adaptable?
• Can our application evolve as markets, users, and technologies change?
• Are security, authentication, and data protection built in, not bolted on?

Modernization succeeds when it is tied directly to business outcomes, not just technical upgrades.

This is why Progress Professional Services often begins with an application assessment evaluating the current application, understanding organizational goals and building a multi‑year roadmap that keeps modernization on track even as priorities shift.

What “Modernization” Really Means Today

Modernization isn’t a one‑time project or a rip‑and‑replace effort. It’s about realigning an application with current and future business needs.

There are several key dimensions of modern applications:

• Agility: The ability to respond quickly to changing requirements
• Efficiency: Streamlined workflows that reduce friction and errors
• User Experience: Desktop, web, mobile, or omni‑channel access
• Innovation Readiness: Being positioned to adopt AI, analytics, and emerging technologies

Legacy applications often struggle because of tightly coupled architectures, outdated UI frameworks and limited scalability. Modernization breaks those constraints by decoupling user experience from business logic and embracing continuous improvement rather than large, disruptive releases.

Importantly, modernization doesn’t have to be “all or nothing.” Organizations can modernize incrementally, improving UX, exposing APIs or introducing AI step by step.

Continuous Improvement Is the Cultural Shift

A recurring theme throughout the session was the importance of continuous improvement.

Instead of waiting months (or years) for a major release, modern teams deliver value in smaller, focused increments. This approach:

• Delivers faster ROI
• Encourages regular stakeholder feedback
• Reduces risk
• Improves alignment between IT and the business

This shift requires more than new tooling. It requires communication, change management and shared ownership. Stakeholders must stay engaged throughout the journey, not just at kickoff or go‑live.

A clear, adaptable roadmap helps teams stay aligned while remaining flexible enough to evolve as priorities change.

Unlocking Data Through APIs

One of the most critical aspects of modernization is unlocking application data.

Rather than exposing databases directly, an API‑first approach that leverages existing business logic. APIs allow organizations to:

• Securely expose data with proper authentication and authorization
• Apply business rules, validation, and transformations
• Enable integration with web, mobile, third‑party applications and AI

By building an API layer, organizations free their data from legacy interfaces and make it accessible wherever it delivers value.

Modern UX Is About Experience, Not Just Screens

User experience remains a major driver of modernization, but expectations have evolved.

Modern UX now includes:

• Personalized, role‑based experiences
• Accessibility and compliance
• Multi‑modal interaction (text, voice, touch, and AI prompts)
• Experiences designed with AI in mind from the start

Users increasingly expect applications to anticipate needs, much like consumer platforms such as Netflix or Alexa, rather than forcing rigid, menu‑driven workflows.

AI Is No Longer Optional in Modern Applications

One of the most compelling parts of the webinar focused on AI‑powered modernization, particularly through the OpenEdge MCP Connector for ABL.

The MCP Connector acts as an AI bridge between ABL development environments and large language models (LLMs), enabling developers to:

• Generate and refactor ABL code
• Convert procedural code to modern OOABL patterns
• Automatically generate unit tests and documentation
• Identify errors, deprecated constructs, and upgrade issues
• Reduce technical debt during OpenEdge 12.8 upgrades

By combining LLMs with deep OpenEdge knowledge, the MCP Connector becomes a living knowledge base, accelerating modernization while reducing risk.

This is especially valuable during upgrades, refactoring, and API enablement, where repetitive and error‑prone tasks can slow teams down.

MCP Connector vs. MCP Server: Different Roles, Same Vision

The Q&A clarified a common question: What’s the difference between the MCP Connector and the OpenEdge MCP Server?

• MCP Connector for ABL focuses on development productivity, helping developers write, refactor, test, and modernize ABL code using AI.
• OpenEdge MCP Server enables runtime AI integration, allowing AI agents to interact with application APIs, chain multiple API calls, and answer business questions in natural language.

Together, they support both sides of modernization: how applications are built and how they are used.

Progress Is Here to Help

For organizations ready to get started, Progress offers professional services engagements to help teams:

• Configure MCP Connector and AI‑enabled IDEs
• Integrate with existing OpenEdge environments
• Train developers on effective AI‑assisted workflows
• Apply modernization best practices to real customer codebases

Final Takeaway

Application transformation in 2026 is no longer just about technology upgrades. It’s about culture, mindset, and continuous evolution.

