AI learning guide

Best AI resources for coding agents

Learn how Codex, Claude Code, Grok Build, and related tools fit real software engineering workflows.

Best course for agent mechanics: Building Coding Agents with Tool Execution. DeepLearning.AI short course taught by Tereza Tizkova and Francesco Zuppichini. Start here to understand how coding agents inspect files, call tools, run commands, and iterate.

Best real-codebase workflow: Claude Code: A Highly Agentic Coding Assistant. DeepLearning.AI course taught by Elie Schoppik. Use it to learn planning, editing, testing, and review inside an existing repo.

Best current Codex operations guide: Codex best practices. Official OpenAI guide for scoping work, AGENTS.md, checks, and review habits. Use it before relying on a coding agent for real repo changes.

Coding agents are software workflows

A coding agent is useful when it can inspect a repo, plan a scoped change, edit files, run commands, read failures, and leave a reviewable diff. The best resources teach that loop explicitly.

Start with Building Coding Agents with Tool Execution for mechanics, then use Claude Code and Codex best practices for real workflow behavior. Matt Pocock's agent-ready codebase material and Hugging Face's Context Course become useful once you want better results inside an existing repo.

Learn review habits alongside tools

Developers still own correctness. A good coding-agent resource should teach task scoping, context gathering, tests, diff review, preservation of unrelated changes, and when to stop the agent.

Avoid resources that only generate a new app from a blank prompt. Real codebases have conventions, failing setup, migrations, data constraints, and product judgement.

Recommended courses and resources

  1. 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.

  2. A Complete Guide To AGENTS.md

    Guide · Matt Pocock · Intermediate

    You want to write project instructions that help coding agents understand commands, conventions, architecture, and working boundaries.

  3. How To Make Codebases AI Agents Love

    Guide · Matt Pocock · Intermediate

    You want to improve a codebase so AI agents can navigate it, run checks, make smaller changes, and recover from mistakes more reliably.

  4. Real-world feature build with Claude Code: every step explained

    Walkthrough · Matt Pocock · Intermediate

    You want to see a real feature built with Claude Code from context gathering through implementation, verification, and iteration.

  5. My Skill Makes Claude Code GREAT At TDD

    Guide / Claude skill · Matt Pocock · Intermediate

    You want an agent workflow that implements behavior with a red, green, refactor loop instead of jumping straight to broad code changes.

Roll a learning mission

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

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 5, 2026. Suggest a correction if a course, doc, or recommendation is outdated.

Videos to watch

Code with Claude London 2026: Opening Keynote video thumbnail

Code with Claude London 2026: Opening Keynote

Claude

The Agentic Engineer Workflow You Need In 2026 video thumbnail

The Agentic Engineer Workflow You Need In 2026

Zen van Riel

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

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

Peter Yang

Claude Code: Build Your First AI Agent video thumbnail

Claude Code: Build Your First AI Agent

Teacher's Tech

Claude Code beginner's tutorial video thumbnail

Claude Code beginner's tutorial

Peter Yang

Agents for everything else video thumbnail

Agents for everything else

AI Engineer

Educators and sources

Educator / source Best for Skills Start with
Developers, AI engineers AI engineering, Agents, Developer tools Watch AI Engineer talks for production patterns and tool choices.
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.
Automation builders, agency owners, freelancers AI automation, Claude Code, Client workflows, AI services Start with the free AI Automation Vault, then only move to the paid community when you know the workflows you want to build.
Non-technical operators, creators, business builders Claude Skills, Claude Code, AI workflows, Business automation Start with the Claude Skills and non-technical Claude Code guides, then install or adapt one workflow skill for a real business task.
Product managers, product leaders, non-technical PMs Claude Code, Technical foundations, AI product work, PM workflows Take the foundations modules first, then use Claude Code on one PM artifact or prototype you already need.
Product managers, product owners, non-technical AI professionals Agentic AI, Product management, Claude Code, AI product workflows Use the course to build one agentic PM workflow, such as requirements discovery, prototype planning, or launch analysis.
Product managers, founders, non-engineering product builders Claude Code, AI prototyping, Product shipping, PM workflows Choose one product idea or internal tool and use Claude Code to build a prototype with clear acceptance criteria.
Developers, automation builders, AI learners who want practical workflows AI agents, RAG, Local AI, n8n, Claude Code Start with Cole's practical agent or local AI walkthroughs, then rebuild one workflow end to end instead of watching tool overviews back to back.
AI engineers and product builders AI engineering, Developer tools, Agents, Structured data Watch talks on AI-native interfaces and structured workflows.

Resources

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.

A Complete Guide To AGENTS.md

Guide · Matt Pocock · Intermediate

You want to write project instructions that help coding agents understand commands, conventions, architecture, and working boundaries.

How To Make Codebases AI Agents Love

Guide · Matt Pocock · Intermediate

You want to improve a codebase so AI agents can navigate it, run checks, make smaller changes, and recover from mistakes more reliably.

My Skill Makes Claude Code GREAT At TDD

Guide / Claude skill · Matt Pocock · Intermediate

You want an agent workflow that implements behavior with a red, green, refactor loop instead of jumping straight to broad code changes.

Give Your Coding Agents a Memory You Own

Open-source guide and repo · Hugging Face · Intermediate

You want a September 3, 2026 walkthrough of funes, an open-source local memory layer that indexes agent traces, preserves provenance, and lets Claude Code, Codex, pi, and Hermes recall decisions across sessions and machines.

OpenAI Codex Record & Replay

Workflow guide · OpenAI · Beginner to intermediate

You want to demonstrate a stable workflow once on macOS and have ChatGPT or Codex turn it into a reusable skill for computer use, browser actions, plugins, and repeated operational work.

OpenAI Codex hooks

Coding agent guide · OpenAI · Intermediate to advanced

You need lifecycle hooks that run scripts or MCP tools around Codex sessions, prompts, tool calls, compaction, subagents, permissions, validation, logging, or persistent-memory workflows.

OpenAI Site tools with WebMCP

Web agent guide · OpenAI · Intermediate

You want a website to expose predefined actions directly to ChatGPT Work or Codex in the built-in browser, using the same live page and signed-in session as the user.

Qwen Code September 3 weekly update

Coding agent release notes · Qwen · Beginner to advanced

You want Qwen's September 3, 2026 practical guide to its latest coding-agent workflows, including learning-oriented output styles, scheduled tasks, a browser terminal, safer workspace writes, skills, MCP stability, and current vision-model support.

GPT-6 Astra launch overview

Model launch · OpenAI · Intermediate to advanced

You want OpenAI's September 3, 2026 launch overview for GPT-6 Astra, including its rollout, computer-use and coding focus, long-context behavior, benchmark disclosures, pricing, and new Codex context-retrieval workflow.

Simon Willison on GPT-6 Astra

Model analysis · Simon Willison · Intermediate to advanced

You want a concise independent read of GPT-6 Astra's launch claims, benchmark caveats, long-context results, pricing, and early comparison with Claude Fable 5.1 and GPT-5.6 Sol.

Claude Fable 5.1 model overview

Model docs · Anthropic · Intermediate to advanced

You need Anthropic's September 1, 2026 source of truth for Claude Fable 5.1 and invite-only Mythos 5.1, including model IDs, pricing, availability, long-horizon agent strengths, and breaking changes from Fable 5.

Prompting Claude Fable 5.1

Prompting guide · Anthropic · Intermediate to advanced

You are testing or migrating to Claude Fable 5.1 and want model-specific guidance for effort, progress updates, tool-call batching, long tasks, compaction, subagents, file edits, and verification.