From answering to acting: agents, (MCP) connections and widgets in practice
From showing information to getting things done: how agents, MCP connections and widgets let a website act.
Joris Meijer Co-founder, AI Lead
4 min read
The real shift comes when a website understands what someone wants and can act on it straight away. A visitor says, for example: "I want to apply for a permit." Or: "Book me an appointment for next Tuesday." Or simply: "I want to place this order." What they expect is not an explanation of the steps involved, but the process actually starting. That calls for a different way of thinking, and a different technical make-up of websites.
When language gets access to systems
As long as AI only generates text, the website stays informative. To get from conversation to result, language has to be able to work safely with the systems behind it: stock data, scheduling software, CRMs, internal processes.
That needs a standardized connecting layer. The Model Context Protocol (MCP) lets an AI retrieve data and prepare or carry out actions in a controlled way, within set business rules. The system can pull up an earlier order, check current availability and assemble a new basket, for instance, without the user having to work through several screens.
The difference isn't whether the processes exist. Websites have always been able to support those. The difference is in the access to them. AI makes it possible to drive systems straight from the conversation, without the detour of traditional navigation and fixed flows.
More than reacting: how agents think
Besides access to systems there is another important change: the way questions are processed. It started with reacting to a single prompt. Now agents can work through several reasoning steps before they answer. They retrieve extra information, apply rules, compare options and decide what the logical next step is.
More important still, you can run different agents at the same time. A service agent gets different instructions and has different priorities than a sales agent. An internal colleague needs a different approach than an external customer. Digital interaction becomes less generic and more tuned to the user's role. The website behaves less like a single voice and more like a set of specialized functions.
Read more about agents in vragen.ai
When conversation turns visual
Even so, text on its own only goes so far when choices or transactions are involved. Which brings a third development: building interactive parts into the conversation. Widgets make it possible to show products, calendars, status overviews or comparisons right there in the exchange.
The answer is no longer "Click here to continue." The answer is the next step. The user sees available time slots, adjusts quantities or confirms a choice, without leaving the conversation. Conversation and interface become one.
Read more about widgets in vragen.ai
Why the combination makes the difference
On their own, agents, system connections and widgets are interesting innovations. Together they change what a website is. It stops being about providing information and starts being about producing concrete outcomes.
Here is how the three play together:
| Component | Role in the interaction |
|---|---|
| Agent | Understands intent, reasons in several steps and decides on the right next step |
| MCP | Connects the conversation to the systems behind it and makes controlled actions possible |
| Widget | Makes information and actions visual, interactive and immediately actionable inside the conversation |
When these three layers work together, the interaction shifts from question-and-answer to intent-and-result. The user no longer has to navigate structures someone designed in advance, but gets support in reaching a goal.
A different design question
Websites have of course always been able to support processes. Permits could be applied for, appointments booked, orders placed. The difference isn't in what is possible, it is in how accessible that becomes.
AI changes the access to these processes. No longer through fixed menus and pre-designed flows, but through intent. The user states a goal, and the system works out the fastest route to carrying it out.
That calls for a different way of thinking. Not only: which page do we show and what steps does someone go through? But also: which intents do we want to support directly, and which systems do we need for that?
AI works as the connecting layer here. Not as a replacement for existing functionality, but as an accelerator and a connector. What used to be spread across pages and forms can now be brought together in one conversation.
The value of a digital environment shifts subtly as a result. Not because the processes are new, but because the route to them becomes shorter, more natural and more adaptive. Less dependent on navigation, more focused on progress.
Getting started with vragen.ai
At vragen.ai we make this concrete. Organizations can configure agents with specific roles and reasoning steps, set up MCP connections to their own systems, and use widgets to make actions directly executable inside the conversation. We support you in setting up that structure and turning intents into working interactions.
That doesn't mean you have to start big. You can begin with one clear use case: a frequently asked question that leads into a process, an appointment module driven from the conversation, or an order flow sped up through intent. From there the functionality can be extended step by step.
What emerges is an environment where intent, knowledge and action come together. The next step in conversational is more than understanding better. It is actually making things happen.