mitramandal.ai ep2
What is mitramandal?
mitramandal is an AI meetup where engineers share how they've actually integrated AI into their daily development workflows. Every developer is solving applied AI differently: some are orchestrating agentic pipelines across MCPs, others are wiring real-time RAG loops into Cursor or Claude, and more are operationalizing multimodal copilots inside CI/CD. We've seen fine-tuning flywheels, retrieval sandboxes, and autonomous evaluation harnesses that ship to prod every week.
Martin Fowler nailed it recently: "we are still figuring out how to use LLMs... what I suggest is that people experiment with them... and do share the experiences."
What you'll see
agent orchestration, RAG implementations, and tool integrations
real-world case studies from production implementations
deep dives into fine-tuning strategies, evaluation methods, and model optimization
discussions on observability, guardrails, and scaling AI systems in production
Our focus
This meetup is for AI engineers, LLMOps engineers, and developers working at the intersection of applied AI and traditional software engineering. We're talking about the application of AI and how AI is being integrated into real engineering workflows.
Upcoming: episode 2 - feb 21, 2026
We're hosting the second mitramandal meetup. same vibe: builders, researchers, and tinkerers sharing real-world AI workflows. Speaker lineup will be added here soon. sign up below to get notified.
Speaker lineup:
Udayan Kanade - CEO, Oneirix Labs
Talk: Computing meaning: A structural method for processing language
Language models today produce fluent text from textual input. Any computation of meaning is effervescent and inscrutable. Could there be another approach to text processing? This talk will present a system that converts natural language text into persistent, inspectable meaning representations. Based on a new class of statistical inference algorithms on constrained graphs, this technique becomes the springboard for deeper computation that manipulates meaning to achieve specific, clear, controlled outcomes. The goal is repeatability, inspectability, precision, explainability and auditability, in tasks where language understanding, not free-form generation, is the prime requirement. The talk will present the formal foundations of the text-to-meaning approach, walk through some examples, and discuss use cases. Use cases will include knowledge base generation, data querying and analysis, and causal queries.
Dr. Venkat Chandar - Co-Founder, MoneyPlant.AI
Talk: Shipping AI Without Breaking Your Game
MCP hype is fun, but real products still need deterministic, reliable backends. In this talk, we’ll dive into how MoneyPlant.AI layered AI on top of live game systems without blowing up the in‑game economy. Expect a candid walkthrough of the architectural choices, guardrails, and failure modes we hit while keeping both player experience and business constraints intact
Chinmay Naik - Founder and CEO, One2N
Talk: Solving synthetic data generation using LLMs
We recently worked on a use case that required generating large volumes of synthetic data for a financial technology and fraud detection use case. I will cover the journey and challenges of using LLMs and Agentic tools to dynamically generate synthetic data. As an audience, you will learn use of LLMs and prompts to generate this data.
Last meetup
Our first meetup (dec 6, 2025) has concluded. thanks to everyone who joined. talks, photos, and resources are on the past events page.