Start here in Generative AI
The most useful guides in this topic, not just the most recent.
Generative AI Guides & Tutorials
Practical guides to LLMs, RAG, agents, prompt engineering and the modern Gen AI stack used in production today.
Generative AI articles
How Transformers Changed AI: Attention Explained
Attention lets every word in a sentence draw information from every other word in one step. That idea, from a 2017 paper, replaced the older sequence models and underlies current language models. This guide works the arithmetic by hand, then shows a real attention head in GPT-2 linking a pronoun to its noun.
AI Coding Assistants: How to Use Them Effectively
AI coding assistants write plausible code quickly, and plausible is not the same as correct. This guide summarises what research says about their speed and security, then has a small local model write six functions, scores them with hidden tests, and shows what examples and test feedback fix.
Building a Multi-Agent System: Patterns and Pitfalls
Splitting work across several cooperating AI agents is appealing and often disappointing. This guide sets out the main multi-agent patterns, what published experience says about when they beat a single agent, a small model of how errors compound across hand-offs, and design rules that follow from it.
Building AI Agents with LangGraph: A Hands-On Tutorial
Agent tutorials stop when the demo works. Production agents fail in other ways: tools time out, loops never end, and behaviour changes silently. This hands-on guide builds a small LangGraph agent and makes it reliable, with a retry policy on its tool node, a recursion limit and deterministic tests.
Prompt Engineering: Techniques That Actually Improve Output
Most prompt advice is a list of tips. This guide takes one job, pulling three fields out of customer emails, and rewrites the prompt seven times, scoring each version on the same twelve emails. An example and a schema fixed the format; definitions and asking for evidence before the verdict fixed the meaning.
Agentic AI Roadmap 2026: From Prompts to Autonomous Systems
Agentic AI is the most hyped corner of generative AI and the easiest to learn in the wrong order. This roadmap builds it in seven stages, from reliable prompts and structured output through retrieval and tools to workflows, agents and production safeguards, with something to build at each stage.