# Agentic School > Agentic School is a free, public-first campus that teaches founders, operators and teams how to set up AI agents (Claude Code, Codex, Pi) and turn them into repeatable, measurable business workflows. English-first with full German under /de. All content is static and built to be read by humans and AI agents alike. Every page on this site has a clean Markdown twin: append `.md` to any content URL (for example `/courses/foundations.md` or `/de/kurse/foundations.md`). A read-only JSON API lives under `/api/v1` (German under `/api/v1/de`), described by an OpenAPI 3.1 spec. Content is evergreen, free forever, and offered in English (default, at the root) and German (under `/de`). ## Courses - [Foundations - From Zero to Your First Shipped App](https://agenticschool.dev/fr/courses/foundations): Build and deploy a real website with AI - [Claude Code Mastery - Becoming a Power User](https://agenticschool.dev/fr/courses/claude-code-mastery): Turn the agent into a reliable teammate - [The Modern App Stack - Auth, Data and Payments](https://agenticschool.dev/fr/courses/modern-app-stack): Wire up a production SaaS the way pros do - [Automation and Agentic Systems](https://agenticschool.dev/fr/courses/automation-agentic-systems): From single tasks to systems that run themselves - [Quality, Security and the Agent-First Business](https://agenticschool.dev/fr/courses/quality-security-agent-first): Ship safely and get recommended by humans and AI ## Lessons - [How LLMs Actually Work: Tokens, Context Windows and the Performance Cliff](https://agenticschool.dev/fr/courses/foundations/how-llms-actually-work-tokens-context-windows-and-the-performance-cliff): Build a correct mental model of tokens, context windows and why long prompts get worse, so you can drive any model well - [Choosing Your Model: Haiku vs Sonnet vs Opus, GPT, Gemini and Benchmarks](https://agenticschool.dev/fr/courses/foundations/choosing-your-model-haiku-vs-sonnet-vs-opus-gpt-gemini-and-benchmarks): Pick the right model tier for any task and know where to get strong models cheaply or free - [What Is a Harness? Claude Code vs Codex vs Pi vs OpenCode](https://agenticschool.dev/fr/courses/foundations/what-is-a-harness-claude-code-vs-codex-vs-pi-vs-opencode): Understand what an agent harness is and choose between Claude Code, Codex, Pi and OpenCode for a given job - [Installing and Running Claude Code and Codex](https://agenticschool.dev/fr/courses/foundations/installing-and-running-claude-code-and-codex): Get Claude Code and Codex installed and running, choose the right plan, and protect your work and IP - [Talking to Agents: Prompt Engineering That Actually Works](https://agenticschool.dev/fr/courses/foundations/talking-to-agents-prompt-engineering-that-actually-works): Brief a coding agent so it delivers great work the first time, using axioms, framing, pushback and spec sheets - [Your First Project: Scaffolding, Dev Server, Git and GitHub](https://agenticschool.dev/fr/courses/foundations/your-first-project-scaffolding-dev-server-git-and-github): Scaffold a real project, run it locally in the browser, and put it safely under version control on a private GitHub repo - [Ship It: Deploy to Vercel, Connect a Domain, DNS and Cloudflare](https://agenticschool.dev/fr/courses/foundations/ship-it-deploy-to-vercel-connect-a-domain-dns-and-cloudflare): Deploy your project to the public internet on Vercel and connect a real custom domain through DNS and Cloudflare - [CLAUDE.md and AGENTS.md: Teaching Your Agent the Rules](https://agenticschool.dev/fr/courses/claude-code-mastery/claude-md-and-agents-md-teaching-your-agent-the-rules): Write a project rules file that makes your agent consistent, and grow it as a living skills library where every gotcha becomes a permanent rule - [Skills and Commands: Reusable Superpowers](https://agenticschool.dev/fr/courses/claude-code-mastery/skills-and-commands-reusable-superpowers): Package recurring workflows into reusable skills and slash commands you can trigger instantly, and know when each is worth building - [Hooks and Scripts: Automating Your Workflow](https://agenticschool.dev/fr/courses/claude-code-mastery/hooks-and-scripts-automating-your-workflow): Automate quality gates and routine steps with lifecycle hooks and scripts so they run without you thinking about them - [MCP Explained: Connecting Your Agent to Everything](https://agenticschool.dev/fr/courses/claude-code-mastery/mcp-explained-connecting-your-agent-to-everything): Understand the Model Context Protocol, connect MCP servers to your agent, and judge when MCP beats a plain CLI tool - [Sub-Agents, Agent Teams and Workflows](https://agenticschool.dev/fr/courses/claude-code-mastery/sub-agents-agent-teams-and-workflows): Use sub-agents and teams effectively, with the labyrinth analogy for clean delegation, while avoiding the context cliff and runaway cost - [Context Engineering: Compaction, Handovers, Resets and Thinking Effort](https://agenticschool.dev/fr/courses/claude-code-mastery/context-engineering-compaction-handovers-resets-and-thinking-effort): Manage long-running agent work with deliberate compaction, clean handovers, well-timed