AI with Aish

12 hours away! Last chance to register for the AI Evals workshop, happening tomorrow morning 8am PT Register now: https://topmate.io/the_gen_academy/1887727

Heyy folks! Reminder that the AI Evaluations workshop is happening this Sunday- 8am PT It's for everyone who is an AI professional whether you are an engineer, PM, product lead, GTM lead, or product marketer. It is super important that you understand how models and GenAI products are evaluated and what "good" really means. https://topmate.io/the_gen_academy/1887727

Last chance to register ⏰ Join me and Arvind Narayanamurthy tomorrow at 8am PT, for a 1.5-hour live LangChain & LangGraph workshop on orchestrating AI applications and agentic workflows: https://topmate.io/the_gen_academy/1814529 This is a beginner–intermediate, hands-on session where you’ll move from prompt-based scripts to structured pipelines and agentic systems, and build a portfolio-ready project you can showcase. The session will be recorded, and all participants will receive the recording. Basic Python required.

If you’re an aspiring AI engineer, here’s the shift you can’t afford to miss: We’ve officially moved from Prompt Engineering → Context Engineering. Prompt engineering was about crafting better inputs. Context engineering is about designing smarter systems. As models get larger and more capable, the real differentiator isn’t how well you can write a prompt, it’s how well you can manage, structure, and serve context. In our next hands-on AI workshop, we’ll dive deep into: - What “context” really means in LLM systems and why it determines how powerful your model can become - Techniques like Summarization, Query Rewriting, Context Offloading, Isolation, and Memory - How to balance accuracy, cost, and reliability in production use cases - A live demo bringing these methods together in real time 📅 November 8 ⏱️ 1.5 hours 🎙️ With Arvind Narayanamurthy & me 🎟️ Save your spot: https://topmate.io/aishwarya_srinivasan/1774817

New Post on how I built my Content Insight Agent: https://www.linkedin.com/posts/aishwarya-srinivasan_when-youre-juggling-a-95-and-creating-content-activity-7378820959581077504-SDzA

🚨 Final call - RAG: Towards Mastery workshop is happening in less than 12 hours! Tomorrow at 8 a.m. PST, we’re going live for a 3-hour deep dive on advanced RAG pipelines. Registrations close tonight at 12 a.m. PST. Join 300 AI engineers, LLM builders, and researchers learning how to: → Use RAG as a memory layer → Engineer context for performance → Choose the right architectures → Build multimodal & graph RAG apps (hands-on) Don’t miss it, and secure your spot before midnight:https://topmate.io/aishwarya_srinivasan/1682863

Happening this Saturday!! I’m also co-hosting a hands-on session on Saturday: RAG – Towards Mastery with Arvind We’ll go deep into: - RAG as a memory layer for LLMs - Advanced context engineering strategies - Architectural trade-offs for scaling RAG - Two live builds: multimodal RAG and Graph RAG It’s a 3-hour deep dive for AI engineers and builders. Details & registration: https://topmate.io/aishwarya_srinivasan/1682863

Reminder- we are going live with the RAG workshop tomorrow morning. Last few hours to book your slot. Registration closing at 11pm PT https://topmate.io/aishwarya_srinivasan/1596941

I'll be speaking at the Google DeepMind office this Friday. If you're in bay- feel free to register:) https://www.linkedin.com/posts/aishwarya-srinivasan_excited-to-be-back-at-google-ill-be-speaking-activity-7353944692746596353-5pPG

We are back with RAG workshop 🔥 After the incredible response to our MCP, Agentic AI, and Vibe Coding sessions, Arvind Narayanamurthy and I are kicking off a brand-new workshop series on one of the most requested and practical topics- Retrieval-Augmented Generation (RAG). The first installment of this series is specifically designed for beginner to intermediate learners, offering a comprehensive introduction to the fundamental concepts of RAG. 🔍 Whether you're building production-grade AI apps or just starting to explore how LLMs can go beyond their training data - RAG is a must-have skill. This isn’t your usual high-level webinar. We’ll take you through real implementation, live guidance, and building from scratch You’ll: ✅ Learn how RAG improves LLM performance with fresh, contextual data ✅ Understand vector DBs, indexing, and retrieval techniques ✅ Get Hands-on: Build and deploy a working RAG pipeline using LangChain + Pinecone ✅ See no-code and low-code demos for faster experimentation ✅ Explore real-world use cases and performance tips 📅 Reserve your seat, roll up your sleeves, and let's get building. 👉 https://topmate.io/aishwarya_srinivasan/1596941

Tomorrow( May 31, 8am PT), Arvind Narayanamurthy and I are hosting a 3-hour live webinar: → Deep dive into how MCP works under the hood → Two hands-on projects: build agents using real tools → Best practices for schema design, memory planning, and fallback logic If you’re serious about building autonomous, tool-augmented systems - this is the session you don’t want to miss: https://topmate.io/aishwarya_srinivasan/1540389

