The vragen.ai roadmap: from answers to control over conversations

At SWIS we see this development every day. Not only in the technology, but in how organizations set up their digital services. AI is no longer an experiment, it is becoming a fixed part of how you help visitors, guide them and prompt them to act.

So this year we are developing vragen.ai further, around two closely connected themes: the Conversation Management System and self-service.

The shift: from RAG to a Conversation Management System

We have written before about the change from traditional websites to a more conversational and generative kind of interaction (see the article on Frankwatching, in Dutch, and our earlier piece on agents, MCPs and widgets).

The heart of this development is simple, and important: it is no longer only about giving answers, it is about helping someone reach a goal. Users don't come to search, they come to achieve something. Which means the systems we use have to change too. A stand-alone chatbot or search function is no longer enough. What is needed is a system that understands intent, combines information, carries out actions and keeps an eye on quality and results at the same time. That is what the concept of a Conversation Management System is about.

Our roadmap works toward such a system step by step.

Theme 1: the Conversation Management System

Within this theme the focus is on strengthening the foundation that makes conversational interaction possible, manageable and scalable.

The knowledge layer as the foundation

One of the most important parts of vragen.ai is the knowledge layer. Where traditional systems often treat content as separate items, here it is all about coherence. The system has to understand where information comes from, how sources connect and in what context something is relevant.

We look beyond text at other forms of information too, such as images, videos and documents. How current the information is matters as well. Information changes constantly, and the system has to handle that without becoming less reliable.

So the focus isn't on adding as much new content as possible, but on organizing and using existing information intelligently. In the end the AI has to do more than find something, it has to understand how knowledge connects.

Brand identity and governance

Now that AI plays a larger role in how organizations communicate, it matters that this communication stays consistent and controlled. After all, the AI speaks on behalf of the organization.

So we are working on a central place where organizations can set down their tone of voice, along with the underlying rules and goals that steer how the AI behaves. That keeps the interaction in line with the organization's identity and positioning.

An important part of this is managing escalations. There are always situations where it is better for a person to take over the conversation, for instance with complex or sensitive questions, or when the AI is uncertain. The system has to make that handover smooth, with the full context preserved. That is how good collaboration between people and AI comes about.

From text to interaction

Conversational interfaces consisted mainly of text for a long time. Now we see a clear shift toward more visual and interactive forms. Within vragen.ai, answers are increasingly supplemented with interactive elements such as buttons, forms and choices. That changes the role of AI. The system doesn't only give information, it helps users take a next step right away.

Users no longer have to go to a separate page: they can carry out actions inside the conversation itself, such as making choices or entering details. Information and action come together in one interface.

Insight as a way to steer

As conversational interaction becomes more important, so does the need for insight. Not only into what happens, but above all into what it delivers.

Within vragen.ai we are working on analytics that show this from several angles. Organizations get insight into which conversations contribute to goals such as applications or conversions. It also becomes clear what users are after and what they need. And we look at quality: how well does the AI help, and where could it do better?

Analytics becomes more than reporting. It becomes a way to steer and keep improving.

From understanding to doing

One of the most important developments within such a system is the step from understanding to actually doing. That takes skills and flows: reusable building blocks that determine how the AI acts on an intent.

In practice this means a system doesn't only recognize what someone wants, but also knows which steps are needed to reach that goal. Sometimes that is a simple flow, sometimes a more complex process involving several systems.

Integrations play an important part here. Through a connection with a CRM, for example, the AI can do more than inform: it can carry out actions inside existing processes. The AI's role shifts from advising to supporting and executing.

Testing and manageability

As more people get involved in setting up and optimizing conversational systems, governance grows more important too. It has to be clear who can change what, and how changes are rolled out.

So we are investing in features that let organizations test and check new settings, content or flows before they go live. That makes for a clear process, and better safeguards quality and reliability.

Personalization as the next step

A conversational interface only becomes truly powerful when it takes the user's context into account. Think of a logged-in user, earlier interactions or personal preferences.

Within vragen.ai this is already partly possible through API and MCP connections. During a conversation the system can retrieve information from other systems in real time. That lets the AI adjust answers based on an account or a role, for instance.

As we develop further toward a complete Conversation Management System, we are exploring how personalization can play a bigger part.

Theme 2: self-service

Besides strengthening what the product can do, this year is also about making it more approachable.

vragen.ai has been around for three years now. In that time we have extended the platform and let it grow along with developments in AI. At the same time we see that managing it isn't always easy for organizations. The features are powerful, but not always immediately clear or simple to adjust. We want to change that.

More control for the user

The goal is for organizations to manage and improve their own conversational environment. That means you don't depend on our team for changes, but can steer what happens yourself.

For that, the system has to be more than powerful. It has to be clear and easy to understand.

A new admin environment

Together with our designers we are working on a new layout for the admin environment. Features will be grouped more logically and it will be clearer what you can adjust.

The focus is on clarity and simplicity. Not by making less possible, but by showing more plainly how everything connects.

Support for optimization

Beyond day-to-day management, we are also focusing on continuous improvement. Conversations deliver valuable insight, but that insight has to be turned into concrete action.

So we are working on features that help organizations quickly see where improvement is needed and how to make it happen.

Accessibility and multiple languages

In its conversations with visitors, vragen.ai is already multilingual. A visitor can ask a question in their own language and gets an answer in that language, even when the underlying website or knowledge base only holds Dutch content. So information stays accessible to a wider group of users, without an organization having to translate all its source content.

What is currently Dutch-only is the admin environment where organizations configure and improve vragen.ai. The multilingual work is therefore about that admin environment: we see more and more teams wanting to use it in other languages.

That way we make the conversation more accessible for visitors, and the management more accessible for organizations.

A roadmap as a direction, not an end point

Developing toward a Conversation Management System isn't an end point you reach in one go. It is an ongoing process in which technology, organization and use come together.

This roadmap takes steps in that direction. Not by changing everything at once, but by continuing to develop the parts that matter most.

Our team keeps working on vragen.ai in the months ahead, with one thing at the center: learning from what happens in practice.

Feedback and input are essential to that. By building and improving together with customers, we make sure vragen.ai keeps pace with AI and helps organizations get real value out of it.