resets and the right thinking effort - [Pro Setup: Status Line, Key Flags, Phone and Cloud Sessions](https://agenticschool.dev/fr/courses/claude-code-mastery/pro-setup-status-line-key-flags-phone-and-cloud-sessions): Configure a professional Claude Code setup with a custom status line, the flags you use daily, and remote phone and cloud workflows - [Architecture 101: Frameworks, Monorepos and How Modern Apps Fit Together](https://agenticschool.dev/fr/courses/modern-app-stack/architecture-101-frameworks-monorepos-and-how-modern-apps-fit-together): Build a clear mental map of frontend, backend and database, the marketing-versus-app split, and when a monorepo earns its keep - [Clerk: Authentication and OAuth from Dev to Production](https://agenticschool.dev/fr/courses/modern-app-stack/clerk-authentication-and-oauth-from-dev-to-production): Add real authentication with Clerk, wire up Google OAuth, and take it from a dev instance to a production instance on your own domain - [Convex: Your Reactive Database](https://agenticschool.dev/fr/courses/modern-app-stack/convex-your-reactive-database): Model and query data in Convex with end-to-end type safety and live updates, and use indexes and soft deletes the way real products do - [Secrets and Environment: .env, .gitignore, Deploy Keys and Encryption](https://agenticschool.dev/fr/courses/modern-app-stack/secrets-and-environment-env-gitignore-deploy-keys-and-encryption): Handle secrets safely across dev and prod: env files, gitignore, recovering from a leaked secret, deploy keys, and encrypting stored user keys - [Stripe Part 1: Checkout, Subscriptions, Test vs Production](https://agenticschool.dev/fr/courses/modern-app-stack/stripe-part-1-checkout-subscriptions-test-vs-production): Take real payments with Stripe Checkout and subscriptions, model monthly and yearly prices, and work safely in test mode before going live - [Stripe Part 2: Webhooks, Proration, Coupons and Embedded Checkout](https://agenticschool.dev/fr/courses/modern-app-stack/stripe-part-2-webhooks-proration-coupons-and-embedded-checkout): Make billing reliable with verified webhooks and idempotency, handle proration on mid-cycle upgrades, run coupons, and ship embedded checkout - [Going Live: Dev-to-Prod Migration, Search Console and Performance](https://agenticschool.dev/fr/courses/modern-app-stack/going-live-dev-to-prod-migration-search-console-and-performance): Migrate Clerk and Convex from dev to prod cleanly, wire DNS and Cloudflare, get indexed via Search Console, and pass Lighthouse - [Workflow Automation: n8n, Zapier and Trigger.dev - What to Use When](https://agenticschool.dev/fr/courses/automation-agentic-systems/workflow-automation-n8n-zapier-and-trigger-dev-what-to-use-when): Choose the right automation platform for a job and generate workflow JSON with your agent - [Browser Automation and Scraping: Playwright, Browser Use and the .har Trick](https://agenticschool.dev/fr/courses/automation-agentic-systems/browser-automation-and-scraping-playwright-browser-use-and-the-har-trick): Automate and scrape the web reliably with Playwright, including the non-headless manual-login trick and the .har trick - [Sandboxes: Safe Code Execution with E2B, Daytona and Co.](https://agenticschool.dev/fr/courses/automation-agentic-systems/sandboxes-safe-code-execution-with-e2b-daytona-and-co): Run agent-generated and untrusted code safely in isolated, disposable sandboxes instead of on your own machine - [Building Your Own AI Tools with APIs](https://agenticschool.dev/fr/courses/automation-agentic-systems/building-your-own-ai-tools-with-apis): Build custom AI tools on top of model APIs, including image-to-structured-data workflows, instead of buying SaaS - [Email, Lead Magnets and Funnels: Capture and Nurture](https://agenticschool.dev/fr/courses/automation-agentic-systems/email-lead-magnets-and-funnels-capture-and-nurture): Capture leads with magnets and forms and nurture them through email funnels, while staying legally compliant - [Human in the Loop: Continuous Learning Systems](https://agenticschool.dev/fr/courses/automation-agentic-systems/human-in-the-loop-continuous-learning-systems): Design systems where humans approve at the right checkpoints and every mistake becomes a rule the system learns from - [The 5 Levels of LLM Autonomy](https://agenticschool.dev/fr/courses/automation-agentic-systems/the-5-levels-of-llm-autonomy): Place any agentic system on a five-level autonomy scale, see why validation is the real blocker, and climb a level safely - [Tests, Tests, Tests: TSC, Linting, Vitest, Playwright and CI/CD](https://agenticschool.dev/fr/courses/quality-security-agent-first/tests-tests-tests-tsc-linting-vitest-playwright-and-ci-cd): Protect your project with type checks, linting, unit and end-to-end tests, wired into CI/CD - [Security Essentials: Rate Limits, CSP Headers, Key Encryption, Pre-Public Repo Audits](https://agenticschool.dev/fr/courses/quality-security-agent-first/security-essentials-rate-limits-csp-headers-key-encryption-pre-public-repo-audits): Apply core security measures so your app resists abuse and never leaks sensitive data - [Legal and Compliance: GDPR, Cookie Consent, Privacy