Agentic AI, explaining what agents are, how they work and the role of toolsAug 16, 2025·4 min read·15
Where RAG FailsYou've built your first Retrieval-Augmented Generation (RAG) system. It connects your Large Language Model (LLM) to a private knowledge base, and it feels like magic. But then, you start noticing problems. It misses obvious answers, gives irrelevant ...Aug 22, 2025·6 min read·44
Explain Vector EmbeddingsWhen humans read a sentence, we instantly understand the meaning, context, and relationships between words. Computers, however, don’t “understand” language in the same way. They work with numbers, not words. This is where vector embeddings come in a ...Aug 13, 2025·5 min read·18
Explain Tokenization for LLMsWhat is Tokenization? Tokenization is the process of breaking text into smaller pieces called tokens (like words, subwords, or characters) so a computer or AI model can understand and process it. In tokenization, each token is assigned a unique ID fr...Aug 12, 2025·6 min read·43
How to Trace/Monitor an AI applicationIntroduction We need AI tracing because AI systems are often like "black boxes": they take in inputs and give outputs, but we don't always understand how they get there. Tracing helps to open that black box for different important reasons. How to Tra...Apr 29, 2025·6 min read·59
Hypothetical Document Embeddings: For Retrieval EnhancementImagine asking a friend for a book recommendation, but instead of describing the book perfectly, you fumble with your words. A great friend might still guess correctly by focusing on the essence of what you need. Hypothetical Document Embeddings (HyD...Apr 23, 2025·3 min read·43
Step-Back Prompting: A Way to understand the user query betterSometimes, users ' queries are ambiguous, but to give the user a perfect answer, LLMs need to understand the user's query better. For this, we use Step-Back Prompting. What is Step-Back Prompting? Instead of directly using the user query to fetch doc...Apr 23, 2025·3 min read·19
Chain of Thought: Understand the user's QueryNow that you've learned how to make AI step back and think, let's go one level deeper. The next cool technique is called Chain-of-Thought Prompting. What Is Chain-of-Thought Prompting? Imagine solving a math problem. You don’t just say the answer, yo...Apr 23, 2025·3 min read·16
