Agentic Conversations (formally mlops.community)

Tricks to Fine Tuning // MLOps Podcast #318 with Prithviraj Ammanabrolu, Research Scientist at Databricks.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

// Abstract

Prithviraj Ammanabrolu drops by to break down Tao fine-tuning—a clever way to train models without labeled data. Using reinforcement learning and synthetic data, Tao teaches models to evaluate and improve themselves. Raj explains how this works, where it shines (think small models punching above their weight), and why it could be a game-changer for efficient deployment.

// Bio

Raj is an Assistant Professor of Computer Science at the University of California, San Diego, leading the PEARLS Lab in the Department of Computer Science and Engineering (CSE). He is also a Research Scientist at Mosaic AI, Databricks, where his team is actively recruiting research scientists and engineers with expertise in reinforcement learning and distributed systems.

Previously, he was part of the Mosaic team at the Allen Institute for AI. He earned his PhD in Computer Science from the School of Interactive Computing at Georgia Tech, advised by Professor Mark Riedl in the Entertainment Intelligence Lab.

// Related Links

Website: https://www.databricks.com/

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Raj on LinkedIn: /rajammanabrolu

Timestamps:

[00:00] Raj's preferred coffee

[00:36] Takeaways

[01:02] Tao Naming Decision

[04:19] No Labels Machine Learning

[08:09] Tao and TAO breakdown

[13:20] Reward Model Fine-Tuning

[18:15] Training vs Inference Compute

[22:32] Retraining and Model Drift

[29:06] Prompt Tuning vs Fine-Tuning

[34:32] Small Model Optimization Strategies

[37:10] Small Model Potential

[43:08] Fine-tuning Model Differences

[46:02] Mistral Model Freedom

[53:46] Wrap up

Raza Habib, the CEO of the LLM Eval platform Humanloop, talks to us about how to make your AI products more accurate and reliable by shortening the feedback loop of your evals. Quickly iterating on prompts and testing what works, along with some of his favorite Dario from Anthropic AI Quotes.

// Bio

Raza is the CEO and Co-founder at Humanloop. He has a PhD in Machine Learning from UCL, was the founding engineer of Monolith AI, and has built speech systems at Google. For the last 4 years, he has led Humanloop and supported leading technology companies such as Duolingo, Vanta, and Gusto to build products with large language models. Raza was featured in the Forbes 30 Under 30 technology list in 2022, and Sifted recently named him one of the most influential Gen AI founders in Europe.

// Related Links

Websites: https://humanloop.com

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Raza on LinkedIn: /humanloop-raza

Timestamps:

[00:00] Cracking Open System Failures and How We Fix Them

[05:44] LLMs in the Wild — First Steps and Growing Pains

[08:28] Building the Backbone of Tracing and Observability

[13:02] Tuning the Dials for Peak Model Performance

[13:51] From Growing Pains to Glowing Gains in AI Systems

[17:26] Where Prompts Meet Psychology and Code

[22:40] Why Data Experts Deserve a Seat at the Table

[24:59] Humanloop and the Art of Configuration Taming

[28:23] What Actually Matters in Customer-Facing AI

[33:43] Starting Fresh with Private Models That Deliver

[34:58] How LLM Agents Are Changing the Way We Talk

[39:23] The Secret Lives of Prompts Inside Frameworks

[42:58] Streaming Showdowns — Creativity vs. Convenience

[46:26] Meet Our Auto-Tuning AI Prototype

[49:25] Building the Blueprint for Smarter AI

[51:24] Feedback Isn’t Optional — It’s Everything

Getting AI Apps Past the Demo // MLOps Podcast #319 with Vaibhav Gupta, CEO of BoundaryML.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

// Abstract

It's been two years, and we still seem to see AI disproportionately more in demos than production features. Why? And how can we apply engineering practices we've all learned in the past decades to our advantage here?

// Bio

Vaibhav is one of the creators of BAML and a YC alum. He spent 10 years in AI performance optimization at places like Google, Microsoft, and D.E. Shaw. He loves diving deep and chatting about anything related to Gen AI and Computer Vision!

