
AI Agents 101 is a free, offline iOS app that teaches how large language models and AI agents work through interactive, labeled demos that run directly on your device.
Every demo is marked either REAL (actual logic running) or MOCK (scripted), removing the fog from AI marketing and letting learners see tokens, attention, RAG, and other core concepts in action without internet, accounts, or ads.
What happened
A developer has released AI Agents 101, a free interactive iOS app that runs entirely offline and teaches how AI agents and language models work through hands-on demos. Every demo is labeled either REAL (genuine logic running on device) or MOCK (scripted illustration), so users know exactly what they're seeing.
Why it matters
The app addresses skepticism about AI hype by making the underlying concepts tangible and transparent — tokens, attention weights, tool-calling, RAG, embeddings, hallucination — without requiring accounts, ads, internet, or special hardware. For developers, students, or anyone curious about how AI actually works rather than marketing claims, it offers concrete understanding without gatekeeping.
What to watch
The app requires iOS 17.0 or later and works on iPhone, iPad, Apple Vision, and Mac (M1 or later). It includes a bundled vault of 33 linked concept notes that users can turn into an AI-queryable knowledge base using their own markdown files. The app is free with an optional tip jar; nothing is gated.
Ask the AI about this article →
AI Agents 101 addresses a real gap in how AI concepts are commonly explained. Marketing-driven narratives often obscure what models and agents actually do, leaving learners to puzzle out hype from reality. This app takes the opposite approach: every interactive demonstration explicitly flags whether it's running actual logic on the device (REAL) or showing a scripted walkthrough (MOCK). That transparency is its core strength.
The app's design choices reinforce its pedagogical mission. By running entirely offline, it removes dependencies on cloud services and avoids data collection — the developer states no user data is gathered. The choice to use scripted demos rather than requiring Apple Intelligence or special hardware lowers the barrier to understanding. The inclusion of a bundled concept vault (33 linked markdown notes) and the ability to turn personal notes into a queryable knowledge base grounds abstract AI concepts in learner-controlled, concrete material.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Israeli startup DataAgent Ltd
SK Hynix presented a custom HBM concept at SEMICON Taiwan 2026, where compute functions are placed in the base…

Nvidia reported earnings that were both remarkable and boring, reflecting its focus on avoiding a consolidated…

Anthropic has agreed to a $35bn cloud-computing contract with Lambda, a Nvidia-backed cloud provider

The Supreme Court of Japan has included about ¥60 million in its fiscal 2027 budget request for AI-related exp…

The Consumer Affairs Agency said Tuesday it will use generative AI to analyze about 900,000 annual consultatio…