By aligning modernization with business objectives, embracing incremental improvement, unlocking data through APIs, and leveraging AI‑powered tooling, organizations can modernize with confidence, without losing the value embedded in their existing OpenEdge applications.

Modernization isn’t a destination. It’s a journey and the right culture makes all the difference.

Watch the webinar recording to learn more.

Every great innovation starts with a spark, and for David, 31, and Alireza, 26, that spark was a shared passion for solving real-world problems with technology. Both students, with backgrounds in software engineering and a keen interest in artificial intelligence (AI), joined the OpenEdge AI Hackathon that took center stage at the Leeds Digital Festival with a bold vision: to build systems that make a tangible difference in industries like healthcare, sales and manufacturing.

First Steps with Progress OpenEdge

For David and Alireza, the hackathon marked their first experience with Progress OpenEdge. “Truth be told, it was our first time using OpenEdge and its data,” they explained. “We worked heavily on it, analyzing and filling in missing values to train our AI model. The support from the OpenEdge team was incredible—it made this one of the best experiences of our lives.”

The OpenEdge Classroom Edition played a critical role in accelerating their onboarding. From a developer perspective, the availability of a ready-to-use environment eliminated common setup friction such as database configuration, schema bootstrapping and access management. This allowed the team to immediately focus on learning OpenEdge fundamentals, ABL concepts, database schemas and query patterns, while simultaneously using the data into their AI workflow.

Their project, Demand IQ, aimed to help sales managers optimize inventory by predicting product demand and balancing overstocks and stockouts. Using advanced data imputation techniques and time series transformers, they built a model capable of forecasting demand up to seven days ahead, with plans to extend this horizon to a full month.

Overcoming Challenges and Building Value

David and Alireza’s hackathon journey was a testament to creativity and determination. As first-time OpenEdge users, they quickly adapted to the platform, leveraging its capabilities to build their AI-powered solution. With guidance from the OpenEdge team, they engineered innovative approaches to data preparation and model training, making sure their project delivered actionable insights for businesses.

A Vision for the Future

David and Alireza’s journey didn’t end with the hackathon. They’re already working on new projects, developing novel ideas to improve model accuracy and extend prediction horizons.

At present, they are building the API layer of their AI service, designed to abstract model inference, data access and future agent-based workflows. The goal is to expose prediction and analytics capabilities via well-defined endpoints that can integrate cleanly with enterprise applications.

As a next architectural step, they are actively considering the adoption of Progress Agentic RAG. The motivation is to enable intelligent agents that can reason over both structured OpenEdge data and contextual enterprise knowledge, enabling advanced use cases such as dynamic querying, root-cause analysis and decision support.

The release of the OpenEdge MCP Server is a key enabler in this roadmap. Its ability to facilitate secure and efficient access to OpenEdge data significantly lowers the barrier for integrating Agentic RAG with existing OpenEdge-based systems, making it feasible to embed AI agents directly into enterprise workflows.

Reflecting on their experience, David said,

“I am absolutely eager to continue this project with OpenEdge. It’s really perfect for all students, even for all senior people or mid-level people.”

Alireza said, “In a world where everything is being integrated with AI, we want to leverage AI-centric frameworks to extend an organization’s predictive capabilities. Starting with OpenEdge-based systems is a powerful foundation, given their mature data models, enterprise reliability and seamless integration with modern AI workflows.”

Why This Matters

These hackathons are more than a competition—it’s a launchpad for innovation. David and Alireza’s story shows how curiosity, collaboration and a willingness to tackle tough challenges can lead to solutions that benefit entire industries. Their work is a testament to the power of combining AI with OpenEdge, and it’s just the beginning.

Discover What’s Possible with Progress OpenEdge

Learn more about how OpenEdge can help you modernize, innovate and integrate AI into your applications.

Progress® OpenEdge® 13.0 marks a pivotal moment for OpenEdge customers—introducing the first release in the 13 series and setting the stage for continuous innovation, modernization and security leading up to the next Long-Term Support (LTS) milestone.

As organizations navigate evolving business, regulatory and technical demands, OpenEdge 13.0 helps you modernize confidently, comply with ease and prepare your applications for a secure, AI and cloud-driven future.