// Related Links

Website: https://www.boundaryml.com/

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Vaibhav on LinkedIn: /vaigup

Timestamps:

[00:00] Vaibhav's preferred coffee

[00:38] What is BAML

[03:07] LangChain Overengineering Issues

[06:46] Verifiable English Explained

[11:45] Python AI Integration Challenges

[15:16] Strings as First-Class Code

[21:45] Platform Gap in Development

[30:06] Workflow Efficiency Tools

[33:10] Surprising BAML Insights

[40:43] BAML Cool Projects

[45:54] BAML Developer Conversations

[48:39] Wrap up

Tricks to Fine Tuning // MLOps Podcast #318 with Prithviraj Ammanabrolu, Research Scientist at Databricks.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

// Abstract

Prithviraj Ammanabrolu drops by to break down Tao fine-tuning—a clever way to train models without labeled data. Using reinforcement learning and synthetic data, Tao teaches models to evaluate and improve themselves. Raj explains how this works, where it shines (think small models punching above their weight), and why it could be a game-changer for efficient deployment.

// Bio

Raj is an Assistant Professor of Computer Science at the University of California, San Diego, leading the PEARLS Lab in the Department of Computer Science and Engineering (CSE). He is also a Research Scientist at Mosaic AI, Databricks, where his team is actively recruiting research scientists and engineers with expertise in reinforcement learning and distributed systems.

Previously, he was part of the Mosaic team at the Allen Institute for AI. He earned his PhD in Computer Science from the School of Interactive Computing at Georgia Tech, advised by Professor Mark Riedl in the Entertainment Intelligence Lab.

// Related Links

Website: https://www.databricks.com/

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Raj on LinkedIn: /rajammanabrolu

Timestamps:

[00:00] Raj's preferred coffee

[00:36] Takeaways

[01:02] Tao Naming Decision

[04:19] No Labels Machine Learning

[08:09] Tao and TAO breakdown

[13:20] Reward Model Fine-Tuning

[18:15] Training vs Inference Compute

[22:32] Retraining and Model Drift

[29:06] Prompt Tuning vs Fine-Tuning

[34:32] Small Model Optimization Strategies

[37:10] Small Model Potential

[43:08] Fine-tuning Model Differences

[46:02] Mistral Model Freedom

[53:46] Wrap up

Demetrios and Mohan Atreya break down the GPU madness behind AI — from supply headaches and sky-high prices to the rise of nimble GPU clouds trying to outsmart the giants. They cover power-hungry hardware, failed experiments, and how new cloud models are shaking things up with smarter provisioning, tokenized access, and a whole lotta hustle. It's a wild ride through the guts of AI infrastructure — fun, fast, and full of sparks!

Big thanks to the folks at Rafay for backing this episode — appreciate the support in making these conversations happen!

// Bio

Mohan is a seasoned and innovative product leader currently serving as the Chief Product Officer at Rafay Systems. He has led multi-site teams and driven product strategy at companies like Okta, Neustar, and McAfee.

// Related Links

Websites: https://rafay.co/

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Mohan on LinkedIn: /mohanatreya

Timestamps:

[00:00] AI/ML Customer Challenges

[04:21] Dependency on Microsoft for Revenue

[09:08] Challenges of Hypothesis in AI/ML

[12:17] Neo Cloud Onboarding Challenges

[15:02] Elastic GPU Cloud Automation

[19:11] Dynamic GPU Inventory Management

[20:25] Terraform Lacks Inventory Awareness

[26:42] Onboarding and End-User Experience Strategies

[29:30] Optimizing Storage for Data Efficiency

[33:38] Pizza Analogy: User Preferences

[35:18] Token-Based GPU Cloud Monetization

[39:01] Empowering Citizen Scientists with AI

[42:31] Innovative CFO Chatbot Solutions

[47:09] Cloud Services Need Spectrum

Demetrios, Sam Partee, and Rahul Parundekar unpack the chaos of AI agent tools and the evolving world of MCP (Model Context Protocol). With sharp insights and plenty of laughs, they dig into tool permissions, security quirks, agent memory, and the messy path to making agents actually useful.

// Bio

Sam Partee

Sam Partee is the CTO and Co-Founder of Arcade AI. Previously, a Principal Engineer leading the Applied AI team at Redis, Sam led the effort in creating the ecosystem around Redis as a vector database. He is a contributor to multiple OSS projects, including Langchain, DeterminedAI, LlamaInde,x, and Chapel, amongst others. While at Cray/HPE, he created the SmartSim AI framework, which is now used at national labs around the country to integrate HPC simulations like climate models with AI.

Rahul Parundekar

Rahul Parundekar is the founder of AI Hero. He graduated with a Master's in Computer Science from USC Los Angeles in 2010, and embarked on a career focused on Artificial Intelligence. From 2010-2017, he worked as a Senior Researcher at Toyota ITC, working on agent autonomy within vehicles. His journey continued as the Director of Data Science at FigureEight (later acquired by Appen), where he and his team developed an architecture supporting over 36 ML models and managing over a million predictions daily. Since 2021, he has been working on AI Hero, aiming to democratize AI access, while also consulting on LLMOps(Large Language Model Operations) and AI system scalability. Other than his full-time role as a founder, he is also passionate about community engagement, and actively organizes MLOps events in SF, and contributes educational content on RAG and LLMOps at learn.mlops.community.

