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...

The problem Most AI models write text one word at a time. That keeps answers good, but makes them slow. Some models try to write everything at once to be faster. But then: they lose memory efficiency the text feels less connected compute cos...

AI Agents are powerful, but without security, they’re also dangerous. In this episode, Jigyaasu learns why AI Agent security isn’t just a technical concern, but a leadership and business imperative. From prompt injection and hallucinations to dat...

Over the years, LLMs have become great at understanding training text and images. But things fall apart when we move to new data type. For example, medical scans, or sensor data. Training an LLM on these new data types usually needs thousa...

But what if the next phase of AI doesn’t isolate us? What if it brings us together? Picture this. It’s 3:00 AM. You’re talking to an LLM about a relationship problem that strangely feels like debugging code. The model pauses and asks: “Do...

Through humour, simple analogies, and real-world examples, Jigyasu and Saral explore: What MCP Servers are and who builds them How MCP makes AI Agentic systems scalable, maintainable, and safe What is Google's A2A and more > Next episode: AI Age...

Let us build a multi-AI agent system that can customize your resume according to the "Job Description." It would also come up with the probable questions that the interviewer might ask based on the JD. All you need to do is upload your basic r...

Speech isn’t just words. It includes emotion, accent, tone, and identity – all mixed together. Traditional audio tokens try to capture everything. That makes them heavy, complex, and inefficient for language models. For example: Imagine ...

Remember when LLMs could only handle text? Well, those days are long gone. Today’s AI models can see images, watch videos, and even listen to your voice. They’ve evolved into what we now call LMMs - Large Multimodal Models. But how did we g...

Turns out, models don’t just learn facts. They can pick up traits like cheerfulness, stubbornness… even sycophancy. And fine-tuning can amplify these behaviours quietly Recently, researchers introduced “Persona vectors - numerical patterns” ...

Can AI Agents debate? Let us build a Multi AI Agent Debating System using AutoGen, where AI agents don’t just answer, they argue! Basically, Autogen provides this functionality of "Conversable Agents" and in this video, let us learn how to use th...

Employees are feeding sensitive data into Copilots and AI tools at massive scale. Most of it happens through unmanaged personal accounts, invisible copy/paste flows, and non-federated logins. Traditional DLP tools don’t even see it. A ne...