AI learning guide

Best official AI provider docs and model catalogs

Start with primary-source documentation when learning current models, APIs, agents, MCP, and provider-specific tradeoffs.

Best OpenAI docs to bookmark: OpenAI model guide. Official OpenAI guide to current GPT, reasoning, coding, and tool-capable models. Use it when model names, reasoning levels, and API behavior matter.

Best OpenAI learning hub: OpenAI Academy. Official OpenAI Academy hub for guided courses and skills. Use it when you want a more structured OpenAI learning path than raw API docs alone.

Best Claude learning hub: Anthropic Academy. Official Anthropic hub for AI fluency, Claude Code, MCP, and Claude courses. Use it to move from one-off Claude docs pages into a broader official learning path.

Best Gemini model reference: Gemini API models. Official Google AI for Developers model documentation. Use it to compare Gemini context, modality, and release channels.

Best open-model catalog: Hugging Face model hub. Hugging Face's live catalog for open checkpoints, datasets, and demos. Use it to see what open models are actually available, not just which ones were announced.

Best DeepSeek migration source: DeepSeek models and pricing. Official DeepSeek pricing and model page. Use it to verify live model names, pricing, and alias migrations before building around DeepSeek.

Best routed-catalog reference: OpenRouter models guide. OpenRouter's cross-provider model directory. Use it when you want one place to compare current provider availability across model families.

Primary sources matter most when models move fast

Model names, aliases, context windows, pricing, tool support, and recommended usage can change quickly. Official docs and model catalogs are the first place to check before relying on a course, tweet, or old benchmark.

Bookmark the model catalog and release notes for every provider your work depends on. As of Saturday, September 5, 2026, the highest-priority model changes remain OpenAI's GPT-6 Astra launch and migration guidance, Anthropic's Claude Fable 5.1 model and prompting guides, and Google's GA Gemini 3.8 Flash page plus its Lyria 3.5 preview documentation. New practical learning references now cover Astra mid-turn steering, Codex Record & Replay, Codex lifecycle hooks, WebMCP site tools, and Hugging Face's open-source funes memory layer for coding agents. Keep the broader source set close too: Meta's Model API and Llama docs; Mistral's models, Agentic Search, and OCR guides; Cohere's model and retrieval docs plus its open Agentic Task Ecosystem research; DeepSeek's V4 pricing, vision, Responses, and Codex pages; Qwen's model and coding-agent docs; xAI's Grok model and Build release streams; Perplexity's Search, Agent, embeddings, eval, and MCP docs; Hugging Face's model, agent, retrieval, and course hubs; and OpenRouter's catalog, routing, eval, benchmark, and agent documentation. Secondary summaries are useful for discovery, but check the primary source before migrating or teaching a workflow.

Use catalogs to narrow the test set

A model catalog should not make the final decision for you. It should narrow the candidates by modality, context, tool support, speed, price, hosting route, and data constraints.

Once the list is short, test the models on your own prompts and workflows. That is the only way to know whether a model is right for your coding agent, RAG system, product feature, or research assistant.

Recommended courses and resources

The AI Engineer Roadmap

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.
Model Context Protocol Tutorial

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.
AI Coding Dictionary

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.
MCP: Build Rich-Context AI Apps with Anthropic

Short course · DeepLearning.AI · Intermediate

You want a hands-on MCP course for connecting tools, context, and Claude-powered apps.
Hugging Face MCP Course

Free course · Hugging Face · Beginner to intermediate

You want a free structured MCP path with concepts, assignments, SDKs, and a certificate route.

Roll a learning mission

Pick one small move from this guide instead of opening ten tabs.

Open mission

About this guide

Author: Learnetto Editorial Team. Learnetto maintains this AI learning directory by organizing public course pages, official documentation, educator material, and practical learning resources.

How it is made: Learnetto uses public course pages, official documentation, educator material, and directory data to compile these recommendations. AI may help draft and organize the page, but recommendations are checked against the listed sources, page topic, and learner intent.

Review policy: We only add a named personal reviewer when that person has substantially reviewed the page. Until then, the page is attributed to Learnetto rather than a founder, editor, or individual expert.

Last updated: September 24, 2026. Suggest a correction if a course, doc, or recommendation is outdated.