// Related Links

Websites: arcade.dev // aihero.studio

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Rahul on LinkedIn: /rparundekar

Connect with Sam on LinkedIn: /sampartee

Timestamps:

[00:00] Agents & Tools, Explained (Without Melting Your Brain)

[09:51] MVP Servers: Why Everything’s on Fire (and How to Fix It)

[13:18] Can We Actually Trust the Protocol?

[18:13] KYC, But Make It AI (and Less Painful)

[25:25] Web Automation Tests: The Bugs Strike Back

[28:18] MCP Dev: What Went Wrong (and What Saved Us)

[33:53] Social Login: One Button to Rule Them All

[39:33] What Even Is an AI-Native Developer?

[42:21] Betting Big on Smarter Models (High Risk, High Reward)

[51:40] Harrison’s Bold New Tactic (With Real-Life Magic Tricks)

[55:31] Async Task Handoffs: Herding Cats, But Digitally

[1:00:37] Getting AI to Actually Help Your Workflow

[1:03:53] The Infamous Varma System Error (And How We Dodge It)

AI in M&A: Building, Buying, and the Future of Dealmaking // MLOps Podcast #315 with Kison Patel, CEO and M&A Science at DealRoom.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

// Abstract

The intersection of M&A and AI, exploring how the DealRoom team developed AI capabilities and the practical use cases of AI in dealmaking. Discuss the evolving landscape of AI-driven M&A, the factors that make AI companies attractive acquisition targets, and the key indicators of success in this space.

// Bio

Kison Patel is the Founder and CEO of DealRoom, an M&A lifecycle management platform designed for buyer-led M&A and recognized twice on the Inc. 5000 Fastest Growing Companies list. He also founded M&A Science, a global community offering courses, events, and the top-rated M&A Science podcast with over 2.25 million downloads.

Through the podcast, Kison shares actionable insights from top M&A experts, helping professionals modernize their approach to deal-making. He is also the author of *Agile M&A: Proven Techniques to Close Deals Faster and Maximize Value*, a guide to tech-enabled, adaptive M&A practices.

Kison is dedicated to disrupting traditional M&A with innovative tools and education, empowering teams to drive greater efficiency and value.

// Related Links

Website: https://dealroom.net

https://www.mascience.com

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Kison on LinkedIn: /kisonpatel

Timestamps:

[00:00] Kison's preferred coffee

[00:11] Takeaways

[00:40] Founders' Journey Slumps

[05:07] Jira for M&A

[10:57] Overcoming Idea Paralysis

[14:32] Customer-led Discovery Success

[22:20] Legal Fees in Deals

[26:24] Data Room Differentiators

[29:26] PLG vs Sales Teams

[31:43] AI Pricing Strategies

[35:15] PLG AI Cost Optimization

[40:53] Building AI Teams

[47:40] Great Companies Are Bought

[51:10] M&A Failures and Fever

[54:23] Wrap up

AI, Marketing, and Human Decision Making // MLOps Podcast #313 with Fausto Albers, AI Engineer & Community Lead at AI Builders Club.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

// Abstract

Demetrios and Fausto Albers explore how generative AI transforms creative work, decision-making, and human connection, highlighting both the promise of automation and the risks of losing critical thinking and social nuance.

// Bio

Fausto Albers is a relentless explorer of the unconventional—a techno-optimist with a foundation in sociology and behavioral economics, always connecting seemingly absurd ideas that, upon closer inspection, turn out to be the missing pieces of a bigger puzzle. He thrives in paradox: he overcomplicates the simple, oversimplifies the complex, and yet somehow lands on solutions that feel inevitable in hindsight. He believes that true innovation exists in the tension between chaos and structure—too much of either, and you’re stuck.

His career has been anything but linear. He’s owned and operated successful restaurants, served high-stakes cocktails while juggling bottles on London’s bar tops, and later traded spirits for code—designing digital waiters, recommender systems, and AI-driven accounting tools. Now, he leads the AI Builders Club Amsterdam, a fast-growing community where AI engineers, researchers, and founders push the boundaries of intelligent systems.

Ask him about RAG, and he’ll insist on specificity—because, as he puts it, discussing retrieval-augmented generation without clear definitions is as useful as declaring that “AI will have an impact on the world.” An engaging communicator, a sharp systems thinker, and a builder of both technology and communities, Fausto is here to challenge perspectives, deconstruct assumptions, and remix the future of AI.

