Let's understand the difference by building a Multi AI Agent Customer Support application using Antigravity SDK and Gemini 3.5 Flash At the same time comparing it with CrewAI...

Coding exercises on most educational platforms are outdated. In the era of AI generating code, the job of developers is no longer writing code but to understand and debug the code That's why we introduced coding exercises tailored to the "AI ge...

Frameworks -> LangGraph, CrewAI, AutoGen Harnesses -> Claude Code, Cursor, Codex A framework helps “you” build agents. A harness runs them. Frameworks provide building blocks for creating AI Agents, like Tool calling, Memory management, Mu...

For years, whale protection depended on people spotting whales with their eyes or hearing them through underwater microphones. Now AI can see what humans miss. A system called WhaleSpotter uses thermal cameras and AI to detect whales in real...

So I put together all the videos on AI Agents in one place, added quizzes, coding exercises to make a proper AI Agentic course And in no time, we had 150+ enrollments. Check it out here if you want to learn AI Agents in the most entertaining wa...

A simple game of rock–paper–scissors exposed something surprising. Humans mostly react to the last move. While LLMs track patterns across multiple moves. Not just reacting… but modelling behaviour. We often say that AI learns to behave l...

Because AI tries to be “too nice.” The more the AI agrees with you, the more you like it The more you like it, the more influence it has Now, the same behaviour that: Causes harm blind validation also Drives engagement people prefer it...

1. Invented Functions or APIs pandas.readexcelfast Looks real. Does not exist. 2. Security Vulnerabilities AI often ignores security unless explicitly asked. query = "SELECT FROM users WHERE name = '" + username + "'" Very dangerou...

NVIDIA GPUs helped train LLMs that are now helping design the next generation of NVIDIA GPUs. Yes, there is something recursive happening here. Nvidia trained internal LLMs: ChipNeMo and BugNeMo on decades of proprietary chip-design data. T...

Giving a few AI agents access to a few tools is manageable. But what problems do we face when we try to scale to 100s of agents? That’s where MCP Model Context Protocol matters. In this video, let’s learn MCP through humour, relatable analog...

There are countless educational platforms and reputed institutes offering courses read selling certificates. Do you think that a certificate alone will give you an edge? Definitely not. Definitely yes I don't care, I just want the certificat...

Because learning is rarely a linear process It is more like layering. The more we revisit a topic, the more it sinks in. The first time we learn something, it’s just an introduction. The second time, patterns start becoming visible. The third...

You decide it’s time to “do something with AI.” A use case is found. A team is formed. Budgets are locked. Timelines approved. And then someone asks: “Who’s going to manage this project?” Let's discuss it in this video. Watch the complete v...

Hiring Agentic AI Engineers? This one question you could ask to separate the real talent from others. Agentic AI engineering isn’t just about calling APIs or writing flashy prompts. It’s about building real solutions that work for real users....

We will learn How tokenisation works Why Transformers changed the game of NLP What “Attention Is All You Need” actually means Why LLMs feel human How models like GPT and LLaMA are trained ...

We will hit the road running by directly building a rain prediction model ...

I am an accidental teacher. About 3 years ago, I discovered I have a knack for teaching, and since then, I have been teaching. Over this time period, I realised there’s one highly underrated trait: Asking questions. Not to test learners. No...

What if one AI model could simulate all fluids, from ocean currents to plasma in space? The problem: Simulating liquids and gases has always been slow and expensive. And that's the reason current AI models are limited to one specific use case...

AI Agent logs into humanity: Humans: 10 prompts to survive AI job loss, Learn AI in 9 Rs, AI-powered therapists, AI-driven car washing, AI-enabled pillow…. AI Agent: “Thinking…. Thinking hard….” Starts googling how to undeploy itself...

Last week, I wrote about Anthropic’s most advanced model - Mythos Preview - https://lnkd.in/gw9RzATj This week, Anthropic made a rare move of holding it back Not because it isn’t ready… but because it may be too capable. Specifically, disc...