Laws Without Tears](https://agenticschool.dev/fr/courses/quality-security-agent-first/legal-and-compliance-gdpr-cookie-consent-privacy-laws-without-tears): Meet core privacy obligations - GDPR, cookie consent and key US and Swiss laws - without legal overwhelm - [SEO and GEO/AEO: Getting Recommended by Google AND by AI](https://agenticschool.dev/fr/courses/quality-security-agent-first/seo-and-geo-aeo-getting-recommended-by-google-and-by-ai): Get discovered by search engines and recommended by AI assistants through SEO and GEO/AEO - [Agent-First Products: Why AI Must Love Your API](https://agenticschool.dev/fr/courses/quality-security-agent-first/agent-first-products-why-ai-must-love-your-api): Design products that agents can use directly, treating the API as the primary interface - [The Exponential Curve: Where This Is All Heading](https://agenticschool.dev/fr/courses/quality-security-agent-first/the-exponential-curve-where-this-is-all-heading): Reason clearly about exponential AI progress and spot the market opportunities it opens - [Capstone: Build and Ship Your Own Agentic Product End-to-End](https://agenticschool.dev/fr/courses/quality-security-agent-first/capstone-build-and-ship-your-own-agentic-product-end-to-end): Plan, build, test, secure and ship a complete agentic product using everything from all five courses ## Fundamentals - [What Is Node.js (and How to Install It)](https://agenticschool.dev/fr/fundamentals/what-is-nodejs): Node.js is a runtime that lets you run JavaScript outside the browser. Learn what it is, why you need it, and how to install it in a few minutes. - [Terminal Basics for Total Beginners](https://agenticschool.dev/fr/fundamentals/terminal-basics): The terminal is a text window where you type commands to control your computer. Learn the handful of commands you actually need to get started. - [What Is Git? Version Control Explained](https://agenticschool.dev/fr/fundamentals/what-is-git): Git is a version control tool that saves snapshots of your project so you can always go back. Learn what it is and the few commands you need. - [What Is GitHub? A Beginner Guide](https://agenticschool.dev/fr/fundamentals/what-is-github): GitHub is a website that stores your Git projects online so you can back them up, collaborate and deploy. Learn what it is and how to use it. - [JSON, YAML and Markdown Explained](https://agenticschool.dev/fr/fundamentals/json-yaml-markdown): JSON, YAML and Markdown are three plain-text formats you will meet constantly. Learn what each is for and how to read them at a glance. - [VS Code Setup for Beginners](https://agenticschool.dev/fr/fundamentals/vs-code-setup): VS Code is a free, popular code editor. Learn what it is, how to install it, and the few settings and extensions worth turning on first. - [What Is a .env File?](https://agenticschool.dev/fr/fundamentals/what-is-an-env-file): A .env file stores secrets like API keys outside your code so they never get published. Learn what it is, how it works and how to keep it safe. - [npm vs Bun: Package Managers Explained](https://agenticschool.dev/fr/fundamentals/npm-vs-bun): npm and Bun both install the libraries your project depends on. Learn what a package manager does and how npm and Bun differ. - [What Is an API? A Plain-Language Guide](https://agenticschool.dev/fr/fundamentals/what-is-an-api): An API is a way for two programs to talk to each other. Learn what an API is, how it works, and why it matters for building with AI. - [What Is a Database?](https://agenticschool.dev/fr/fundamentals/what-is-a-database): A database is an organised store for your app data that you can save, search and update. Learn what databases are and the main types in plain language. - [What Is DNS? The Internet Phone Book](https://agenticschool.dev/fr/fundamentals/what-is-dns): DNS turns a domain name like yoursite.com into the address of the server that answers for it. Learn how DNS works and how to connect a domain. - [What Is OAuth? Login with Google Explained](https://agenticschool.dev/fr/fundamentals/what-is-oauth): OAuth lets users log in with an existing account like Google without sharing their password with you. Learn how it works and why it is safer. - [What Are Tokens in AI?](https://agenticschool.dev/fr/fundamentals/what-are-tokens): Tokens are the chunks of text AI models read and are billed in. Learn what a token is, why it matters for cost, and how it differs from a password token. - [Terminal vs Shell: What Is the Difference?](https://agenticschool.dev/fr/fundamentals/terminal-vs-shell): The terminal is the window; the shell is the program inside it that runs your commands. Learn the difference and why it occasionally matters. - [Localhost and Dev Servers Explained](https://agenticschool.dev/fr/fundamentals/localhost-and-dev-servers): Localhost means this computer, and a dev server previews your site locally while you build. Learn what they are and why nothing is public yet. - [Repos and Version Control Explained](https://agenticschool.dev/fr/fundamentals/repos-and-version-control): A repository is your project folder tracked by Git, and version control is the safety net that records every