MLOps Community
+00:00 GMT

Collections

All Collections
MLOps Reading Group
1 Item

All Content

Popular topics
# LLMs
# LLM in Production
# AI
# LLM
# Machine Learning
# Rungalileo.io
# MLops
# MLOps
# RAG
# Interview
# Machine learning
# Tecton.ai
# Arize.com
# Generative AI
# mckinsey.com/quantumblack
# AI Agents
# Redis.io
# Zilliz.com
# Humanloop.com
# Snorkel.ai
All
Devansh Devansh
Demetrios Brinkmann
Devansh Devansh & Demetrios Brinkmann · May 2nd, 2025
Behavior Modeling, Secondary AI Effects, Bias Reduction & Synthetic Data
Open-source AI researcher Devansh Devansh joins Demetrios to discuss grounded AI research, jailbreaking risks, Nvidia’s Gretel AI acquisition, and the role of synthetic data in reducing bias. They explore why deterministic systems may outperform autonomous agents and urge listeners to challenge power structures and rethink how intelligence is built into data infrastructure.
# Open source
# Jailbreaking
# Synthetic data
1:01:36
Arthur Coleman
Adam Becker
Nehil Jain
+1
Arthur Coleman, Adam Becker, Nehil Jain & 1 more speaker · May 1st, 2025
This paper introduces a novel agentic memory system that dynamically organizes knowledge—going beyond traditional methods by linking memories contextually, adapting over time, and evolving as new information is added. Inspired by the Zettelkasten method, this system allows LLM agents to build a structured yet flexible network of past experiences, improving their ability to tackle complex real-world tasks.
# Agentic Memory
# LLMs
# AI Agents
58:13
Existing BI and big data solutions depend largely on structured data, which makes up only about 20% of all available information, leaving the vast majority untapped. In this talk, we introduce GraphBI, which aims to address this challenge by combining GenAI, graph technology, and visual analytics to unlock the full potential of enterprise data. Recent technologies like RAG (Retrieval-Augmented Generation) and GraphRAG leverage GenAI for tasks such as summarization and Q&A, but they often function as black boxes, making verification challenging. In contrast, GraphBI uses GenAI for data pre-processing—converting unstructured data into a graph-based format—enabling a transparent, step-by-step analytics process that ensures reliability. We will walk through the GraphBI workflow, exploring best practices and challenges in each step of the process: managing both structured and unstructured data, data pre-processing with GenAI, iterative analytics using a BI-focused graph grammar, and final insight presentation. This approach uniquely surfaces business insights by effectively incorporating all types of data.
# GraphBI
# Gen AI
# Visual Analytics
# Kineviz
# Senzing
1:12:38
This article introduces BKFC (Build Knowledge From Chats), a Python notebook designed as an agentic workflow to tackle the common problem of extracting useful information from cluttered Google Chat histories. The author explains how manually searching through chats is inefficient. BKFC automates this by fetching recent messages via the Google Chat API, processing them, and then using Vertex AI's Gemini model for analysis. Crucially, it prompts Gemini to return structured insights (like summaries, Q&A, action items, project updates) based on a predefined Pydantic schema. The tool demonstrates a practical way to use AI (specifically Gen AI and APIs) to turn conversational data into organized, actionable knowledge, saving time and improving team awareness.
# Data Sceince
# MLOps
# Generative AI Tools
# Artificial Intelligence
# Automation
Vikram Chennai
Demetrios Brinkmann
Vikram Chennai & Demetrios Brinkmann · Apr 25th, 2025
A discussion of Agentic approaches to Data Engineering. Exploring the benefits and pitfalls of AI solutions and how to design product-grade AI agents, especially in data.
# Agentic Approaches
# Data Engineering
# Ardent AI
48:07
​Stefan French
David de la Iglesia Castro
Nathan Brake
+2
​Stefan French, David de la Iglesia Castro, Nathan Brake & 2 more speakers · Apr 24th, 2025
As AI moves beyond general-purpose LLMs, domain-specific agents are redefining automation, decision-making, and real-world applications. But what does this mean for MLOps, infrastructure, and AI adoption? How can open-source AI keep up with this shift?
# AI Agents
# MLOps
# Mozilla.ai
1:35:03
Oleksandr Stasyk
Demetrios Brinkmann
Oleksandr Stasyk & Demetrios Brinkmann · Apr 22nd, 2025
What does it mean to MLOps now? Everyone is trying to make a killing from AI, everyone wants the freshest technology to show off as part of their product. But what impact does that have on the "journey of the model". Do we still think about how an idea makes it's way to production to make money? How can we get better at it, maybe the answer lies in the ancient "non-AI" past...
# MLOps
# AI
# Model
1:06:22
Jumpstarting AI development can be tricky, but AI starter kits can provide the necessary launchpad. The article explores three main types: Frameworks offer a highly structured, guided approach suited for mature domains and consistency; Templates provide a standardized project setup with more flexibility, ideal for diverse projects with common delivery needs; and Examples offer simple, working code illustrations, best for quickly exploring new or rapidly changing areas like Generative AI. The key is choosing the right type based on your team's needs and the specific project context to build AI applications more efficiently.
# AI
# Machine Learning
# Data Sceince
# MLOps
# Generative AI Tools
This talk explores the complexities and requirements for building AI Agents for financial institutions like banks, credit unions, and fintechs. The focus will be on how to build a scalable and modern architecture capable of handling the complex demands of financial institutions.
# Ai agents
# agents in finance
Like
Comment
28:29
As complex AI agents become common, standard evaluation isn't enough. This presentation provides a structured overview of the critical field of agentic system evaluation. We will briefly explore common single and multi-agent patterns, delve into the fundamental reasons why rigorous evaluation is necessary, and outline core principles for conducting meaningful assessments. This talk covers essential principles, methods (benchmarks, simulation, human feedback), and metrics for evaluating agentic system performance, highlighting key challenges.
# Agents
1
Comment
28:21
Popular