Learn AI Agents vs Inside AI

Learn how AI agents work, then build your own. Learn AI Agents is a hands-on course on your phone: short lessons on LLMs, tool calling, RAG and multi-agent systems, a lab where you run real agents and watch every step, and an AI mentor for the moments you get stuck. No machine learning background needed. The lessons start from "what is an LLM agent?" and build up one step at a time, with real Python code from the first course. Think of it as an agentic AI tutorial you can follow five minutes at a time, on the bus or between meetings. WHAT YOU WILL LEARN • Under the hood: goal, tools, memory, steps and the final answer • Tool calling and function calling with real Python examples • Prompt engineering: system prompts, guardrails and step budgets • RAG and vector databases: answer questions from your own documents • Memory, planning and the ReAct loop • Multi-agent orchestration: pipelines, routers, parallel workers and critic loops • LangChain, LangGraph and LlamaIndex patterns next to plain OpenAI and Anthropic API code • Evaluation, cost control, prompt injection and other safety risks • Computer use, governance and where the field is heading AN AGENT LAB IN YOUR POCKET • Live runs: give an agent a task and watch each tool call, result and answer appear step by step • Agent Builder: pick a system prompt, tools, a step budget and a task, then save your own agents • Orchestration Lab: compare five patterns side by side — single agent, sequential pipeline, router, parallel fan-out and generator with critic • Trace viewer: read every run like a debugger and see exactly where it went wrong • Daily drill: one short question a day that keeps your streak alive PRACTICE, NOT JUST THEORY • 200+ bite-sized lessons across 60 courses, 5–10 minutes each • Hundreds of Python examples you can run right inside the lesson • Lab missions: make your first tool call, fix a broken call, read a trace, add a guardrail, route a task and split work across parallel agents • A quiz in every lesson to check what you learned • Certificate of completion: pass the final exam and show your skills YOUR AI MENTOR Not sure why your bot picked the wrong tool? Confused by embeddings or a Python error? Ask the mentor and get a clear answer in seconds, in plain language. No question is too basic. WHY AGENTIC AI? An agent does more than chat. It plans, calls tools, reads results and decides what to do next. That is where automation is heading. Knowing how such systems fail is as important as knowing how they work. This course teaches both: you watch runs succeed, you watch them break, and you learn the guardrails that keep them honest. FREE TO START Your first course, one lab pattern, your first Builder design and a daily allowance of live runs are free. Pro unlocks every course and every orchestration pattern, removes the daily run limit and removes ads. The app interface is available in 22 languages. Part of CoddyKit, a family of coding apps. Download Learn AI Agents and start your first run today. Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Privacy Policy: https://www.coddykit.com/terms/privacy-policy

Inside AI is an interactive field guide to how AI agents and large language models actually work, built for the curious skeptic. Learn from the source, not the hype. No accounts. No ads. No tracking. No internet required. Everything runs on your device. START HERE Where does AI actually live? See the data center, the many copies of a model, and how agents and tools really fit around it. WATCH AGENTS WORK See a live two-agent Writer ↔ Reviewer loop pass work back and forth until it's approved — a feedback loop you can actually watch, step by step. UNDERSTAND THE AGENT'S TOOLKIT Tool-calling, ReAct, RAG, MCP, multi-agent pipelines, A2A, computer use, prompt injection and reliability — the patterns behind every modern AI agent, each shown as a hands-on demo you can poke at. SEE INSIDE THE MODEL Tokens and the context window. Next-token prediction, one piece at a time. Attention weights across a sentence. Parameters and training with real gradient descent. Quantization, and which small models fit on your own device. Watch the ideas behind every LLM come to life. MEANING, LIMITS & CONTROL Embeddings and cosine similarity. Vector databases. Hallucination — and how grounding fixes it. Bias. Structured output. WORK WITH MODELS Prompts and chain-of-thought. Reasoning models with a thinking budget. What the model actually receives on each turn, and what it keeps when a long chat overflows. Evaluation, benchmarks, and how leaderboards get gamed. BUILD A SECOND BRAIN Turn a folder of linked markdown notes into an AI-queryable knowledge base — that's RAG, pointed at your own notes. Explore the bundled vault of 42 linked concept notes. REAL OR MOCK — ALWAYS LABELED Every demo carries a REAL or MOCK badge. REAL means genuine logic is running on your device. MOCK means it's a scripted illustration. You always know exactly what's running — no smoke, no mirrors. Most demos are scripted, and every one says so with a MOCK badge. That's why you can trust the ones marked REAL. RUNS ANYWHERE Works on any iPhone or iPad running iOS 17 or later. The demos use scripted mock agents, so no Apple Intelligence and no special hardware is required. Whether you're a developer, a student, or just AI-curious, Inside AI replaces buzzwords with understanding — one interactive concept at a time. Free to use. If it helps you, there's an optional tip jar — but nothing is ever gated.