Bsc: Internship IT - Application development
Are you an HBO IT student looking for an exciting graduation assignment? Are you ready for a challenge to help us implement an AI agent for a continuous improvement application? Then we are looking for you!

Your Assignment
During this graduation internship, you will research how an AI agent can support users in controlling one of our applications through natural language. This involves the use of a Large Language Model (LLM) in combination with the Model Context Protocol (MCP) to make interactions between the model and the application structured and controllable. The goal is to explore how an AI agent can interpret, plan, and execute tasks within the context of our application.
You will design and build a Proof of Concept (PoC) in which a user provides an instruction in natural language. The AI agent translates this instruction into one or more concrete actions and executes them via available interfaces. Control is facilitated via MCP, where tools, resources, and context are provided to the model in a standardized way. Examples of actions include calling APIs, executing workflows, filling in forms, or generating scripts that operate the application.

Key components of the assignment include:

-Intent recognition and task planning
Analyzing user input to identify intentions and translate these into an executable plan (task decomposition), including determining order, dependencies, and required parameters.

-MCP-based integration with the application
Designing and implementing an MCP server in which the functionality of the application is exposed as tools and context. You will investigate which interfaces (APIs, command layer, workflows, or UI automation) are most suitable to provide via MCP.

-Security, authorization, and control
Enforcing clear boundaries on what the AI agent may execute, including authorization per tool, logging of actions, and requiring explicit user confirmation for critical operations.

-Reliability and error handling
Handling unclear, incomplete, or conflicting instructions, as well as errors during execution. The agent provides understandable feedback to the user and can suggest recovery options or alternative actions.

-User experience and transparency
Making the agent’s reasoning process and planned steps visible, including intermediate results, decision points, and the status of executed actions.

You will work toward a Proof of Concept demonstrating what is technically possible with an MCP-based AI agent, which architecture and integrations best fit our application, and what added value this offers end users. The user always remains in control: the agent proposes actions, executes them within agreed boundaries, and offers options to confirm, adjust, or cancel actions. Based on test results and user feedback, you iteratively improve the solution.

Your Profile
-You are currently studying HBO-ICT and are eager to complete your graduation internship at Canon Production Printing.
-To successfully complete the assignment, you bring skills such as creative problem‑solving and the ability to think about new solutions.
-In short, you are not only a technician, but also someone who can think, collaborate, and communicate effectively.
-You are available from September 2026 for, for a minimum of 4 days per week.

What’s in it for you?
•    A challenging assignment with skilled coaching in a professional environment
•    Internship/ Graduation compensation of €500,- per month
•    Travel cost compensation if you don’t have an ‘OV-weekcard’
•    The possibility to network with professionals inside and outside your field of expertise, thanks to our diversity of disciplines which you will work with

Interested?
Are you interested in this assignment? Please click on the button 'apply now' where you can upload your resume and motivation letter. 
If you would like to receive more information concerning this assignment, please contact Danny op het Veld danny.ophetveld@cpp.canon If you have any questions about the internship in general, please contact Milou Geelen, + 31 6 25653192.