Posted inAI & LLMs PHP Tutorials RAG Tutorial Series
Episode 8 — Evaluating & Shipping
From "seems good" to "measurably good" to "live" For two episodes I've been repeating the…
Episode 7 — Improving Quality: Hybrid Search, Reranking & Guardrails
"Works on my questions" isn't "works" Episode 6 gave us a real, grounded, cited bot.…
Posted inAI & LLMs PHP Tutorials RAG Tutorial Series
Episode 6 — Generation: Grounded Answers with Citations
The last mile Five episodes of groundwork come together here. We can load documents, chunk…
Posted inAI & LLMs PHP Tutorials RAG Tutorial Series
Episode 5 — Retrieval: Top-K, Thresholds & Filtering
Our search is fast, but it isn't smart After Episode 4, MySQL ranks our chunks…
Posted inAI & LLMs PHP Tutorials RAG Tutorial Series
Episode 2 — Preparing the Knowledge Base: Loading & Chunking Your Docs
Where we left off In Episode 1 we cheated. We pasted Nimbus's refund policy into…
Posted inAI & LLMs PHP Tutorials RAG Tutorial Series
Episode 1 — What Is RAG, and Why Should You Care?
The problem, in one support ticket Imagine a customer opens a chat on Nimbus's website…
Posted inAI & LLMs AI-Powered Dev Workflow
AI-Powered Code Review with Claude: What to Check and How to Prompt
Claude reviews code across six dimensions — correctness, security, performance, readability, test coverage, and edge cases — consistently, every time. This post shows the exact prompts, a worked example with three real bugs, and an honest list of what Claude cannot do.
Posted inAI & LLMs AI-Powered Dev Workflow
The CLAUDE.md File: Your Secret Weapon for AI-Assisted Coding
Every time you start a Claude Code session without a CLAUDE.md file, you are starting from zero. This post shows what CLAUDE.md is, the 10 sections it should have, and the full ClientHub example you can copy.