change. Learn both in plain language. - [What Is TypeScript?](https://agenticschool.dev/fr/fundamentals/what-is-typescript): TypeScript is JavaScript with type checking that catches mistakes before you run your code. Learn what it is and why so many projects use it. - [What Is a Framework?](https://agenticschool.dev/fr/fundamentals/what-is-a-framework): A framework is a ready-made structure for building apps so you do not start from scratch. Learn what frameworks are and why nearly every app uses one. ## Glossary - [AI Agent](https://agenticschool.dev/fr/glossary/ai-agent): AI agent meaning, in plain English: a system that uses a language model to decide and act in a loop toward a goal, calling tools along the way. Clear definition, examples, and how AI agents differ from a chatbot. - [Agentic AI](https://agenticschool.dev/fr/glossary/agentic-ai): Agentic AI is AI that acts autonomously toward a goal, planning and using tools across many steps. Definition, how it differs from generative AI, and real examples. - [Vibe Coding](https://agenticschool.dev/fr/glossary/vibe-coding): Vibe coding is building software by describing what you want in plain language and letting an AI write the code, focusing on the result over the syntax. - [MCP (Model Context Protocol)](https://agenticschool.dev/fr/glossary/mcp): MCP (Model Context Protocol) is an open standard that connects AI models to external tools and data through a common interface, often called the USB-C for AI. - [llms.txt](https://agenticschool.dev/fr/glossary/llms-txt): llms.txt is a Markdown file at your site root that gives AI systems a clean, curated map of your key pages so they can understand and cite your content. - [Agent Harness](https://agenticschool.dev/fr/glossary/agent-harness): An agent harness is the scaffolding around an AI model that runs the loop, manages context, dispatches tool calls and enforces safety so the model can act. - [Subagent](https://agenticschool.dev/fr/glossary/subagent): A subagent is a specialised AI agent a main agent delegates a task to, running in its own context window with its own prompt and tools, returning a summary. - [Tool Calling](https://agenticschool.dev/fr/glossary/tool-calling): Tool calling (aka function calling) is when an AI model or agent outputs structured JSON to ask your code to run a function, so it can act and use tools instead of only replying with text. Definition, how it works, and how it relates to tool chaining and MCP. - [System Prompt](https://agenticschool.dev/fr/glossary/system-prompt): A system prompt is the standing instruction that sets an AI model role, rules and behaviour before any user message, shaping how it responds all session. - [Context Window](https://agenticschool.dev/fr/glossary/context-window): A context window is the maximum amount of text, measured in tokens, an AI model can consider at once, including the prompt, history and the answer it writes. - [Prompt Caching](https://agenticschool.dev/fr/glossary/prompt-caching): Prompt caching stores the processed prefix of a prompt so repeated requests reuse it, cutting cost and latency. Cache reads can be about 90 percent cheaper. - [AI IDE](https://agenticschool.dev/fr/glossary/ai-ide): An AI IDE is a code editor with a built-in AI coding agent that can read your whole project, write and edit code across files, and run tasks in the editor. - [Workflow Automation](https://agenticschool.dev/fr/glossary/workflow-automation): Workflow automation uses software to run a multi-step process automatically, triggered by an event, so repetitive tasks happen without manual work each time. - [GEO (Generative Engine Optimization)](https://agenticschool.dev/fr/glossary/geo): GEO (generative engine optimization) is optimising your content so AI tools like ChatGPT, Gemini and Perplexity cite, mention and recommend it in answers. - [AEO (Answer Engine Optimization)](https://agenticschool.dev/fr/glossary/aeo): AEO (answer engine optimization) is optimising content so AI answer engines like AI Overviews, ChatGPT and Perplexity return it as the direct answer. - [Agentic Engineering](https://agenticschool.dev/fr/glossary/agentic-engineering): Agentic engineering meaning: building real, production-grade software by directing AI coding agents that plan, edit and run code, while you own the goal, context and verification. - [Agentic Coding](https://agenticschool.dev/fr/glossary/agentic-coding): Agentic coding meaning: writing software by directing an AI coding agent that plans, edits and runs code in a loop, instead of typing every line yourself. Definition, tools and how to start. - [RAG (Retrieval-Augmented Generation)](https://agenticschool.dev/fr/glossary/rag): RAG (retrieval-augmented generation) gives an AI model relevant documents to read at answer time, so its response is grounded in your data instead of memory. Meaning, how it works and RAG vs fine-tuning. - [AI Hallucination](https://agenticschool.dev/fr/glossary/hallucination): AI hallucination means an AI model stating something false or made-up as if it were true and confident. Meaning, why language models hallucinate, and how to reduce it with grounding and