
The video is a live demo by Kesh Nayak of Sarvam AI, India’s full‑stack sovereign AI platform, illustrating its conversational‑agent capabilities for an e‑commerce support scenario. The agent, presented as a Quick Cart customer‑service rep, smoothly manages order‑status queries, refund requests, and escalation, while maintaining a polite, empathetic tone. It asks for order IDs, provides real‑time delivery updates, offers coupons, and promises to forward feedback to the logistics team. Key excerpts include the agent’s response, “I completely understand your frustration, Kish, and I sincerely apologize,” and its escalation promise: “I’m escalating this immediately to see if we can expedite the delivery.” The demo also references the Indian AI Impact Summit 2026, positioning Sarvam as a home‑grown alternative to foreign LLMs. By delivering a near‑human interaction without apparent latency, Sarvam AI demonstrates that Indian firms can build competitive, privacy‑focused conversational tools, potentially reducing reliance on external providers and accelerating digital transformation in retail and other sectors.

The live Day 3 session walked participants through the practical steps of building production‑ready AI agents. After a brief recap of earlier theory, the instructor opened a shared GitHub repository, demonstrated how to clone the project, and outlined the folder hierarchy...

The video provides a concise introduction to large language models (LLMs), explaining that they are deep‑learning algorithms trained on petabytes of text data. It emphasizes that the term “large” refers both to the massive training corpora and to the billions‑to‑trillions...

The video introduces a hands‑on crash course that walks developers through building a full‑stack application with Next.js and Supabase, starting from an empty repository and ending with a live deployment on Vercel. It outlines a step‑by‑step workflow that begins with...

The video introduces an end‑to‑end LLMOps demonstration called the Azure Multimodal Compliance Orchestration Engine, built to showcase how a production‑grade AI pipeline can be assembled from scratch using Azure managed services. The presenter walks through the project’s architecture, highlighting components...

Oracle unveiled its next‑generation AI‑native offering, the Oracle Database 26AI, emphasizing built‑in vector search capabilities that blend traditional SQL with high‑dimensional similarity queries. The video walks viewers through provisioning a free autonomous AI database instance, selecting workload types, configuring network...

Krishna announced a new product – an end‑to‑end, industry‑grade AI project library with deployment on AWS, GCP and Azure, sold as a yearly subscription. The catalog currently contains 47 projects spanning agentic AI, computer vision, data analytics, deep learning, generative AI,...

The video introduces deep agents, a next‑generation AI architecture that moves beyond the simple request‑response loop of traditional, or "shallow," agents. Krish Naik explains that shallow agents rely on a single LLM decision to either generate an answer or call...

The video spotlights a persistent pain point for AI product teams: designing efficient PostgreSQL schemas from scratch. Krish Nayak explains that generic large‑language models often miss optimal data types, table relationships, and indexing strategies, leading to sub‑par implementations. To address...

The video serves as a crash‑course on the newly released LangChain v1, walking viewers through the framework’s most significant updates and demonstrating how to build autonomous agents with the latest features. Krush Nair frames the tutorial as a one‑shot guide for...