Strengthening the OpenEdge Security Posture

Every release of OpenEdge builds on a commitment to protecting mission-critical applications, and version 13.0 takes that even further. Key enhancements include:

• Foundational FIPS 140-3 enablement for the OpenEdge Database and PAS for OpenEdge, helping organizations move toward compliance with U.S. government and regulated industry requirements.
• Updated cryptographic libraries aligned with the latest industry standards to defend against known exploits and emerging threats.
• External Security Administration Manager (ESAM) policy enhancements that strengthen the configuration and management of OpenEdge installations.
• Modernized ABL cryptography functions powered by these new libraries for stronger, faster, more reliable encryption.

Why Updated Cryptography Matters

It’s easy to assume that encrypted data is automatically safe, but outdated cryptography often hides significant risks. Older algorithms and libraries can contain publicly reported vulnerabilities, leaving even encrypted information susceptible to compromise.

OpenEdge 13.0 eliminates this gap by adopting the latest cryptography standards, improving:

• Data confidentiality and integrity
• Application performance and reliability
• Compliance readiness for regional, national, and industry mandates

With today’s distributed and cloud-connected architectures, robust encryption isn’t optional. It’s a fundamental requirement for maintaining trust and resilience.

The Value of FIPS 140-3 Enablement

FIPS 140-3 is a U.S. government standard for cryptographic modules, a rigorous benchmark for how encryption technologies are implemented and validated. It’s required for any organization that handles sensitive or classified information for federal agencies, the Department of Defense and security-conscious sectors such as healthcare and financial services.

But FIPS 140-3 doesn’t just matter in the U.S… Its influence extends globally. Around the world, regulatory bodies and enterprises view FIPS certification as proof of strong security maturity and cryptographic integrity. Many international frameworks, such as ISO/IEC 19790 and the EU’s cybersecurity standards, align with or reference FIPS requirements, making adherence a powerful differentiator across regions and industries.

By implementing foundational FIPS 140-3 support in OpenEdge 13.0, Progress gives customers a head start toward compliance and a pathway to stronger market credibility. This advancement helps organizations not only protect data but also capitalize on new growth opportunities worldwide.

Key business advantages include:

• Access to government and regulated contracts – A prerequisite for defense, healthcare and public-sector engagements in the U.S. and other regions adopting equivalent security criteria.
• Competitive differentiation – Demonstrates that your solution meets globally recognized government-grade encryption standards, setting you apart in crowded RFP and vendor-assessment processes.
• Customer trust and audit confidence – FIPS 140-3 validation signals to enterprise buyers, auditors and regulators that your applications are built on certified cryptography standards.
• Global market expansion potential – FIPS-compliant solutions are often fast-tracked for acceptance in international procurement, enabling you to pursue business with global enterprises and governments that respect FIPS-integrated frameworks.

For many organizations, FIPS 140-3 support represents a strategic accelerator, driving up to more addressable market opportunity, supporting premium pricing models for verified secure applications and enhancing cross-border credibility with customers who demand high security assurance, wherever they operate.

A Foundation for What’s Next

OpenEdge 13.0 delivers more than just compliance, it delivers confidence. By adopting modern cryptography and introducing foundational FIPS 140-3 capabilities, it supports that your applications are not just protected against today’s threats, but ready for tomorrow’s requirements.

Security innovation doesn’t stop here, the 13 series is built to continually advance protection, modernization, and performance. With OpenEdge 13.0, you’re not only future-ready, you’re future-secure.

Learn more about the OpenEdge 13.0 release.

Prerequisites

• Ubuntu Desktop 24.04.3 LTS
• Python 3.11 or higher
• Docker Community Edition (tested using Docker 29.1.2)
• Distribution package for the OpenEdge MCP Server for Linux (available from the ESD): OPENEDGE_MCP_SERVER_1.0.0_LIN64.zip
• Progress Data Object Service running on the network
• VS Code and GitHub Copilot access to use the OpenEdge MCP Server from VS Code

Installation

1. Extract the MCP Server Packages

Start by extracting the Linux-specific MCP Server distribution package:

This creates the working directory (~/demo) that contains everything needed to run the MCP Server locally.

Using the OpenEdge MCP Server

Navigate to the directory where you installed the server:

2. Load Docker Images

The MCP Server ships with container images that need to be loaded locally:

3. Verify Your Environment

Use the mcpgen doctor command to confirm your configuration is ready. The tool will prompt you for your Python command and perform environment checks:

4. Generate an OpenAPI Spec

To generate an OpenAPI specification from an OpenEdge Data Object Service, use:

For example: “http://192.168.10.132:8810/Sports/web/pdo/SportsService”

This is one of the sources for service information that the OpenEdge MCP Server can use.

