Progress Software has released a new version of Telerik and Kendo UI that takes artificial intelligence beyond developer assistance. The updates aim to enable developers to create applications where not only people interact but also AI agents capable of using interfaces, processing documents, querying enterprise data, and executing actions. Notably, support for WebMCP has been added, designed to give agents a more structured alternative to visual recognition and screen scraping.
The key points of Telerik and Kendo UI in 20 seconds
- Progress enhances Telerik and Kendo UI with tools aimed at developing applications prepared for AI agents.
- WebMCP allows exposing interface functions in a structured way so that agents can utilize them.
- Fiddler now includes capabilities for programming assistants to analyze network traffic during debugging.
- Document libraries add tools for processing Excel files, extracting data, and generating files through agents.
- New features also include RAG, WinForms modernization, and AI-driven interface generation.
This release reflects a shift that is beginning to gain importance in software development. Until now, much of AI integration focused on helping programmers write code. The next phase involves preparing applications so that agents can work with them directly.
This poses a technical challenge. Traditional graphical interfaces are designed for people: buttons, menus, forms, and visual elements that users interpret easily. An agent needs to discover what can be done within an application, understand what each action means, and execute it reliably.
Progress aims to address both sides: using AI during development and building interfaces that can later be used by other AI systems.
WebMCP aims to prevent agents from having to interpret screens
One of the most interesting additions is the support for WebMCP within Progress’s interface tools.
Current agents can handle web pages through various techniques. Some use vision models to interpret on-screen content; others inspect the Document Object Model (DOM), automate browser actions, or employ screen scraping.
These work but can be fragile.
A change in button position, layout modification, or website updates can cause automation to break.
WebMCP proposes an alternative approach: enabling a web application to expose certain functions in a structured manner for agents to discover and use.
This can be illustrated with an example.
An AI needing to book an appointment might try to open a page, visually locate the calendar, select a date, find an available time slot, and click the appropriate button.
A dedicated agent-friendly interface could instead directly indicate which operations are available, their required parameters, and what each returns.
The human would still see and use the usual graphical interface, but the agent would have a software-optimized layer.
Progress suggests this approach can reduce dependence on visual automation techniques and make interactions with applications more reliable for agents.
Fiddler will enable AI assistants to view network traffic
AI also directly integrates into tools used by developers.
Progress introduces Agent Skills for Fiddler, its well-known platform for debugging and analyzing HTTP traffic.
The idea is to give programming assistants access to the context a developer typically observes when troubleshooting.
An agent could analyze network traffic, detect abnormal behaviors, and provide insights about potential causes and solutions.
This addresses a limitation of current programming assistants.
While a model can analyze code within the context it receives, errors are not always within the file being viewed. They might be in an HTTP request, an API returning unexpected data, an incorrect header, or a communication issue between services.
Providing access to this information expands the debugging context.
Agents will also work directly with documents
Another part of the update involves the Telerik Document Processing Libraries (DPL).
Progress adds tools so agents can perform document operations within applications themselves.
These include extracting structured data, analyzing Excel spreadsheets, converting formats, and generating documents.
The company emphasizes that these operations can be integrated into existing applications without necessarily relying on external AI services for document processing.
This is especially valuable in enterprise environments.
An integrated agent could receive spreadsheets, extract specific information, structure data, and generate new documents using the available libraries.
Thus, AI shifts from merely discussing documents to actively working with them through specialized tools.
RAG now directly integrates with .NET applications
Progress is also incorporating Retrieval-Augmented Generation (RAG) capabilities for .NET developers.
RAG allows connecting a large language model with external information sources outside of its original training data.
In a business context, this could mean a system consulting internal manuals, contracts, technical documentation, or data repositories before crafting a response.
The new version enables integration of .NET applications with Progress’s RAG-as-a-Service offering, allowing models to operate on unstructured enterprise data.
Compared to a general-purpose chatbot, the key is the context supplied.
An application can feed only the relevant information to the model, resulting in responses informed by organizational documentation.
While this doesn’t eliminate issues like inaccurate model responses or guarantee correctness, it provides a more suitable architecture for handling confidential or specialized knowledge.
AI will also be used to modernize WinForms applications
This update also addresses a less flashy but very common problem: legacy software.
Progress adds automation tools to convert old interfaces to Telerik UI for WinForms.
The process uses smart control mapping, code analysis, and Model Context Protocol (MCP)-based automation to assist in transformation.
The goal isn’t just to generate new interfaces from scratch but to reduce the effort required to modernize existing applications.
WinForms remains prevalent in many enterprise systems built over decades. Migrating these apps is time-consuming because they contain accumulated logic and components.
AI is beginning to help with this less visible work of maintaining and updating legacy software.
From using AI for programming to programming for AI
The Telerik and Kendo UI update is noteworthy for a reason beyond its new features.
In recent years, tools like GitHub Copilot and various programming agents have brought AI into the developer’s environment. Models write code, analyze repositories, run tests, and suggest fixes.
Now, an inverse movement is emerging: developers must build software with the understanding that other intelligent software will also be users.
This can influence application design.
A user-only interface must be visually understandable. An agent-enabled app must also clearly describe available operations, required inputs, and limits.
Standards and protocols like MCP and WebMCP point toward that goal.
Progress speaks of agent-ready applications, though adoption outside experimental projects remains to be seen. Nonetheless, this concept aligns with the evolution of agents: as they become capable of completing entire tasks, applications need to reliably provide mechanisms for interaction.
The future of AI in development may involve not only programmers using agents to write faster but also rethinking how software is built so humans and agents can utilize the same applications differently.
Frequently Asked Questions
What new features are added to Telerik and Kendo UI?
The update adds AI-driven interface generation, support for agent-ready applications, document processing, assisted debugging, RAG integration, and tools for modernizing WinForms applications.
What does WebMCP offer to AI agents?
It enables applications to expose certain functions in a structured way so agents can interact with them, reducing reliance on techniques like screen scraping.
What changes are there in Fiddler?
Progress introduces Agent Skills that give programming assistants visibility into network traffic to help detect issues during debugging.
Do the new tools include RAG?
Yes. Progress allows connecting .NET applications to their RAG-as-a-Service platform, enabling models to work with documents and other unstructured business data.
via: investors.progress
