AI & LLM Engineering - PenlumaBuilding, evaluating, and shipping with large language models.https://penluma.com/How LLMs Actually Work (And Why It Still Matters)https://penluma.com/blog/ai-llm-engineering/01-foundations-how-llms-work-why-these-skills-endure/https://penluma.com/blog/ai-llm-engineering/01-foundations-how-llms-work-why-these-skills-endure/Learn how LLMs actually work in plain English - tokens, context windows, temperature, and the durable engineering skills that outlast every model release.Sun, 21 Jun 2026 00:00:00 GMTAI & LLM EngineeringAI Evals: How to Know Your LLM App Actually Workshttps://penluma.com/blog/ai-llm-engineering/02-evaluation-measurement/https://penluma.com/blog/ai-llm-engineering/02-evaluation-measurement/Learn how AI evals replace guesswork with repeatable measurement. A plain-language guide to LLM evaluation, graders, LLM-as-a-judge, RAG, and agents.Sun, 21 Jun 2026 00:00:00 GMTAI & LLM EngineeringContext Engineering: How to Feed an LLM the Right Factshttps://penluma.com/blog/ai-llm-engineering/03-context-engineering-retrieval/https://penluma.com/blog/ai-llm-engineering/03-context-engineering-retrieval/Learn context engineering and RAG: why more context hurts, how retrieval works, and the proven stack that makes AI answers accurate and grounded.Sun, 21 Jun 2026 00:00:00 GMTAI & LLM EngineeringAI Agents Explained: From One LLM Call to Multi-Agent Systemshttps://penluma.com/blog/ai-llm-engineering/04-agent-architecture-orchestration/https://penluma.com/blog/ai-llm-engineering/04-agent-architecture-orchestration/Learn how AI agents really work: the ReAct loop, tools, workflow patterns, and when to go multi-agent. A clear, practical guide to agent architecture.Sun, 21 Jun 2026 00:00:00 GMTAI & LLM EngineeringWhen to Use AI (and When Plain Code Wins)https://penluma.com/blog/ai-llm-engineering/05-ai-product-judgment/https://penluma.com/blog/ai-llm-engineering/05-ai-product-judgment/Most AI products fail before the model is even chosen. Learn when to use AI, when plain code wins, and how to climb the ladder of escalation wisely.Sun, 21 Jun 2026 00:00:00 GMTAI & LLM EngineeringLLM Engineering FAQ: RAG, Agents, Evals, and Morehttps://penluma.com/blog/ai-llm-engineering/06-frequently-asked-questions/https://penluma.com/blog/ai-llm-engineering/06-frequently-asked-questions/Clear answers to the questions every LLM engineer asks: RAG vs fine-tuning, agents vs workflows, evals, hallucinations, tokens, context windows, and more.Sun, 21 Jun 2026 00:00:00 GMTAI & LLM EngineeringLLM Engineering Cheat Sheet: The Whole Field on One Pagehttps://penluma.com/blog/ai-llm-engineering/07-revision-cheat-sheet/https://penluma.com/blog/ai-llm-engineering/07-revision-cheat-sheet/A fast, plain-English LLM engineering cheat sheet covering evals, RAG, agents, and judgment - plus a decision table for picking the right technique every time.Sun, 21 Jun 2026 00:00:00 GMTAI & LLM Engineering