5. Start the MCP Server 

Once you have an OpenAPI spec (for example, openapi_SportsService.yml), spin up a new MCP Server instance:

1. ./mcpgen up --spec <openapi-spec>

Smoke tests will run automatically as part of the startup process.

Using the OpenEdge MCP Server with GitHub Copilot in VS Code

One of the most powerful parts of the MCP Server is the ability to securely expose OpenEdge services to AI models like Claude through GitHub Copilot in VS Code.

1. Open the Generated Server Directory

2. Add the MCP Server in VS Code

1. Open View -> Command Palette...
2. Run: MCP: Add Server...
3. Select HTTP (HTTPS) as the connection method
4. Enter a temporary URL, such as:
   
a. http://localhost:3000
5. Choose Workspace as the configuration target
6. Replace the content of the newly created.vscode/mcp.json with the version from client/mcp.json
7. Click Start next to the server entry in the MCP panel:
   

3. Test It Through Copilot

1. Open the Chat view in VS Code and enter a prompt such as: 1. Please list customers in Ohio.
2. Copilot will ask permission to run the request through the MCP Server. Once allowed, it will return the customer list directly drom the Progress Data Object Service.

Related Resources

For troubleshooting, here is OpenEdge MCP Server-specific documentation:

• Introduction to the OpenEdge MCP Server
• Install OpenEdge MCP Server
• Step 4: Provide OpenAPI Specification

Learn more about AI capabilities within the OpenEdge platform.

Prerequisites

• Windows 11
• Python 3.11 or higher
• Docker Desktop or Rancher Desktop
• Distribution package for the OpenEdge MCP Server for Windows (available from the ESD): OPENEDGE_MCP_SERVER_1.0.0_WIN64.zip
• Progress Data Object Service running on the network
• VS Code and GitHub Copilot access to use the OpenEdge MCP Server from VS Code

Installation

Note: The following commands use the Windows Command Prompt.

1. Extract the MCP Server Packages

Start by extracting the Windows-specific MCP Server distribution package:

This creates the working directory (c:\demo) that contains everything needed to run the MCP Server locally.

Using the OpenEdge MCP Server

Navigate to the directory where you installed the server:

2. Load Docker Images

The MCP Server ships with container images that need to be loaded locally:

3. Verify Your Environment

Use the mcpgen doctor command to confirm your configuration is ready. The tool will prompt you for your Python command and perform environment checks:

4. Generate an OpenAPI Spec

To generate an OpenAPI specification from an OpenEdge Data Object Service, use:

For example: “http://192.168.10.132:8810/Sports/web/pdo/SportsService”

This is one of the sources for service information that the OpenEdge MCP Server can use.

5. Start the MCP Server 

Once you have an OpenAPI spec (for example, openapi_SportsService.yml), spin up a new MCP Server instance:

1. mcpgen.bat up --spec <openapi-spec>

Smoke tests will run automatically as part of the startup process.

Using the OpenEdge MCP Server with GitHub Copilot in VS Code

One of the most powerful parts of the MCP Server is the ability to securely expose OpenEdge services to AI models like Claude through GitHub Copilot in VS Code.

1. Open the Generated Server Directory

2. Add the MCP Server in VS Code

1. Open View -> Command Palette...
2. Run: MCP: Add Server...
3. Select HTTP (HTTPS) as the connection method
4. Enter a temporary URL, such as:
   
a. http://localhost:3000
5. Choose Workspace as the configuration target
6. Replace the content of the newly created.vscode\mcp.json with the version from client\mcp.json
7. Click Start next to the server entry in the MCP panel:
   

 

3. Test It Through Copilot

1. Open the Chat view in VS Code and enter a prompt such as: 1. Please list customers in Ohio.
2. Copilot will ask permission to run the request through the MCP Server. Once allowed, it will return the customer list directly drom the Progress Data Object Service.

Related Resources

For troubleshooting, here is OpenEdge MCP Server-specific documentation:

• Introduction to the OpenEdge MCP Server
• Step 4: Provide OpenAPI Specification
• Develop a Progress Data Object Service

Learn more about AI capabilities within the OpenEdge platform.

