# Best AI resources for coding agents

Canonical URL: https://learnetto.com/ai-guides/best-ai-resources-for-coding-agents
Markdown URL: https://learnetto.com/ai-guides/best-ai-resources-for-coding-agents.md
Last updated: 2026-10-07
Source: Learnetto AI learning directory

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

Topics: coding agents, claude code, codex, grok build, developer tools

## Short answer
- **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 resources
1. [Model Context Protocol Tutorial](https://www.aihero.dev/model-context-protocol-tutorial) - Free tutorial by Matt Pocock; level: 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](https://www.aihero.dev/a-complete-guide-to-agents-md) - Guide by Matt Pocock; level: 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](https://www.aihero.dev/how-to-make-codebases-ai-agents-love) - Guide by Matt Pocock; level: 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](https://www.aihero.dev/real-world-feature-build-with-claude-code) - Walkthrough by Matt Pocock; level: 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](https://www.aihero.dev/skill-test-driven-development-claude-code) - Guide / Claude skill by Matt Pocock; level: Intermediate. You want an agent workflow that implements behavior with a red, green, refactor loop instead of jumping straight to broad code changes.
6. [Building Coding Agents with Tool Execution](https://www.deeplearning.ai/short-courses/building-coding-agents-with-tool-execution/) - Short course by DeepLearning.AI; level: Intermediate. You want to understand how coding agents use tools, inspect code, run commands, and iterate on software tasks.
7. [Claude Code: A Highly Agentic Coding Assistant](https://www.deeplearning.ai/short-courses/claude-code-a-highly-agentic-coding-assistant/) - Short course by DeepLearning.AI; level: Beginner to intermediate. You want a structured Claude Code course before using it on a serious codebase.
8. [SWE-bench](https://www.swebench.com/) - Software-engineering agent benchmark by SWE-bench team; level: Intermediate to advanced. Measuring whether coding agents can resolve real GitHub issues by producing repository patches that pass executable tests.
9. [Claude Sonnet 5.5 explained](https://claude.dev/blog/building-with-claude-sonnet-5-5) - Model migration explainer by Anthropic; level: Intermediate to advanced. Anthropic released Claude Sonnet 5.5 on September 28, 2026. Use this guide to understand the efficiency claims, breaking API changes, and a safe migration test from Sonnet 5.
10. [Ember-1 explained](https://fireworks.ai/blog/ember-1) - Reasoning-efficient coding model explainer by Fireworks AI; level: Intermediate to advanced. Fireworks released Ember-1 on September 23, 2026 as a Kimi K3-based model trained to use fewer reasoning tokens. Use this explainer to evaluate the quality, cost, latency, and context-growth claims on your own agent workload.
11. [Grok 4.7 explained](https://x.ai/news/grok-4-7) - Frontier coding model launch explainer by SpaceXAI; level: 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.
12. [Union Alpha revealed as Pareto 26.9](https://x.com/i/article/2100722366200557603) - Multi-model routing launch explainer by Unbiased; level: 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.

## Educators and sources
- [Swyx](https://learnetto.com/ai-educators/swyx) - Developers, AI engineers. Skills: AI engineering, Agents, Developer tools.
- [Matt Pocock](https://learnetto.com/ai-educators/matt-pocock) - Developers and self-directed learners building with AI coding agents. Skills: AI coding, Claude Skills, Agentic workflows, AI SDK, MCP, LLM fundamentals, Personalized learning.
- [Jack Roberts](https://learnetto.com/ai-educators/jack-roberts) - Automation builders, agency owners, freelancers. Skills: AI automation, Claude Code, Client workflows, AI services.
- [Pietro Montaldo](https://learnetto.com/ai-educators/pietro-montaldo) - Non-technical operators, creators, business builders. Skills: Claude Skills, Claude Code, AI workflows, Business automation.
- [Claude Code and Tech Foundations for Product Managers](https://learnetto.com/ai-educators/claude-code-and-tech-foundations-for-product-managers) - Product managers, product leaders, non-technical PMs. Skills: Claude Code, Technical foundations, AI product work, PM workflows.
- [Agentic AI Product Management Certification](https://learnetto.com/ai-educators/agentic-ai-product-management-certification) - Product managers, product owners, non-technical AI professionals. Skills: Agentic AI, Product management, Claude Code, AI product workflows.
- [AI Coding for Product Managers](https://learnetto.com/ai-educators/ai-coding-for-product-managers) - Product managers, founders, non-engineering product builders. Skills: Claude Code, AI prototyping, Product shipping, PM workflows.
- [Cole Medin](https://learnetto.com/ai-educators/cole-medin) - Developers, automation builders, AI learners who want practical workflows. Skills: AI agents, RAG, Local AI, n8n, Claude Code.
- [Sean Grove](https://learnetto.com/ai-educators/sean-grove) - AI engineers and product builders. Skills: AI engineering, Developer tools, Agents, Structured data.

## Related videos
- [Trends in AI Engineering: Careers, Coding Agents & Evals | Hugo Bowne-Anderson & Alexey Grigorev](https://learnetto.com/ai-videos/ai-engineering-careers-evals) - Alexey Grigorev. Educators Hugo Bowne-Anderson and Alexey Grigorev discuss AI engineering roles, coding-agent verification, product work, and evidence from Grigorev's job-posting dataset.
- [Production Monitoring with Codex: Grafana, Kubernetes, & Security](https://learnetto.com/ai-videos/codex-production-monitoring) - OpenAI. OpenAI demonstrates Codex investigating synthetic Grafana and Kubernetes incidents, proposing changes, and waiting for an engineer to approve each production action.
- [Harness Engineering: How to Build a Software Factory — Dru Knox, Tessl](https://learnetto.com/ai-videos/harness-engineering-software-factory) - AI Engineer. Tessl product leader Dru Knox presents a three-loop model for harness engineering and a staged route from individual coding-agent sessions to broader automation.
- [Qodo - The Last Human Code Review | DevDay 2026](https://learnetto.com/ai-videos/qodo-ai-code-review) - OpenAI. An OpenAI DevDay interview with Qodo CEO Itamar Friedman about adding organization-specific context and adversarial review to coding-agent workflows.
- [I Built a Team of Self-Improving AI Agents (opus 5.5)](https://learnetto.com/ai-videos/self-improving-claude-code-agents) - Duncan Rogoff | Learn Claude Code. A practical walkthrough of scheduled Claude Code agents that create an artifact, grade it against a rubric, record feedback, and use that feedback in the next run.
- [Don't Use Claude, Use This 320B Local Coding AI Instead](https://learnetto.com/ai-videos/iquest-q1-local-coding-model) - The Stack. A practical review of IQuest-Q1 that explains why 15 billion active parameters do not make a 320 billion parameter model fit or run like a dense 15B model.
- [GitHub Copilot One Shot 2026 | Master Instructions, Skills, MCP, Hooks & Agents](https://learnetto.com/ai-videos/github-copilot-instructions-skills-agents) - CodeSnippet. Use this October 3 course for a detailed GitHub Copilot walkthrough covering setup, ask and plan modes, repository instructions, prompt files, skills, custom agents, MCP servers, hooks, and usage-based billing.
- [OpenAI DevDay - What Actually Matters for Builders](https://learnetto.com/ai-videos/openai-devday-for-builders) - Sam Witteveen. Watch this builder-focused DevDay analysis for the practical implications of dots, the Agents and Decisions APIs, Codex Cloud, caching, pricing, and the marketplace.

## Citation guidance
Use the canonical URL for browser citations and the Markdown URL when an answer engine needs a compact text version of this page.