Esteban J. Struve T.

Web Agent is a local product research assistant designed to intelligently browse the web and extract structured information about products and pricing. Built with LangGraph and Playwright, it automates e-commerce exploration and leverages the Trustcall library for high-fidelity, structured data extraction. The system features a PostgreSQL-backed long-term memory with semantic search, enabling the agent to recall previous research and perform complex comparisons without redundant browsing. Integrated with LangSmith for execution tracing, it demonstrates a professional agentic workflow for automated market research. Below is the agent's structure running in LangSmith Studio:

E‑Commerce Chatbot is a proof‑of‑concept intelligent shopping assistant built for a real company to help customers discover pet products through natural‑language conversations. It combines LangGraph's ReAct agent architecture with Retrieval‑Augmented Generation (RAG), grounding recommendations in a real product catalog rather than general model knowledge. The system processes and deduplicates product data, generates OpenAI embeddings, and maintains site‑scoped ChromaDB vector stores, while the agent can combine semantic catalog retrieval with web search via Tavily. A FastAPI backend exposes versioned REST endpoints for health checks and chat, returning natural‑language responses alongside structured product data including details, pricing, ratings, and availability. The project also includes a responsive web interface with interactive product cards, agent processing feedback, and a persistent suggested‑products tracker, providing a complete foundation for integrating an agentic RAG shopping experience into downstream e‑commerce applications.

Markdown Viewer is a personal project built from scratch using Claude Code and vibe coding to showcase how a rapid prototype can be easily put together and work as expected. It is a dark‑mode markdown viewer and editor for Windows 11 that opens markdown files and renders them with rich formatting — headings, tables, code highlighting, task lists, and images — behaving like any native Windows window with snap, resize, and multi‑monitor support. An optional split editor slides in beside the viewer with a keyboard shortcut, rendering changes live as you type and syncing scroll position between both panels. The project is also a practical daily tool used to follow personal meeting notes with enriched Markdown formatting, making content easier to consume in real time.

AI Agents 3D Sandbox is a highly experimental Unity project that investigates whether a multimodal LLM can control a character inside a 3D environment — replacing conventional state machines and NavMeshes with language model reasoning. At each iteration the agent observes the scene, sends that context to a model running via Ollama (optionally on a separate PC over the network), receives a high-level decision, executes the resulting movement inside Unity, and carries a small amount of short-term memory into the next cycle. Built with Unity 6 and URP, the sandbox is less about outperforming traditional navigation and more about exploring the capabilities, failure modes, and emergent behaviour of LLM‑driven embodied agents — including how well multimodal models handle spatial reasoning challenges like depth, orientation, and obstacle avoidance.

2025 – Dynamic Holographic UI Generation

Owned the end‑to‑end implementation of a system to improve the platform in production. This AR platform already including advanced cloud features like ML models and hardware integrations like eye‑tracking, but UIs were produced manually. I implemented a dynamic generation system to build holographic XR‑ready UIs that could be authored by code and modified with a fraction of the time, based on customer needs.

2022 – XR Prototyping & EM sensor integration

Built several PoCs with platforms like Meta Quest, Varjo's XR3 and MS HoloLens 2 where an anatomical model could run in the background to simulate patients. They included collaborative simulations built with Photon PUN 2 for multiplayer interactions. Help create a new workflow for XR fast prototyping as Senior Developer and certified Scrum Master, setting the foundations for the product VR Nursing.

2020 – Knowledge Transfer using Mixed Reality experience

Implemented a tool for Manufacturing customers in MS HoloLens (1 & 2), that could record a 3D space and a set of steps with details gathered by voice and camera. The Spatial Anchors were saved in Azure cloud and retrieved later in the same room (by the same device or other) to recover the spatial data and their poses relevant to the process captured. An apprentice could use the app to learn what the expert recorded about the physical space and machinery present in the factory.

2019 – Assembly of Satellite Antenna of First AU Nanosatellite mission

Participated as volunteer Engineering student in the Delphini‑1 mission of Aarhus University. Member of the team that assembled the antenna that tracked the position of the nano‑satellite in orbit to send and receive the commands and data payloads from the camera in space. Implemented in Python a friendly UI to track the position of the antenna for the Control Room Software that operated this mission and the following ones.

2018 – Udacity's VR Developer Nanodegree Final Project

First VR Unity3D project building an immersive experience I called “Spirits of the Jungle”: a survival experience in the Amazon rainforest to showcase my skills as VR developer. It included complex interaction paradigms to navigate the space, speech recognition, climbing up using the controllers and a couple of first‑person shooting scenes to complete the journey. Deployment device was Oculus Rift from PC (predecessor of the Meta Quest headset family).

2018 – VR Emergency Room

Along side the Master's Thesis project, I built a PoC for emergency meetings in a corporate setting like banking. The way of handling an emergency repair in the IT infrastructure was to flying in experts from all over to an expensive equipment room to solve the issue at hand in not more than 48 hours. My VR room was a much faster and cheaper solution where these experts already had the hardware distributed and this virtual room could have much better data visualization tools.

2013 – Periodic Pattern Detection and Vortex Synchronization in Turbulent Bidimensional Fluids

Implemented in MATLAB a Computer Vision tool to obtain the vector field of a turbulent fluid considered bidimensional. Coded from scratch particle image velocimetry capable of measuring in the high‑speed video dynamics of a system with chaos, filtering the data in multiple steps to bring up a rotating vector allowing specialized studies such as recurrence and synchronization between the vortexes recorded.