Why OpenEdge 13.0 Matters

Regulated industries like finance, healthcare and government face pressures to meet evolving security and compliance mandates. OpenEdge 13.0 is designed to break down barriers, empowering you to modernize confidently, without disruption or risk.

The Value of OpenEdge 13.0

• FIPS Mode Support: Introduces initial FIPS 140-3 support for critical OpenEdge components, facilitating compliance for common scenarios in regulated industries. Applications that encrypt data, manage keys or handle sensitive information must use FIPS 140-validated cryptographic modules.
• Updated Cryptographic Libraries: Uses the latest cryptographic libraries to help adhere to industry-established standards, regulations and best practices.
• User-Defined Generics: Enables Advanced Business Language (ABL) developers to craft reusable, type-safe code structures, improving maintainability and reducing debugging cycles.
• Scientific Notation Support: Promotes data integrity with full parsing of exponential numeric formats, enabling integration with modern APIs and industry standards.
• Threaded Offline Backup: Reduces window maintenance and downtime by allowing multi-threaded execution of database backup operations.
• Threaded Offline Index Check: Accelerates integrity diagnostics via concurrent index validation during offline periods, reducing recovery times.
• OpenEdge Memory Profiler: Identifies memory-related issues within OpenEdge applications.
• OpenEdge Command Center (OECC): Centralizes management of multiple PAS for OpenEdge instances and OpenEdge Databases.

What Does This Mean for You?

OpenEdge 13.0 is more than a collection of new features. It’s a strategic release for secure innovation and sustained transformation. By adopting OpenEdge 13.0, you’re not just meeting today’s requirements; you’re preparing your business for the future.

The world is changing fast. With OpenEdge 13.0, you have the tools to stay ahead—helping protect your business, your data and your reputation.

Ready to learn more? Read our datasheet and get started today!

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
  sources

• Sending 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
  APIs

• Integrate 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

If you missed the live event, here’s a quick recap of what we covered, plus answers to some of the top questions participants asked.

What We Covered in the Webinar

We opened the webinar by setting a shared foundation around several key concepts shaping how AI is being applied in OpenEdge environments today. A major focus was clarifying common terminology—especially Model Context Protocol (MCP)—and grounding it in practical, real‑world value rather than hype.

Understanding MCP

The Model Context Protocol (MCP) is an open standard that enables AI systems to securely access business‑specific data, APIs, files and services. Instead of relying on custom integrations, MCP provides a unified, interoperable way for AI agents to communicate with back‑end systems of all types.

This allows organizations to move beyond internet‑based AI responses and bring their own structured, contextual, and secure data into the AI workflow.

Why MCP Matters

Before MCP, building AI assistants or agentic solutions typically resulted in:

• High maintenance overhead due to multiple SDKs, LLMs and integration layers
• Security risks from hardcoded credentials or over‑permissioned access
• Inconsistent performance with no standard for caching or context handling
• Scalability limitations as each new service introduced exponential complexity

MCP standardizes these interactions, reducing technical debt, improving security, and accelerating AI adoption. Should we add in something about the benefits of using industry standards here?

The OpenEdge MCP Ecosystem

1. OpenEdge MCP Server

The OpenEdge MCP server exposes OpenEdge REST/WEB services and PAS for OpenEdge-based business logic as MCP‑standard tools. Through this, AI agents can:

• Interact with OpenEdge data
• Query services
• Perform business‑specific operations
• Receive structured outputs

All in a secure, governed way.

2. OpenEdge MCP Connector for ABL

The connector enhances developer productivity by providing AI with:

• Access to ABL documentation
• Syntax references
• Code examples
• Best practices

Common Questions From the Webinar

Here are some of the top questions participants asked:

1. What does the OpenEdge backend need to work with the MCP Server?

The OpenEdge backend must expose its application logic as RESTful services (REST/WEB) and provide an OpenAPI specification. The OpenEdge MCP Server requires only a valid OpenAPI spec as input to communicate with backend services.

If your application uses business entities, the mcpgen CLI provided with the OpenEdge MCP Server can automatically generate an OpenAPI specification for you.

2. Can MCP Server be deployed locally?

Yes. The OpenEdge MCP Server can run entirely within a local environment. You can generate multiple MCP Servers, and each server can be associated with a specific OpenEdge backend (RESTful services running on PAS for OpenEdge).

