Best first move
Pick one educator from the table, watch one matched video, then open one hands-on resource. The aim is to leave with a working habit, project, or mental model tied to official docs.
AI learning guide
Start with primary-source documentation when learning current models, APIs, agents, MCP, and provider-specific tradeoffs.
Pick one educator from the table, watch one matched video, then open one hands-on resource. The aim is to leave with a working habit, project, or mental model tied to official docs.
Compare audience, level, format, and starting point. Favor a source that matches your current role and gives you exercises, examples, docs, or code you can use immediately.
Avoid collecting dozens of generic AI tips. Use this guide to choose a narrow learning loop: one topic, one educator, one video, one resource, one application in your own work.
Start here if you want the shortest route from search result to useful learning.
Pick 1
Free tutorial · Matt Pocock
You want a guided path through core AI concepts, model selection, the AI engineering mindset, evals, and techniques for improving LLM-powered apps.
Pick 2
Free tutorial · Matt Pocock
You want to understand MCP and build TypeScript MCP servers over stdio or HTTP, connect Claude Code to tools, use MCP prompts, and package servers for distribution.
Pick 3
Dictionary · Matt Pocock
You want plain-English definitions for agentic coding concepts such as context windows, tools, MCP, handoffs, skills, subagents, feedback loops, and agent-ready work.
Pick 4
Short course · DeepLearning.AI
You want a hands-on MCP course for connecting tools, context, and Claude-powered apps.
Pick 5
Free course · Hugging Face
You want a free structured MCP path with concepts, assignments, SDKs, and a certificate route.
Simon Willison
| Educator / source | Best for | Skills | Start with |
|---|---|---|---|
| Developers, technical generalists | LLM tools, Prompting, AI safety, Local models, Model selection | Read the recent model-roundup posts, then try the llm command-line tool with two or three different providers. | |
| Developers and self-directed learners building with AI coding agents | AI coding, Claude Skills, Agentic workflows, AI SDK, MCP, LLM fundamentals, Personalized learning | Use LLM Fundamentals or the AI Engineer Roadmap if you need concepts, the Vercel AI SDK Tutorial or AI SDK v6 Crash Course if you want to build apps, and the AI Skills catalog if you want practical agent workflows like /teach, /grill-me, /tdd, and /triage. |
Free tutorial · Matt Pocock · Beginner to intermediate
You want a guided path through core AI concepts, model selection, the AI engineering mindset, evals, and techniques for improving LLM-powered apps.
Free tutorial · Matt Pocock · Intermediate
You want to understand MCP and build TypeScript MCP servers over stdio or HTTP, connect Claude Code to tools, use MCP prompts, and package servers for distribution.
Dictionary · Matt Pocock · Beginner to intermediate
You want plain-English definitions for agentic coding concepts such as context windows, tools, MCP, handoffs, skills, subagents, feedback loops, and agent-ready work.
Short course · DeepLearning.AI · Intermediate
You want a hands-on MCP course for connecting tools, context, and Claude-powered apps.
Free course · Hugging Face · Beginner to intermediate
You want a free structured MCP path with concepts, assignments, SDKs, and a certificate route.
API docs · Perplexity · Intermediate
You want to compare search, Sonar, Agent API, and cited research workflows from the primary source.
Model docs · OpenAI · Beginner to advanced
You need to choose between GPT-5.5, GPT-5.5 Pro, GPT-5.4 mini, GPT-5.4 nano, reasoning levels, tool support, and cost-sensitive API paths.
Guide · OpenAI · Intermediate
You need the official OpenAI path for wiring MCP servers and connectors into agent workflows instead of inventing your own tool contract.
Model docs · Anthropic · Beginner to advanced
You need the official comparison of current Claude models, context windows, aliases, and release families before choosing cost, speed, and reliability tradeoffs.
Official learning hub · Anthropic · Beginner to advanced
You want official Anthropic courses for AI fluency, Claude Code, MCP, or Claude API development before diving into narrower docs.
Guide · Anthropic · Intermediate
You want Anthropic's official guidance for exposing tools and data to Claude through MCP instead of only reading the base spec.
Model docs · Google AI for Developers · Beginner to advanced
You need to compare current Gemini 3.5 model families, context windows, modalities, stable releases, and experimental model IDs.
Guide · Google AI for Developers · Intermediate
You want Google's official setup path for Gemini-driven coding-agent workflows, Gemini Docs MCP, and skills rather than generic prompt advice.
Model docs · Mistral AI · Beginner to advanced
You need to compare current Mistral families such as Devstral, Magistral, Voxtral, OCR, and general-purpose models.
Model docs · Cohere · Beginner to advanced
You need to choose between current Cohere Command, embedding, and rerank models for grounded enterprise search.
API docs · DeepSeek · Beginner to advanced
You need first-call examples, OpenAI-compatible API usage, and current migration notes for DeepSeek models.
Use the educator table, videos, and resources above to compare options by topic fit, depth, and format. A good choice gives you a concrete next step: a course module, code example, video walkthrough, project, or workflow you can try today.
Use the educator table, videos, and resources above to compare options by topic fit, depth, and format. A good choice gives you a concrete next step: a course module, code example, video walkthrough, project, or workflow you can try today.
Use the educator table, videos, and resources above to compare options by topic fit, depth, and format. A good choice gives you a concrete next step: a course module, code example, video walkthrough, project, or workflow you can try today.