RAG is Not Just Chunking + Embedding + Retrieval — Here's What Production Actually Looks Like
A complete breakdown of enterprise-grade RAG pipeline with packages, architecture, and real engineering decisions
Jun 4, 20266 min read38
Command Palette
Search for a command to run...
Series
AI in Production
A practical series on building and shipping AI systems that actually work — RAG pipelines, agents, observability, and MLOps. No theory, no toy examples. Real patterns, real failures, real fixes.
AI Agents in Production — What Actually Breaks
After studying production AI systems, reading real post-mortems, and building pipelines on enterprise data — one pattern stands out. Everyone talks about building agents. Nobody talks about what break
Jun 6, 20267 min read19
# Not Every RAG System Needs a Vector Database
Everyone building RAG systems starts the same way. Document → Chunks → Embeddings → Vector Database → Similarity Search → LLM That pipeline works. But it is not the only way to retrieve information. A
Jun 12, 20268 min read9
The 5 Layers of Agent Memory — What Every Production Agent Needs
Everyone talks about context engineering. Nobody shows you the memory stack underneath it. Without memory, an agent forgets everything after each session. Like talking to someone with amnesia — you sh
Jun 14, 202610 min read5