THESIS: Use case of AI agent in Customer Success

High level descriptionWith the rising amount of AI agents (ChatGPT, OpenAI, Grok, Microsoft CoPilot, Google Gemini, …), it becomes more difficult to know which AI agent to use in different contexts. Some agents might not be fact based enough with no access to real time data, others are easily manipulated by the user, others might provide propaganda due to...

High level descriptionIndustries increasingly collect sensor data from equipment, but much of this data is not fully used for real time insights or predictive maintenance. A device-to-cloud prototype can demonstrate how even simple hardware can generate valuable data for health monitoring and failure prediction.Who are we looking for?Bachelor/Master of...

High level descriptionThis project examines the application of artificial intelligence in translating change requests into automated test cases by referencing software interface descriptions, aiming to enhance verification coverage and overall software quality.Who are we looking for?Bachelor/Master of Science in Computer Science/EngineeringProject...

High level descriptionWith the rapid advancement of artificial intelligence, AI-driven communication tools such as chatbots, virtual assistants, and deepfake voice generators, are becoming increasingly indistinguishable from human interaction. While these technologies offer numerous benefits, they also pose significant risks by blurring the line between...

BackgroundIn today's digital landscape, services and offerings are increasingly composed of multiple interconnected applications and systems. This complexity makes it difficult to trace which services are tied to a specific customer identifier and to detect issues such as failed orders or recurring system errors.Traditionally, support and operations teams...

High level descriptionWith the rising popularity of AI agents, Anthropic has developed a new protocol for LLM models to communicate with tools. The Model Context Protocol (MCP) is slowly becoming a standard for developing tools for LLMs and LLM Agents. In MCP there are no security or authentication methods, so exposing tools towards end users can be harmful...

High level descriptionGenerative AI is increasingly used in software development to write code, tests and suggest solutions. This increases productivity but at the cost of several risks, one being security. The AI tools being used may generate code that contains vulnerabilities, reproduce insecure patterns from training data, or create a false sense of...

High level descriptionEffort and time estimation remain among the most challenging aspects of software engineering. Despite decades of research, human estimates are still often uncertain and inconsistent.With the rise of advanced AI assistants and code-generating tools such as GitHub Copilot, ChatGPT, Amazon CodeWhisperer, and similar systems, new...

AbstractManaging third-party dependencies is critical for software security, yet existing tools such as Dependabot treat all version updates and reported vulnerabilities as equally urgent. This lack of prioritization leads to alert fatigue and wasted developer effort. This thesis explores how AI can make dependency risk management more contextual and...

High level descriptionModern data engineering faces unprecedented challenges as organizations increasingly deploy IoT devices and edge computing infrastructure that generate massive volumes of distributed data.Traditional centralized data processing approaches struggle with the latency, bandwidth, and reliability constraints inherent in edge-to-cloud data...