Comprehensive guide to building and orchestrating agents that reason, plan, and act using foundational design patterns (Evaluator-Optimizer, Context-Augmentation, Prompt-Chaining, Parallelization, Routing, and Orchestrator-Workers).

Deep dive into MCP - an open protocol for connecting LLM applications with external data sources, tools, and systems - through a practical implementation of an MCP Server that performs retrieval and analytics on news articles with frontier models.

LLM-based applications face security challenges in form of prompt injections and jailbreaks. This project reviews the key architectural improvements underpinning ModernBERT, and implements fine-tuning for discriminating malicious prompts. PangolinGuard closely approximates the performance of Claude 3.7 on a mixed benchmark, while maintaining low latency (< 40ms).

As highlighted by the FBI, digital scams cause devastating impacts across society. MINERVA is an AutoGen implementation that helps users identify scam attempts with just a screenshot, achieving higher accuracy than baseline prompt methods (88.3% vs. 69.5%).

My personal top takeaways after attending TED.AI in Vienna (October 17-19, 2024) and participating in the official TED.AI Hackathon AI for Good @ UNIDO.

The ever-growing volume of research publications necessitates efficient methods for structuring such knowledge. This automated solution uses Machine Learning (UMAP, HDBSCAN), Embedding Quantization, and an LLM pipeline to classify 25,000 arXiv publications under a novel taxonomy.

Python from-scratch implementation of the modules required to build and train a Neural Network that classifies garment images, incl. Linear and Flatten Transformations, Non-Linearity, Regularization, Gradient-Descent-Optimizer, Backpropagation, Mini-Batch Training, and Evaluation.