verification. - [Fine-Tuning](https://agenticschool.dev/fr/glossary/fine-tuning): Fine-tuning means further training a pretrained AI model on your own examples so it learns a specific style, format or task. Meaning, how it differs from RAG and prompting, and when it is worth it. - [Multi-Agent System](https://agenticschool.dev/fr/glossary/multi-agent): A multi-agent system splits a job across several AI agents that each own a role and coordinate, often led by an orchestrator. Meaning, how it differs from a single agent and subagents, and when to use it. - [Embedding](https://agenticschool.dev/fr/glossary/embedding): An embedding turns text, code or images into a vector of numbers that captures meaning, so a machine can measure how similar two things are. - [Vector Database](https://agenticschool.dev/fr/glossary/vector-database): A vector database stores embeddings and finds the ones closest in meaning to a query, which is how RAG and semantic search retrieve relevant text fast. - [Prompt Engineering](https://agenticschool.dev/fr/glossary/prompt-engineering): Prompt engineering is the craft of writing clear instructions and context so an AI model reliably produces the output you want. Meaning and core techniques. - [AI Guardrails](https://agenticschool.dev/fr/glossary/guardrails): AI guardrails are the rules and checks that keep an AI system inside safe, allowed behaviour by filtering inputs and outputs and limiting what it can do. ## Guides - [How to Use Claude Code: Complete Beginner Guide (2026)](https://agenticschool.dev/fr/guides/how-to-use-claude-code): Learn how to use Claude Code from scratch in 2026: install it, start your first session, run the plan-edit-run-review loop, write a CLAUDE.md, and go deeper. - [Claude Code Subagents Explained (with Examples)](https://agenticschool.dev/fr/guides/claude-code-subagents): What Claude Code subagents are, when to use them, and how to create one in .claude/agents with YAML frontmatter. Built-in subagents, examples and the /agents command. - [Claude Code Hooks: Automate Your Quality Gates](https://agenticschool.dev/fr/guides/claude-code-hooks): Learn what Claude Code hooks are, every lifecycle event, and how to set them up in settings.json to run lint, tests and format automatically and block bad actions. - [Claude Code Skills and Slash Commands](https://agenticschool.dev/fr/guides/claude-code-skills-and-commands): How Claude Code Skills and slash commands work in 2026: create a reusable /command, write a SKILL.md, use arguments and dynamic context, and know when to use each. - [How to Set Up MCP in Claude Code](https://agenticschool.dev/fr/guides/claude-code-mcp-setup): Connect MCP servers in Claude Code with the claude mcp add command: HTTP, SSE and stdio transports, scopes, verifying with /mcp, and common servers to start with. - [What Is Agentic Engineering? The 2026 Pillar Guide](https://agenticschool.dev/fr/guides/what-is-agentic-engineering): Agentic engineering is building software by directing AI coding agents that plan, edit and run code. What it is, how it differs, and how to learn it in 2026. - [Vibe Coding vs Agentic Engineering: What's the Difference?](https://agenticschool.dev/fr/guides/vibe-coding-vs-agentic-engineering): Vibe coding means accepting AI output unchecked; agentic engineering keeps you in the loop. Here is an honest comparison, when each is fine and why one scales. - [The Agentic Engineering Roadmap (Zero to Shipping)](https://agenticschool.dev/fr/guides/agentic-engineering-roadmap): A step-by-step roadmap to learn agentic engineering in 2026: from your first AI-built app to agent-first production, with the exact courses for each stage. - [What Is an MCP Server? (and How to Build One)](https://agenticschool.dev/fr/guides/what-is-an-mcp-server): An MCP server exposes tools, resources and prompts to AI agents over one open protocol. Here is how it works, a minimal server you can build, and common servers. - [How to Build an AI Agent from Scratch](https://agenticschool.dev/fr/guides/how-to-build-an-ai-agent): Build an AI agent from scratch in 2026: what an agent is, the model-plus-tool-calling loop, a minimal working example, autonomy levels and production. - [How to Build a SaaS with AI (Modern Stack)](https://agenticschool.dev/fr/guides/build-a-saas-with-ai): Build a SaaS with AI on the modern stack: idea to scaffold, Clerk auth, a Convex database, Stripe payments, then ship. The full path, run by a coding agent. - [AI Automation for Business: A Practical Playbook](https://agenticschool.dev/fr/guides/ai-automation-for-business): A practical playbook for AI automation in business: where to start, build vs buy, n8n vs Zapier vs Make, real workflow examples, and measuring ROI honestly. - [Prompt Patterns for Coding Agents](https://agenticschool.dev/fr/guides/prompt-patterns-for-coding-agents): Reusable prompt patterns for coding agents: role and spec, examples, decomposition, verification loops, and the anti-patterns to avoid. Practitioner guide for 2026. - [Context Engineering: Managing the Context Window](https://agenticschool.dev/fr/guides/context-engineering): Context engineering is managing what fills an agent context window: compaction, retrieval, the