- Published on
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).
All Posts
All Posts
- llms (7)
- ai-engineering (5)
- deep-dive (3)
- rag (2)
- function-calling (2)
- agents (2)
- ai-safety (2)
- nlp (2)
- embeddings (2)
- agentic-ai (1)
- design-patterns (1)
- agents-orchestration (1)
- in-context-learning (1)
- openai (1)
- autogen (1)
- rdi-berkeley (1)
- model-context-protocol (1)
- deep-learning (1)
- multilayer-perceptron (1)
- backpropagation (1)
- gradient-descent (1)
- fine-tuning (1)
- modern-bert (1)
- hugging-face-transformers (1)
- knowledge-graphs (1)
- langchain (1)
- neo4j (1)
- quantization (1)
- clustering (1)
- topic-modeling (1)
- tedai (1)
- innovation (1)
- research (1)
- ai-ethics (1)
- hackathon (1)
- conference (1)
- Published on
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.- Published on
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).- Published on
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%).- Published on
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.