For restricted or air‑gapped networks, the MCP Connector also supports offline rules files.

3. Does MCP require internet access?

No. The OpenEdge MCP Server itself does not require internet access and does not communicate directly with an LLM. It functions as a server that interacts with an MCP Client.

The MCP Client, which communicates with the MCP Server, requires LLM and internet access to perform natural‑language processing and response generation.

4. Can the MCP Connector work with our existing codebase?

Yes. The MCP Connector can analyze existing ABL code, follow organization‑specific standards, and assist with modernization initiatives—such as converting procedural code to OOABL, adding structured error handling, and improving design patterns.

5. Does the MCP Server provide direct access to the database?

No. All access is enforced through REST/WEB services or business entities, maintaining strong security boundaries.

Business entities can be easily generated for selected database tables and fields, providing controlled RESTful access to your data without exposing the database directly.

6. Does this support older OpenEdge versions?

The MCP Connector supports language constructs for OpenEdge 12.2 and 12.8, with planned updates for OpenEdge 13.0.

If you are running an older version of OpenEdge, we recommend modernizing with the help of the Progress Services team to ensure compatibility and get the most value from MCP.

7. Can MCP help generate or refactor REST APIs?

Yes. When combined with the MCP Connector’s documentation and examples, AI can guide—and in many cases generate—the creation or refactoring of REST endpoints.

8. Is PAS for OpenEdge required?

Yes. For OpenEdge applications with business logic, deployment to PASOE is required.

The solution follows best‑practice security patterns by validating user identity across all layers—from the OpenEdge MCP Server, to PAS for OpenEdge, and down to the database.

How can we get started faster with MCP and AI services?

To help teams adopt AI‑assisted development faster, Progress offers the AI Coding Assistant for ABL Accelerator Service, a tailored Professional Services engagement built around the OpenEdge Model Context Protocol (MCP) Connector for Advanced Business Language (ABL).

The OpenEdge MCP Connector for ABL extends AI coding assistants directly into the development environment, enabling developers to work with AI‑powered features without switching tools or disrupting workflows. By combining Generative AI with Retrieval‑Augmented Generation (RAG) grounded in your ABL code, documentation and development standards, the MCP Connector provides context‑aware guidance designed specifically for how OpenEdge teams build and modernize applications.

Through a focused Professional Services engagement, Progress experts help set up the development environment, configure AI‑powered tooling and lead hands‑on onboarding and enablement. This approach accelerates modernization, improves code quality and helps development teams integrate AI into their daily workflows with confidence.

Contact Progress Professional Services to learn how AI‑powered OpenEdge development tools and the MCP Connector for ABL can support your modernization and developer productivity goals.

Learn more.

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

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/whatismcp-webinar

For OpenEdge developers, while AI-powered coding assistants like GitHub Copilot, VS Code, and Claude are game-changers for mainstream languages, they don’t truly understand OpenEdge Advanced Business Language (ABL). The result? Out-of-the-box AI tools often generate inaccurate ABL code, leaving developers fixing errors, managers struggling to enforce standards and IT leaders worrying about modernization risks and costs.

This gap is why we built the Progress OpenEdge Model Context Protocol (MCP) Connector for ABL—a purpose-built bridge between your AI assistant and your unique OpenEdge environment. It’s the human-centric AI solution designed specifically to accelerate ABL modernization and boost productivity across your teams.

Key Capabilities

• Automate repetitive tasks like boilerplate code, refactoring and unit
  test generation

• Leverage your organization’s rules and documentation at query time
  for compliant, aligned outputs

• Modernize outdated ABL into OpenEdge 12-ready syntax and practices

• Get real-time, in-context support that adapts as your project evolves

Beyond the Connector: AI Coding Assistant Service

Alongside the product, we offer the OpenEdge AI Coding Assistant Service to help you implement, customize and scale AI-enabled workflows. This includes indexing your codebase, enforcing compliance and supporting modernization initiatives like refactoring for OpenEdge 12 and PAS for OpenEdge.

Learn more.

Move Faster, Reduce Risk, Modernize with Confidence

With the OpenEdge MCP Connector for ABL, your team gains a tailored AI coding partner that understands your environment, enforces your standards and accelerates your modernization roadmap.

It’s time to ship ABL code faster, cleaner and more confidently with AI built for your needs, not somebody else’s.

Learn more about accessing the MCP Connector for ABL.