Collections
All Collections
All Content
Popular topics
# LLMs
# LLM in Production
# AI
# Machine Learning
# Rungalileo.io
# LLM
# MLops
# Interview
# RAG
# Tecton.ai
# Machine learning
# Arize.com
# mckinsey.com/quantumblack
# MLOps
# Redis.io
# Zilliz.com
# Generative AI
# Humanloop.com
# Snorkel.ai
# Redis.com


Alex Miłowski & Demetrios Brinkmann · Feb 14th, 2025
There seems to be a shift from workflow languages to code - mostly annotation pythons - happening and getting us. It is a symptom of how complex workflow orchestration has gotten. Is it a dominant trend or will we cycle back to “DAG specifications”? At Stitchfix, we had our own DSL that “compiled” into airflow DAGs and at MicroByre, we used a external workflow langauge. Both had a batch task executor on K8s but at MicroByre, we had human and robot in the loop workflows.
# Workflow
# Orchestration
# DAG

Alex Miłowski · Feb 13th, 2025
This survey examines popular workflow orchestration systems, highlighting their strengths, weaknesses, and key features. It provides insights into how these tools handle automation, scalability, and reliability, helping teams choose the right solution for their needs.
# Workflow
# Survey
# Orchestration Systems


Willem Pienaar & Demetrios Brinkmann · Feb 11th, 2025
In this MLOps Community Podcast episode, Willem Pienaar, CTO of Cleric, breaks down how they built an autonomous AI SRE that helps engineering teams diagnose production issues. We explore how Cleric builds knowledge graphs for system understanding, and uses existing tools/systems during investigations. We also get into some gnarly challenges around memory, tool integration, and evaluation frameworks, and some lessons learned from deploying to engineering teams.
# AI SRE
# Knowledge Graphs
# Cleric AI

Jessica Michelle Rudd, PhD & MPH · Feb 11th, 2025
This blog post kicks off a delicious deep-dive into ETL pipelines, but instead of boring technical jargon, it's all about cooking up data! Think of it as a multi-course data feast, and Dataform is the cookbook and kitchen. The goal? To transform raw, messy data into beautifully plated, insightful dishes for your customers.
The post breaks down the process, focusing on Dataform, one of the main tools of our ETL meal. Dataform isn't just another tool; it's your digital cookbook, keeping your data transformation recipes organized and error-free. Forget messy spreadsheets – Dataform brings the order and precision of a Michelin-star kitchen to your data.
It dives into why Dataform rocks: modular recipes, version control (think "undo" button for data blunders!), built-in taste testing, and clear documentation. The post then gets hands-on, walking you through creating a Dataform project, writing a basic SQLX recipe, and testing it out before committing to a full-blown transformation. Think of it as prepping your mise en place before firing up the stove. Finally, it stresses the importance of sharing your recipe, using version control and Git.
Basically, Dataform lets you transform your raw data into gourmet insights, and this post is just the appetizer for the complete ETL feast. Stay tuned for the next courses, where they'll tackle orchestration and data governance! Get ready to cook!
# Dataform
# ETL Pipelines
# SQLX Recipe


Vinu Sankar Sadasivan & Demetrios Brinkmann · Feb 7th, 2025
Recent rapid advancements in Artificial Intelligence (AI) have made it widely applicable across various domains, from autonomous systems to multimodal content generation. However, these models remain susceptible to significant security and safety vulnerabilities. Such weaknesses can enable attackers to jailbreak systems, allowing them to perform harmful tasks or leak sensitive information. As AI becomes increasingly integrated into critical applications like autonomous robotics and healthcare, the importance of ensuring AI safety is growing. Understanding the vulnerabilities in today’s AI systems is crucial to addressing these concerns.
# AI
# Data Privacy
# Google DeepMind

Patrick Barker · Feb 6th, 2025
R1 > computer? In this talk, we will explore applying the ideas of R1 style RL fine-tuning for computer use

Sarah Wooders · Feb 6th, 2025
We are currently in the midst of a paradigm shift from stateless LLM workflows to stateful LLM agents. Today, developers are responsible for managing state (e.g. message history across sessions) and memory (e.g. with a RAG and a vector DB) themselves. Letta is an agents framework where the agents service is responsible for state and memory management, rather than client-side applications. This dramatically simplifies the experience of building stateful agentic applications, as Letta will use memory management techniques (extending the ideas from MemGPT) to automatically ensure the most relevant information is passed into the LLM context window, and also avoid context overflow errors. In this talk, we’ll cover Letta’s high-level architecture, and also explain the details of state and memory management. We’ll also go over how to use Letta to build stateful, reasoning agents with support for custom tools, secure tool environments, and personalized memory.

Médéric Hurier · Feb 5th, 2025
Poetry to Uv: A faster, simpler way to manage dependencies for MLOps projects
# MLOps
# AI
# Python
# Programming


Alex Strick van Linschoten & Demetrios Brinkmann · Jan 31st, 2025
Alex Strick van Linschoten, a machine learning engineer at ZenML, joins the MLOps Community podcast to discuss his comprehensive database of real-world LLM use cases. Drawing inspiration from Evidently AI, Alex created the database to organize fragmented information on LLM usage, covering everything from common chatbot implementations to innovative applications across sectors. They discuss the technical challenges and successes in deploying LLMs, emphasizing the importance of foundational MLOps practices. The episode concludes with a call for community contributions to further enrich the database and collective knowledge of LLM applications.
# ChatBot
# LLM
# ZenML

Bartosz Mikulski · Jan 28th, 2025
Expert strategies for improving AI agent performance through better data retrieval, query generation, automated decision-making process, and response generation. The article covers data collection, metrics, and techniques to improve the agent's performance.
# AI Agents
# AI
# RAG
# PydanticAI