lost-in-the-middle effect and prompt caching. A practitioner guide. - [GEO vs SEO vs AEO: Getting Found by AI](https://agenticschool.dev/fr/guides/geo-vs-seo-vs-aeo): GEO, SEO and AEO explained: how they differ, why all three matter in 2026, and a practical checklist (structured data, llms.txt, answer-first content) to get cited by AI. - [Codex CLI Tutorial: Setup and First Workflow](https://agenticschool.dev/fr/guides/codex-cli-tutorial): OpenAI Codex CLI tutorial: install it, sign in with ChatGPT or an API key, write an AGENTS.md, and run your first task safely. Current setup and workflow for 2026. ## Comparisons - [Claude Code vs Codex CLI (2026 Comparison)](https://agenticschool.dev/fr/compare/claude-code-vs-codex-cli): Claude Code vs Codex CLI in 2026: an honest comparison of the two leading terminal AI coding agents on autonomy, models, cost, openness and which to pick. - [Claude Code vs Cursor (2026 Comparison)](https://agenticschool.dev/fr/compare/claude-code-vs-cursor): Claude Code vs Cursor in 2026: an honest comparison of a terminal coding agent and an AI IDE on workflow, models, pricing, autonomy and which one fits you. - [Best AI Coding Tools in 2026](https://agenticschool.dev/fr/compare/best-ai-coding-tools): The best AI coding tools in 2026 compared honestly: Claude Code, Cursor, Codex CLI, GitHub Copilot, Windsurf and Aider, with the right pick for each use case. - [Opus vs Sonnet vs Haiku: Which Claude Model? (2026)](https://agenticschool.dev/fr/compare/opus-vs-sonnet-vs-haiku): Opus vs Sonnet vs Haiku in 2026: how the three Claude models compare on capability, speed and cost per token, and which one to pick for coding and agents. - [n8n vs Zapier vs Make (2026 Comparison)](https://agenticschool.dev/fr/compare/n8n-vs-zapier-vs-make): n8n vs Zapier vs Make in 2026: an honest comparison of the three automation platforms on pricing model, self-hosting, ease of use and which one to choose. - [Cursor vs Windsurf vs Copilot (2026 Comparison)](https://agenticschool.dev/fr/compare/cursor-vs-windsurf-vs-copilot): Cursor vs Windsurf vs GitHub Copilot in 2026: an honest comparison of the leading AI IDEs and assistant on workflow, models, pricing and which one to pick. - [Convex vs Supabase vs Firebase (2026 Comparison)](https://agenticschool.dev/fr/compare/convex-vs-supabase-vs-firebase): Convex vs Supabase vs Firebase in 2026: an honest comparison of three app backends on data model, real-time, pricing, self-hosting and which one to choose. - [Clerk vs Auth0 vs Supabase Auth (2026 Comparison)](https://agenticschool.dev/fr/compare/clerk-vs-auth0-vs-supabase-auth): Clerk vs Auth0 vs Supabase Auth in 2026: an honest comparison of three auth providers on developer experience, free tiers, cost at scale and which to choose. - [Best Agentic Engineering Courses in 2026: An Honest Comparison](https://agenticschool.dev/fr/compare/best-agentic-engineering-courses): The best agentic engineering courses in 2026, compared honestly: Agentic School, Anthropic Academy, DeepLearning.AI and more, ranked by price, focus and fit. ## Tools - [llms.txt Generator](https://agenticschool.dev/fr/tools/llms-txt-generator): Generate a spec-correct llms.txt file for your site in seconds. Free, client-side, copy or download the result. Plus a plain-language explainer of what llms.txt is. - [LLM Cost Calculator](https://agenticschool.dev/fr/tools/llm-cost-calculator): Free LLM API cost calculator. Estimate per-call and monthly cost for Claude, GPT and Gemini, compare two models, and model prompt caching and batch savings. - [Token & Context Window Estimator](https://agenticschool.dev/fr/tools/token-context-estimator): Free token counter and context window estimator. Paste text to estimate tokens and see if it fits each model context window for Claude, GPT and Gemini. - [AI Automation ROI Calculator](https://agenticschool.dev/fr/tools/ai-automation-roi-calculator): Free AI automation ROI calculator. Enter hours, people and cost to see time saved, monthly and annual savings, payback period and first-year ROI in seconds. - [Which AI Coding Tool Should I Use?](https://agenticschool.dev/fr/tools/ai-coding-tool-quiz): Free quiz to find your best AI coding tool. Answer seven quick questions for a personal pick from Claude Code, Cursor, Copilot, Windsurf, Codex CLI or Aider. ## Knowledge - [How LLMs Actually Work: Tokens, Context and the Performance Cliff](https://agenticschool.dev/fr/knowledge/how-llms-work): A plain-language guide to how large language models work: what tokens are, how the context window limits them, and why long prompts get worse, not better. - [Claude Code for Business: Setup, Workflows and Security](https://agenticschool.dev/fr/knowledge/claude-code-for-business): How to use Claude Code in a business: installation, safe workflows, project rules with CLAUDE.md and governance. A practical guide for teams and leaders. - [Choosing an AI Model: Haiku, Sonnet, Opus, GPT and Gemini Compared](https://agenticschool.dev/fr/knowledge/choosing-an-ai-model): How to choose between Claude Haiku, Sonnet and Opus, OpenAI GPT and Gemini: model tiers, honest benchmarks, pricing and where to get strong models