Learn AI Agents vs CCA

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

Prepare for Anthropic's Claude Certified Architect – Foundations (CCA-F) exam with a study companion built around how the exam actually tests you: scenario-based questions about real architectural decisions. EVERY DOMAIN, EVERY TOPIC Browse all five CCA-F domains — Agentic Architecture & Orchestration, Tool Design & MCP Integration, Claude Code Configuration & Workflows, Prompt Engineering & Structured Output, and Context Management & Reliability — with concise topic summaries and curated links to official documentation, Anthropic Academy courses, and conference talks. ORIGINAL ARCHITECTURE DIAGRAMS Per-topic diagrams show how Claude, the Agent SDK, Claude Code, and MCP servers fit together — agent loops, tool-use flows, context windows, multi-agent orchestration. Zoomable and fully offline. ADAPTIVE PRACTICE QUIZ Hundreds of original, scenario-style practice questions modeled on the exam format (never real exam content). The quiz adapts: domains you miss show up more often, domains you ace fade back. Every question explains why the right answer is right — and why the tempting one is wrong — with a citation into the official docs. KNOW WHERE YOU STAND Daily and weekly progress stats plus a per-domain strength radar mapped to the official exam weightings. One tap starts a focused quiz on your weakest domain. AI TUTOR, GROUNDED IN THE DOCS Stuck on a concept? Ask the built-in AI tutor (Claude, via Amazon Bedrock). Answers are grounded in official Claude, Claude Code, and MCP documentation and cite their sources. The tutor stays on topic and will not provide real exam questions or answers. OFFLINE-FIRST, PRIVACY-FIRST All study content works offline — only the AI tutor needs a connection. No account, no sign-up, no ads, no tracking. The first domain and 10-question practice quizzes are free; a one-time Premium Unlock opens all five domains, the full question bank, longer quiz modes, and unlimited AI tutor use. Content is refreshed weekly against the latest official documentation. This app is not affiliated with, endorsed by, or sponsored by Anthropic, PBC. Claude and "Claude Certified Architect" are trademarks of Anthropic, PBC. All practice questions are original work.