Learn AI Agents vs MicroAgent

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

Learn AI agents from the inside out. MicroAgent shows you the agent loop, tool calls, planning, memory, and multi-agent coordination — the parts every other AI app hides behind a chat box. This is not another chatbot. It is a 12-lesson visual course that breaks down how a real AI agent runtime is built, from a minimal loop with one tool to a full multi-agent team with task isolation. WHY MICROAGENT • See inside every step: messages, tool calls, plans, task state, memory, collaboration • Replayable demos: deterministic scenarios you can run again and again • Source code you can follow: each lesson maps to real Swift / Python code • 12 lessons that build on each other, not 50 random tips • Built for iPhone and iPad, fully offline-readable • One-time purchase, no subscription WHAT YOU WILL LEARN ① s01 The Agent Loop — a minimal agent with a single bash tool, end to end ② s02 Tools — read, write, edit, bash; how a tool registry actually works ③ s03 TodoWrite — make the agent plan before it acts ④ s04 Subagents — isolate work and avoid context pollution ⑤ s05 Skills — load knowledge on demand with SKILL.md ⑥ s06 Compact — keep the context window healthy with summarization ⑦ s07 Tasks — file-backed task system with dependencies ⑧ s08 Background Tasks — long-running work without blocking the loop ⑨ s09 Agent Teams — multi-agent coordination via JSONL inbox ⑩ s10 Team Protocols — shutdown, plan approval, request-response patterns ⑪ s11 Autonomous Agents — idle-loop teammates that auto-claim tasks ⑫ s12 Worktree + Task Isolation — parallel execution with shared task board WHO IT IS FOR ① iOS / Swift / full-stack developers ready to move from "use AI" to "build agents" ② AI and LLM self-learners who have read about ReAct, reflection, tool calling and want to see them run ③ Tech leads, PMs and indie builders who need a real mental model of agent architecture, not just prompt tricks HOW IT IS DIFFERENT • Visual breakdown of every step — not another chat interface. See the agent loop, planning, memory and coordination in action. • Learn from deterministic demos — run the same scenario repeatedly and understand each step. • Engineering patterns for real agent systems — not just prompting tricks. • Built-in code visualization — each lesson maps directly to runnable Swift and Python source. CORE CONCEPTS COVERED agent loop, tool calling, function calling, ReAct, planning, memory, RAG, MCP, subagents, skills, context compaction, multi-agent systems, team protocols, autonomous agents, task isolation, worktree, prompt engineering, LLM runtime, agent harness, replayable trajectory, eval, prompt injection safety. PRICING Start free with s01 to s03 plus the full course overview. Unlock full access to s04–s12 including planning, memory, background tasks, multi-agent teams, autonomous agents, and worktree isolation. No subscription, ever. LANGUAGES English · 简体中文 · 日本語 — fully localized course content and UI. Contact us: sectojoy@gmail.com Terms & Conditions: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Privacy Policy: https://zelonai.com/app/microagent/privacy-policy