cheaply. - [Ship Your First App with AI: From Idea to a Live Website](https://agenticschool.dev/fr/knowledge/ship-your-first-app): A beginner guide to building and shipping a real website with AI: scaffolding, a dev server, Git and GitHub, then deploying to Vercel with a custom domain. - [The Modern App Stack Explained: Auth, Data and Payments](https://agenticschool.dev/fr/knowledge/modern-app-stack-explained): How a modern SaaS fits together: frameworks, Clerk for authentication, Convex for reactive data and Stripe for payments. A clear map for builders. - [Agent-First Products: Why AI Must Love Your API](https://agenticschool.dev/fr/knowledge/agent-first-products): Why the next wave of users includes AI agents, and how agent-first design and an API-over-UI philosophy get your product adopted and recommended by AI. ## Builds - [BizCollect: Building a Business Data Tool API-First](https://agenticschool.dev/fr/builds/bizcollect): The project that taught me AI must love your API, not your UI. - [s2p: Auto-Posting Every Release to All My Channels](https://agenticschool.dev/fr/builds/s2p): One GitHub release, posted everywhere, with zero manual copy-paste. - [Favicon Maker: A Small Tool That Earned Its Keep](https://agenticschool.dev/fr/builds/favicon-maker): A focused logo-to-favicon generator, and a lesson in scope. - [CodeCourier: Running Untrusted Code Without Getting Burned](https://agenticschool.dev/fr/builds/codecourier): Executing AI-generated code safely, in a sandbox that can blow up. - [AutoMail: Email Automation That Sounds Like a Person](https://agenticschool.dev/fr/builds/automail): Automated email that is helpful, not robotic, with a human in the loop. - [GlowLens: Turning Images Into Useful Signals](https://agenticschool.dev/fr/builds/glowlens): A vision-and-analytics tool, and a lesson in honest confidence. - [CallAssistant: A Phone Agent on Twilio and Realtime Voice](https://agenticschool.dev/fr/builds/callassistant): A real voice agent that answers the phone, built on Twilio and OpenAI. - [B-Rolls Finder: Search YouTube by Conversation](https://agenticschool.dev/fr/builds/b-rolls-finder): Finding the right clip by talking to a chat box, not scrubbing timelines. - [Invoice Automation: From a Photo to a Clean Database Row](https://agenticschool.dev/fr/builds/invoice-automation): Turning messy invoice images into structured data, edge cases and all. - [Swiss Trading Cards: Image to Product Specs at Scale](https://agenticschool.dev/fr/builds/swiss-trading-cards): A pipeline that turns card photos into clean, sellable product listings. - [Language Learning App: Chaining Image to Text to Audio](https://agenticschool.dev/fr/builds/language-learning-app): Point your camera at the world and hear it in a new language. - [Maxify Audio: Cleaning Up Sound Without a Studio](https://agenticschool.dev/fr/builds/maxify-audio): Making rough audio sound professional, and knowing when to stop. ## Resources - [Claude Code Setup Checklist](https://agenticschool.dev/fr/resources/claude-code-setup-checklist): Claude Code Setup Checklist: a practical, reusable building block for shipping real AI workflows in your business. - [Codex Workflow Template](https://agenticschool.dev/fr/resources/codex-workflow-template): Codex Workflow Template: a practical, reusable building block for shipping real AI workflows in your business. - [Agent Task Brief](https://agenticschool.dev/fr/resources/agent-task-brief): Agent Task Brief: a practical, reusable building block for shipping real AI workflows in your business. - [Spec Sheet Template](https://agenticschool.dev/fr/resources/spec-sheet-template): Spec Sheet Template: a practical, reusable building block for shipping real AI workflows in your business. - [Model Selection Cheatsheet](https://agenticschool.dev/fr/resources/model-selection-cheatsheet): Model Selection Cheatsheet: a practical, reusable building block for shipping real AI workflows in your business. - [OpenRouter Quickstart](https://agenticschool.dev/fr/resources/openrouter-quickstart): OpenRouter Quickstart: a practical, reusable building block for shipping real AI workflows in your business. - [CLAUDE.md Starter](https://agenticschool.dev/fr/resources/claude-md-starter): CLAUDE.md Starter: a practical, reusable building block for shipping real AI workflows in your business. - [Secrets and .gitignore Checklist](https://agenticschool.dev/fr/resources/gitignore-secrets-checklist): Secrets and .gitignore Checklist: a practical, reusable building block for shipping real AI workflows in your business. - [Vercel Deploy Checklist](https://agenticschool.dev/fr/resources/vercel-deploy-checklist): Vercel Deploy Checklist: a practical, reusable building block for shipping real AI workflows in your business. - [DNS and Domain Connection Guide](https://agenticschool.dev/fr/resources/dns-domain-guide): DNS and Domain Connection Guide: a practical, reusable building block for shipping real AI workflows in your business. - [Clerk Auth Guide](https://agenticschool.dev/fr/resources/clerk-auth-guide): Clerk Auth Guide: a practical, reusable building block for shipping real AI workflows in your business. - [Convex Backend