// Related Links

Website: aibuilders.club

Moravec's paradox: https://en.wikipedia.org/wiki/Moravec%27s_paradox?utm_source=chatgpt.com

Behavior Modeling, Secondary AI Effects, Bias Reduction & Synthetic Data // Devansh Devansh // #311: https://youtu.be/jJXee5rMtHI

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Fausto on LinkedIn: /stepintoliquid

Timestamps:

[00:00] Fausto's preferred coffee

[00:26] Takeaways

[01:18] Automated Ad Creative Generation

[07:14] AI in Marketing Workflows

[13:23] MCP and System Bottlenecks

[21:45] Forward Compatibility vs Optimization

[29:57] Unlocking Workflow Speed

[33:48] AI Dependency vs Critical Thinking

[37:44] AI Realism and Paradoxes

[42:30] Outsourcing Decision-Making Risks

[46:22] Human Value in Automation

[49:02] Wrap up

MLOps with Databricks // MLOps Podcast #314 with Maria Vechtomova, MLOps Tech Lead | Founder at Ahold Delhaize | Marvelous MLOps.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

// Abstract

The world of MLOps is very complex as there is an endless amount of tools serving its purpose, and it is very hard to get your head around it. Instead of combining various tools and managing them, it may make sense to opt for a platform instead. Databricks is a leading platform for MLOps. In this discussion, I will explain why it is the case and walk you through Databricks MLOps features.

// Bio

Maria is an MLOps Tech lead with over 10 years of experience in Data and AI.

For the last 8 years, Maria has focused on MLOps and helped to establish MLOps best practices at large corporations.

Together with her colleague, she co-founded Marvelous MLOps to share knowledge on MLOps via training, social media posts, and blogs.

// Related Links

Website: marvelousmlops.io

MLOps Course discount code: MLOPS100 for the podcast listeners - https://maven.com/marvelousmlops/mlops-with-databricks?promoCode=MLOPS100

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Maria on LinkedIn: /maria-vechtomova

Timestamps:

[00:00] Maria's preferred coffee

[00:42] Takeaways

[02:48] Why Databricks for MLOps

[09:56] Platform Adoption vs Procurement Pain

[12:56] Databricks Best Practices

[16:57] Feature Store Overview

[22:00] Managed system trade-offs

[29:15] Databricks Developments and Trends

[44:31] Insider Info and Summit

[45:47] Data Ownership Pros and Cons

[48:08] Data Contracts and Challenges

[51:25] MLOps Databricks Book Guide

[52:19] Wrap up

AI, Marketing, and Human Decision Making // MLOps Podcast #313 with Fausto Albers, AI Engineer & Community Lead at AI Builders Club.

Join the Community: https://go.mlops.community/YTJoinIn Get the newsletter: https://go.mlops.community/YTNewsletter // Abstract

Demetrios and Fausto Albers explore how generative AI transforms creative work, decision-making, and human connection, highlighting both the promise of automation and the risks of losing critical thinking and social nuance.

// Bio

Fausto Albers is a relentless explorer of the unconventional—a techno-optimist with a foundation in sociology and behavioral economics, always connecting seemingly absurd ideas that, upon closer inspection, turn out to be the missing pieces of a bigger puzzle. He thrives in paradox: he overcomplicates the simple, oversimplifies the complex, and yet somehow lands on solutions that feel inevitable in hindsight. He believes that true innovation exists in the tension between chaos and structure—too much of either, and you’re stuck.

His career has been anything but linear. He’s owned and operated successful restaurants, served high-stakes cocktails while juggling bottles on London’s bar tops, and later traded spirits for code—designing digital waiters, recommender systems, and AI-driven accounting tools. Now, he leads the AI Builders Club Amsterdam, a fast-growing community where AI engineers, researchers, and founders push the boundaries of intelligent systems.

Ask him about RAG, and he’ll insist on specificity—because, as he puts it, discussing retrieval-augmented generation without clear definitions is as useful as declaring that “AI will have an impact on the world.” An engaging communicator, a sharp systems thinker, and a builder of both technology and communities, Fausto is here to challenge perspectives, deconstruct assumptions, and remix the future of AI.

// Related Links

Website: aibuilders.club

Moravec's paradox: https://en.wikipedia.org/wiki/Moravec%27s_paradox?utm_source=chatgpt.com

Behavior Modeling, Secondary AI Effects, Bias Reduction & Synthetic Data // Devansh Devansh // #311: https://youtu.be/jJXee5rMtHI~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Fausto on LinkedIn: /stepintoliquid