Ask Nikhil

If you're building anything with LLMs in production, you eventually hit the same wall: you need to know what your app is actually doing — what prompts went out, what came back, how much it cost, and why it broke at 2am. That's observability, and two names keep coming up: Langfuse and MLflow. Before comparing them, it's worth laying out what you're actually trying to observe — because observability means something different at each layer of a modern AI system. LLM observabilit

Every time someone mentions running an LLM in production, the first instinct is to reach for a GPU instance. A100s, H100s, L40s — the cost spirals fast, and for most enterprise inference workloads, you're paying for compute you don't need. I've been running inference experiments on OCI Ampere A1 instances for a while now, and the results keep surprising me in a good way. DeepSeek-R1 7B is the model that changed the conversation. Released by DeepSeek AI, this reasoning-optimis

How Knowledge Graphs Transform AI-Powered Healthcare Search I have been building RAG systems for a while now. And for most use cases, the standard approach works fine — chunk your documents, embed them, store them in a vector database, and retrieve the most similar chunks when someone asks a question. Simple. Scalable. Gets the job done. But then I tried to apply it to medical records. And it fell apart almost immediately. Not because the technology is bad. But because medica