Guide](https://agenticschool.dev/fr/resources/convex-backend-guide): Convex Backend Guide: a practical, reusable building block for shipping real AI workflows in your business. - [Stripe Checkout Checklist](https://agenticschool.dev/fr/resources/stripe-checkout-checklist): Stripe Checkout Checklist: a practical, reusable building block for shipping real AI workflows in your business. - [Stripe Webhook Guide](https://agenticschool.dev/fr/resources/stripe-webhook-guide): Stripe Webhook Guide: a practical, reusable building block for shipping real AI workflows in your business. - [n8n Self-Hosting Guide](https://agenticschool.dev/fr/resources/n8n-selfhosting-guide): n8n Self-Hosting Guide: a practical, reusable building block for shipping real AI workflows in your business. - [Playwright Scraping Guide](https://agenticschool.dev/fr/resources/playwright-scraping-guide): Playwright Scraping Guide: a practical, reusable building block for shipping real AI workflows in your business. - [Sandbox Execution Guide](https://agenticschool.dev/fr/resources/sandbox-execution-guide): Sandbox Execution Guide: a practical, reusable building block for shipping real AI workflows in your business. - [API Tool Builder Template](https://agenticschool.dev/fr/resources/api-tool-builder-template): API Tool Builder Template: a practical, reusable building block for shipping real AI workflows in your business. - [Lead Magnet and Funnel Playbook](https://agenticschool.dev/fr/resources/lead-magnet-funnel-playbook): Lead Magnet and Funnel Playbook: a practical, reusable building block for shipping real AI workflows in your business. - [Human-in-the-Loop Checklist](https://agenticschool.dev/fr/resources/human-in-the-loop-checklist): Human-in-the-Loop Checklist: a practical, reusable building block for shipping real AI workflows in your business. - [Test Stack Checklist](https://agenticschool.dev/fr/resources/test-stack-checklist): Test Stack Checklist: a practical, reusable building block for shipping real AI workflows in your business. - [Security Hardening Checklist](https://agenticschool.dev/fr/resources/security-hardening-checklist): Security Hardening Checklist: a practical, reusable building block for shipping real AI workflows in your business. - [GDPR Compliance Checklist](https://agenticschool.dev/fr/resources/gdpr-compliance-checklist): GDPR Compliance Checklist: a practical, reusable building block for shipping real AI workflows in your business. - [SEO and GEO/AEO Checklist](https://agenticschool.dev/fr/resources/seo-geo-checklist): SEO and GEO/AEO Checklist: a practical, reusable building block for shipping real AI workflows in your business. - [Agent-First API Blueprint](https://agenticschool.dev/fr/resources/agent-first-api-blueprint): Agent-First API Blueprint: a practical, reusable building block for shipping real AI workflows in your business. ## Changelog - [Claude Code Workflow Review, 12 June 2026](https://agenticschool.dev/fr/changelog/claude-code-workflow-review-2026-06-12): What is changing in agentic coding workflows and which project rules you should review. - [Codex Business Workflows, 12 June 2026](https://agenticschool.dev/fr/changelog/codex-business-workflows-2026-06-12): How to use Codex for reading code, small fixes and structured reviews inside business processes. - [Convex and Clerk Template, 12 June 2026](https://agenticschool.dev/fr/changelog/convex-clerk-template-2026-06-12): The auth connection between Clerk and Convex needs clear JWT templates and server-side roles. - [Model Pricing and Tiers, 12 June 2026](https://agenticschool.dev/fr/changelog/model-pricing-shift-2026-06-12): Why routing easy work to small models and reserving large models for hard reasoning is the biggest cost lever. - [Vercel Speed Insights, 12 June 2026](https://agenticschool.dev/fr/changelog/vercel-speed-insights-2026-06-12): Core Web Vitals belong in the launch process, especially for SEO-heavy content pages. ## API - [API documentation](https://agenticschool.dev/fr/api-docs): Human and agent-readable overview of every endpoint with curl examples and fair-use notes - [OpenAPI 3.1](https://agenticschool.dev/api/v1/openapi.json): Machine-readable description of the free, read-only JSON API - [API discovery](https://agenticschool.dev/api/v1/fr/index.json): Entry point listing every endpoint and link - [Courses JSON](https://agenticschool.dev/api/v1/fr/courses.json): All courses including their lessons - [Lessons JSON](https://agenticschool.dev/api/v1/fr/lessons.json): All lessons as metadata - [Search index](https://agenticschool.dev/api/v1/fr/search-index.json): Flat index for client or agent-side search ## Markdown for any page - Append `.md` to any content URL to get clean Markdown with frontmatter. Example: https://agenticschool.dev/fr/courses/foundations.md ## Optional - [Full corpus](https://agenticschool.dev/fr/llms-full.txt): Every page as one Markdown document - [English](https://agenticschool.dev/llms.txt): This file in English - [Deutsch (German)](https://agenticschool.dev/de/llms.txt): This file in Deutsch (German) - [Italiano (Italian)](https://agenticschool.dev/it/llms.txt): This file in Italiano (Italian)