Videos
Whiteboard-style videos and architecture walkthroughs for complex AI systems. Visual explanations that make intricate concepts understandable.
Featured Video
Featured
Architecting LLM Inference
A visual walkthrough of how large-scale LLM inference works — from prefill and decode to KV cache, batching, GPU memory, and serving architecture.
Upcoming Videos
Subscribe to the channel to be notified when new videos are published.
Coming Soon
Architecting LLM Inference
A visual walkthrough of how large-scale LLM inference works — from prefill and decode to KV cache, batching, GPU memory, and serving architecture.
Prefill & DecodeKV CacheBatchingGPU Memory
Coming Soon
Understanding Transformer Architecture
Deep dive into the transformer architecture with visual explanations of attention mechanisms, positional encoding, and layer normalization.
Self-AttentionMulti-Head AttentionFFNLayer Norm
Coming Soon
Building RAG Systems
Complete walkthrough of retrieval-augmented generation — from document chunking to vector search and response generation.
ChunkingEmbeddingsVector SearchGeneration
Coming Soon
Agentic AI Architecture
How to design and build autonomous AI agents with planning, tool use, and memory systems.
PlanningTool UseMemoryOrchestration