Basic vs Production AI Engineering: RAG, Agents, and Context over Prompts
Bashiri Smith · Facebook reel · 2026-10-14 · 1:05 · 3,146 views · Open on Facebook
Topics: Retrieval-Augmented Generation (RAG), AI Agents, Tool Use & MCP, Evaluation (Evals) & Testing · Level: intermediate
Summary
A skit comparing "wannabe" and production-level AI engineering habits. Basic RAG (chunk, embed, store, retrieve) is set against production RAG, which adds hybrid search, re-ranking, query rewriting and retrieval measurement. Agents should have tightly scoped tools and controlled state (for example with LangGraph) instead of being an open-ended LLM loop. The video also says the real job is supplying the right context, the right data and reliable evaluation, not mastering prompt engineering. It ends with a pitch for the creator's paid Skool community.
Key points
- Basic RAG means chunking documents, embedding them, storing them in a vector DB and retrieving. That is a demo, not a product.
- Production RAG uses hybrid search (keyword plus vector) with a re-ranking step.
- Rewrite or transform the user's query before it hits the index.
- Measure retrieval quality before trusting any generated answer.
- An unconstrained 'LLM in a loop with tools' wastes tokens and behaves unpredictably. Scope the tools tightly.
- Control agent state explicitly (e.g., with LangGraph) so you know exactly what the agent is doing.
- The creator argues prompt engineering is not the core skill. The job is giving the model the right context and data, plus reliable evaluation.
Resources mentioned
- LangGraph · tool · langchain.com · free
Graph-based agent framework with typed state, checkpointing, cycles and human-in-the-loop interrupts. The guide calls it the production default for complex stateful agents.
Also in: The 3 AI Engineering Skills: Generative AI, RAG, and Agentic AI (Bashiri Smith on Facebook · notes), Graph Engineering Explained: Nodes, Edges, and State for AI Agent Workflows (Bashiri Smith on Facebook · notes), Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), LangChain vs. LangGraph Explained with One RAG Chatbot (Bashiri Smith on Facebook · notes) and 5 more - BASWE.Ai Engineer (Skool community) · community · skool.com · paid
The creator's paid community and program, with an AI learning roadmap (including the full ops and evaluation track), daily calls with engineers and recruiters, resume and portfolio help, and a job-search pipeline.
Also in: ChatGPT Prompt to Generate Standout Portfolio Project Ideas (Bashiri Smith on Facebook · notes), Vector Database vs. Graph Database: When to Use Each (and Both for RAG) (Bashiri Smith on Facebook · notes), The 5 Levels of RAG: From Naive Retrieval to Agentic RAG (Bashiri Smith on Facebook · notes), Get More Interviews: Prove You Built Your Projects With Video Walkthroughs (Bashiri Smith on Facebook · notes) and 93 more
Try this
- Upgrade basic RAG with hybrid search and re-ranking.
- Add a query-rewriting step before retrieval.
- Set up retrieval-quality evaluation before trusting answers.
- Scope agent tools tightly and manage agent state explicitly (e.g., with LangGraph).
- Focus on context, data and evaluation rather than prompt engineering alone.
- Turn a basic RAG demo into a production-style pipeline: hybrid search, re-ranking, query rewriting and retrieval evals.
- Rebuild a free-running tool-calling agent as a LangGraph workflow with scoped tools and explicit state.