An educational video on a technical topic like AI Agent, and approximately 9 minutes in duration. In a world full of 15-second entertaining videos, Everything was against this format. And yet… it worked. It’s a validation that if we make ...

Most teams do. Because realistically: You don’t have time to review every edge case Security audits are expensive and slow And if something really critical existed… surely someone would’ve caught it by now Right? Here’s the uncomfortab...

Let an AI agent work on your machine and things can go wrong fast: Accessing files it shouldn’t Leaking secrets Running destructive commands Modifying things you never intended So teams do the obvious thing: Add guardrails But Guardrails insi...

Multimodal AI has a hidden problem. Images → one tokenizer Videos → another 3D → completely different setup And it gets worse: Models that generate visuals don’t really understand them Models that understand visuals can’t generate them wel...

As companies deploy more AI agents, new problems appear: Who controls them? Who decides what data they can access? What happens when multiple agents start overlapping or conflicting? OpenAI is trying to solve this with a new platform called Fro...

AI Leadership Playbook In this episode, Jigyaasu and Saral would explore: Why is AI implementation not a weekend hackathon project? For AI implementation, do we need a product manager or a product manager? Why do some AI products become so succes...

Will we eventually design two versions of the internet? One for humans. One optimised for AI agents. AI agents read the web differently from humans. And that's the reason Cloudflare just introduced “Markdown for Agents.” When an AI agent r...

Let's build an AI Agent for email assistance using LangGraph. LangGraph is different from other frameworks like Autogen or CrewAI. Firstly, the Agent can identify whether the incoming email requires a reply or its just for the information. If ...

Can Local AI Replace the Cloud? For the last 2-3 years, the AI conversation has been dominated by one assumption: AI = massive cloud data centres. But a new study suggests something interesting: Your laptop may soon handle a large portion ...

This is one of my most watched videos on YouTube It seems people want to learn how to deploy Gen AI or Agentic AI applications on the cloud. In this video we will discusss how to deploy a Gen AI application on Azure cloud easily. It woul...

If you are running LLMs in production, you have probably seen this: Models slowing down when reasoning gets deep Fewer users per server than expected GPU bills rising fast The problem isn’t compute. It’s memory. When models “think” step by...

Do you trust AI agents to buy things on your behalf? One concern is obvious that they can make mistakes. But there are also technical issues: the current infrastructure is not built for AI Agents. Every store has its own APIs Every payment syst...

One of the biggest limitations of AI agents today is that they do not have internal memory. We have to manage their memory explicitly. But what if an AI agent could edit, update, and manage its own memory... In this video, let us see how...

Unless you’ve been completely offline lately, you have probably heard about OpenClaw. For those new to it, OpenClaw is an open-source, configurable agent framework The good thing is it runs locally and gives AI Agents real operational capab...

In this episode, Jigyaasu and Saral explore what practical safeguards actually help: delimiters, proxies, JSON validation, moderation APIs, LlamaGuard, and more > Next episode: The AI Leadership Playbook Previous episodes: 0. Basics of AI - ht...

While we mostly talk about building AI Agents and LLM applications, not many people talk about - how easy it is to hack these. In this video, I break down what prompt injection is, how it works, and most importantly, how you can protect your AI ...

There’s a common belief: For AI Agents to be truly personalised, they must know everything about you. But that’s a huge privacy risk, isn’t it? So the real question is: Can an AI Agent work on your data without actually seeing it? And ...

Let's build a fun project to make AI agents do stand-up comedy The idea is to learn "multi agent collaboration" in Autogen. The first AI Agent will crack a joke, and another agent will create a counter-joke on the punchline Let's laugh and...

OpenAI is trying something very different from traditional search ads. According to Sam Altman, “Ads on search engines make money when a search fails. If search engines gave you the best answer, there’d be no reason to buy an ad above it.” ...

Prompt Caching: Stop paying for the same prompt twice. Problem: A prompt is an integral part of any Gen AI or Agentic AI application. However, the problem occurs when the prompt becomes too large. Bigger prompts = higher cost every single cal...