Function calling makes your system complexity O(n × m). MCP reduces it to O(n + m). ‼️With traditional function calling, every model must be hardcoded to each tool - n models × m tools = exponential integration overhead. ✅ With MCP, tools and models speak a shared protocol - decoupling logic so you can swap either side independently. Function calling isn’t enough anymore! As we shift from prompt-based interfaces to autonomous agents, we need something more powerful, flexible, and standardized. That’s where MCP (Model Context Protocol) comes in 👇 ➡️ Unlike traditional function calling (think OpenAI-style JSON schemas), MCP is an open protocol that lets LLMs interact with tools, memory, and environments through structured, multi-step reasoning. ➡️ It’s the difference between asking a chatbot a question vs. giving an AI system initiative - to plan, decide, and act across workflows. 🧠 What is MCP? MCP defines how an LLM should: → Call tools and APIs using JSON-defined schemas → Access and update short- or long-term memory → Understand its environment (OS, browser, clipboard, etc.) → Handle failure with structured retries or fallbacks ⚒️ With MCP, AI agents can: → Chain multiple tools declaratively (not manually scripted) → Plan first, act second - enabling multi-step workflows → Switch between memory types - scratchpad, vector, or persistent → Execute across contexts, not just in a single prompt-response loop It's model-agnostic and extensible - works with LLaMA, Claude, Qwen, DeepSeek, Mistral, etc. 🔥 Why it matters? → Building agents that operate in the real world means managing: → Latency and tool invocation overhead → State and context switching → Failures, timeouts, fallbacks, and memory recall → MCP is the emerging standard that gives you a contract between models and the external world, an API for cognition. If you’re building any kind of autonomous agent, MCP will become your orchestration backbone. 🎓 Learn to Build With MCP On May 31, Arvind Narayanamurthy and I are hosting a 3-hour live webinar: → Deep dive into how MCP works under the hood → Two hands-on projects: build agents using real tools → Best practices for schema design, memory planning, and fallback logic If you’re serious about building autonomous, tool-augmented systems - this is the session you don’t want to miss: https://topmate.io/aishwarya_srinivasan/1540389

https://www.linkedin.com/posts/aishwarya-srinivasan_ai-robotics-learning-activity-7328944298580692992-tQnB?utm_source=share&utm_medium=member_ios&rcm=ACoAABcIe6wBDNmiG5woZcoYzaD2wy6FIbMNQNU

After hosting 330 attendees in our first hands-on workshop, Arvind and I are back- this time diving deep into MCP and Agentic AI, on 31st May! If you’ve been trying to wrap your head around how to actually build with Model Context Protocol or deploy intelligent AI agents in production- this session is for you. This is not another theory-heavy webinar. It’s a live, practical workshop where we’ll build, demo, and explain: 🧠 What MCP really is and how it differs from function calling ⚙️ How to build and connect MCP servers and clients from scratch 🕸️ What makes an AI system “agentic” and how to structure one 🧪 Live coding using tools like LangGraph, LangChain, and more! 💡 Real-world agent use cases across verticals like marketing and coding 💻 What you’ll walk away with: ✔️ A solid understanding of MCP and Agentic design ✔️ Confidence to integrate MCP in your AI stacks ✔️ A working MCP-powered AI agent built during the workshop

https://topmate.io/aishwarya_srinivasan/1540389 Happening on 31st May- 8am PT

If your goals are to become an AI Product manager, this is for you: https://www.linkedin.com/posts/aishwarya-srinivasan_in-2025-every-product-decision-is-now-an-activity-7326636459577286659-ZmHZ

Checkout my Llama-4 Maverick experiment: https://www.linkedin.com/posts/aishwarya-srinivasan_meta-sponsored-activity-7322798574797225984-oXJq

hello folks Registration closes tomorrow 12pm PT(Friday) If you want to code faster, smarter, and with the help of AI, then read this 👇 If you’re a student trying to build like a pro, or a founder with more ideas than time, or a software engineer ready to level up your productivity- This 3-hour AI-assisted coding workshop is built just for you! Super excited to be partnering with Replit and teaming up with Arvind Narayanamurthy to host "Vibe Coding Workshop" Here’s what we’ll walk you through (hands-on): → Rapid prototyping with AI to validate ideas → Advanced coding strategies to shorten your learning curve → Smart AI integrations to boost your workflow productivity You just need basic programming skills (Python preferred) and a laptop. We’ll handle the rest. Date: April 26 Time: 7 PM PST Link to join: https://topmate.io/aishwarya_srinivasan/1480451

I am hosting a special 3-hour workshop with my friend Arvind Narayanamurthy on April 26th at 7 PM PST, diving into the world of AI-assisted coding! If you’re a a student aiming to code like a pro, tech entrepreneur with big ideas, or a software developer looking to significantly boost your productivity, this workshop is designed specifically for you. We’ll guide you hands-on through: →Rapid prototyping techniques using AI to quickly validate your tech ideas. → Advanced coding strategies to accelerate your learning curve. → Effective integration of AI tools into your coding workflow for maximum productivity. All you need is basic programming knowledge (ideally Python) and your laptop—we’ll handle the rest and make sure you’re all set up ahead of time. https://topmate.io/aishwarya_srinivasan/1480451

If you are in bay area, and want to make the most of networking and meeting amazing minds, you got to be following SFIRL. I have attended several of their events (at times 3 in the same day), and the curated list is great! It filters the best tech/ startup/ AI events in bay area: https://sfirl.beehiiv.com/subscribe?ref=HfDruBtjrT&_bhlid=7fecfad9eb7fd8bcdb529e945e11346b5897acdc