Videos to watch

►

Google's AI endgame is here... everything you missed at I/O 2026

Fireship

►

How to Build for AI Agents and a Claude Code Second Brain in 25 Min | Ryan Wiggins

Peter Yang

►

The last six months in LLMs in five minutes

Simon Willison

Educators and sources

Educator / source	Best for	Skills	Start with
Simon Willison Simon Willison on LLMs	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.
Matt Pocock AI Hero	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.
Matthew Berman Forward Future	Builders, founders, AI-curious operators, developer-adjacent learners	AI agents, Open-source AI, Vibe coding, MCP, AI workflows	Start with the OpenClaw guide or a Forward Future University lesson, then use the newsletter to follow adjacent tools only after you ship one example.
Mervin Praison PraisonAI	Developers learning agent frameworks, multi-agent systems, and open-source AI tooling	AI agents, Multi-agent workflows, MCP, RAG, Open source	Start with the main repo and one video tutorial, then run a minimal local example before reaching for larger multi-agent setups.

Resources

The AI Engineer Roadmap

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.

Model Context Protocol Tutorial

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.

AI Coding Dictionary

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.

MCP: Build Rich-Context AI Apps with Anthropic

Short course · DeepLearning.AI · Intermediate

You want a hands-on MCP course for connecting tools, context, and Claude-powered apps.

Hugging Face MCP Course

Free course · Hugging Face · Beginner to intermediate

You want a free structured MCP path with concepts, assignments, SDKs, and a certificate route.

Perplexity Deep Research and Search API docs

API docs · Perplexity · Intermediate

You want to compare search, Sonar, Agent API, and cited research workflows from the primary source.

Grok 4.7 explained

Frontier coding model launch explainer · SpaceXAI · Intermediate to advanced

SpaceXAI released Grok 4.7 on September 21, 2026 for coding, agentic tasks, and knowledge work. Use this guide to compare its task reliability and total cost with your current model.

Union Alpha revealed as Pareto 26.9

Multi-model routing launch explainer · Unbiased · Intermediate to advanced

Union Alpha was revealed as Unbiased's Pareto 26.9 on September 17, 2026: a hosted system that routes work across several models and returns one checked answer.

Qwen3.8-Omni-Flash explained

Omnimodal model launch explainer · Qwen · Intermediate

Qwen3.8-Omni-Flash launched September 18, 2026 for long audio and video analysis, text answers, web search, and tool-calling workflows.

Introducing the Agents API

Managed agent API launch and guide · OpenAI · Intermediate to advanced

You want OpenAI's September 10, 2026 launch guide for building long-running cloud agents with the managed Codex harness, context compaction, tool search, multi-agent delegation, and your choice of hosted or self-managed sandbox.

GPT-Live-1 in the API

Voice agent model launch · OpenAI · Intermediate

You want OpenAI's September 10, 2026 launch of GPT-Live-1 in the API for full-duplex voice agents, including its $0.05-per-minute front-end pricing and guidance on pairing it with a backend model and agent harness.

Claude Fable 5.1 and Claude Mythos 5.1

Model launch and safety guide · Anthropic · Advanced

You want Anthropic's September 1, 2026 model announcement covering Fable 5.1 for general availability and Mythos 5.1 for trusted-access research use.

Gemini 3.8 Flash launch

Model launch and selection guide · Google AI · Intermediate

You want Google's September 2, 2026 launch details for Gemini 3.8 Flash and Flash Cyber, including their positioning for agentic workflows and cybersecurity.

Muse Spark 1.3

Model launch and selection guide · Meta AI · Intermediate

You are comparing frontier models for long-horizon coding or knowledge work and need Meta's September 2, 2026 release notes on Muse Spark 1.3's tool use, instruction following, user steering, multitasking, model self-awareness, and availability through Muse Code and Meta Model API.

Agentic models, measured on the injections that move money

Open security benchmark · Hugging Face Community · Intermediate to advanced

You want a reproducible September 5, 2026 benchmark for comparing how agentic models handle indirect prompt injection, with public data, a public harness, control runs, tool-call traces, and outcome metrics tied to unauthorized payment actions.

Project HydraFusion

Model orchestration research preview · GitHub · Intermediate to advanced

You want GitHub's September 4, 2026 technical explanation of runtime model orchestration for coding tasks, including plan decomposition, draft-critique-revise patterns, model cascading, evaluation design, and quality-versus-cost tradeoffs.