Gourav Jain

If you’re an AI engineer or an AI leader looking to level up your skills in LangChain and LangGraph, this one is for you. I’m teaming up with Arvind Narayanamurthy for a beginner–intermediate, 1.5 hour hands-on workshop where you’ll learn how to move from simple prompts to real AI applications and agentic workflows. Why this matters - Most engineers know how to prompt. Few know how to orchestrate. - LangChain and LangGraph are becoming the backbone of production AI systems. - If you want to build or lead AI engineering teams, you need these mental models. What you’ll learn - Foundations of LLM orchestration and where LangChain fits - Essential building blocks: chat models, prompting patterns, structured outputs, LCEL - Tool calling with MCP adapters - RAG basics end to end - LangGraph workflows and agentic architectures - Two live labs: a micro-app and a simple agent - Quick dive into LangSmith for debugging The workshop is recorded, and everyone gets the replay. If you want practical, real-world skills to build modern AI systems, this is the one to sign up for. Grab your seats: https://lnkd.in/eW2WZdcf

328

36 Comments

It is hard to understand Fabric's long-term strategy. On one hand, it was smart to build it around PBI, the leading BI platform. On the other hand, the key to Power BI's success in dethroning Tableau was its' extremely affordable licensing. Competitive licensing is not an element that Fabric's always-on pricing model can boast of at current rates, especially when the likes of Databricks, Snowflake, and other rising platforms are around. Perhaps Microsoft will be content with Fabric always being the 3rd/4th best option?

39

32 Comments

One of the most transformative innovations powering today’s GenAI revolution is the advancement of foundation models (FMs) — large models pre-trained on Internet-scale data that demonstrate remarkable generalization across a wide range of tasks. FMs have redefined performance benchmarks in many fields including, natural language processing, computer vision, and computational biology, becoming the cornerstone of modern GenAI. Yet, progress on structured enterprise data such as tabular time series has lagged behind, where task-specific models optimized on manually extracted signals still dominate. Inspired by the success of FMs in other domains, we set out to explore whether FMs can also be built for finance and banking. After over three years of R&D, I’m excited to share that we’ve deployed our first structured-data FM into production at TD: TD AI Prism https://lnkd.in/gEAb7Scm. Trained on billions of customer events, Prism generalizes to many downstream predictive tasks, delivering higher accuracy and significantly faster time to market. Through this work, we're beginning to observe early signs of scaling laws, similar to those seen in LLMs, where more data and larger models lead to stronger generalization. As part of this effort, we also released a public FM trained on Internet tabular data, capable of making predictions on new datasets without any fine-tuning. Check it out here: https://lnkd.in/gmbWdAf7 As enterprises evolve with AI, we believe that foundation models for structured data will be a major force in redefining how predictive AI is deployed at scale, driving the next wave of innovation in enterprise applications. Layer 6 AI has multiple exciting initiatives in this space, so stay tuned for more updates!

359

15 Comments

I am a Sr. Engineer and AI helps me create 5x more speed and value at Nielsen. I see a lot of these vibecoding memes. I love them, honestly, but jokes apart, if you figure out how to use AI right, it becomes very hard not to stand out in your org. And I am not talking about shortcuts. I do not go to Claude and say “refactor this entire feature and make no mistakes.” That is a good way to ship a bug factory. Here is what actually works for me. 1. Use AI to ask better questions. When I am working on a feature, I do not just say “write a service.” I ask: ➤ What are the edge cases I am missing ➤ What happens if this dependency fails ➤ What other design options do I have Forcing the model to explain the why behind each step sharpens my own thinking. 2. Use it to map end-to-end flows For big changes, I describe the full pipeline and ask it to lay out the sequence ➤ Ingest ➤ Transform ➤ Store ➤ Serve It helps me see where I am missing validation, logs, or access checks. Then I adjust the design myself. 3. Offload documentation After I finish the implementation, I let AI draft ➤ Function level comments ➤ High level design notes ➤ Release notes for the team I still review and edit, but it turns a painful task into a 10 minute job and my future self thanks me. 4. Plug it into the ML and analytics side I also use AI models as part of other pipelines to improve accuracy and signal. My job is to understand how those models behave, how to evaluate them, and where to place them so they help rather than confuse downstream systems. The pattern in all of this is simple. AI is not the engineer. It is the multiplier. If your fundamentals are solid and you keep asking why at every step, AI will make you much faster and much more reliable. If you skip the thinking and only ask it to “do my work”, you will look productive for a few weeks and then spend months debugging what you do not understand.

469

26 Comments

15 years back, when we were building voice bots for the US market - one of the key debates used to be whether to declare or not to declare its a bot. Even if not explicitly say things like "I can help you with X,Y, Z queries and you can say things like .... " indicating a limited understanding. Even if the users did not understand what a virtual assistant is - they understood this is not a human being speaking on the other side. European regulations strictly mandate the voice agents to declare before proceeding in a conversation. India is an upcoming market but getting into the space at different stage of maturity of conversational engines - Hence there is a lot of asks to cover up the underlying bot and not by any means show up its a machine. The experience should be "human like" but that does not mean we should hide the machine behind. For an end consumer, its important to know the species they are speaking to and I now see why some of the western paradigms firmly support the declarative approach. Its just more human.

100

3 Comments