Skip to the good part of every MLOps Community session.
Talks, podcasts and meetups since 2020, with summaries and timestamps to help you find the part you need. 928 talks and counting.
Search talks and packs by topic, or describe the problem you're working on.
Reading groupPrompt Injection as Role Confusion: Rethinking Agent SecurityThe paper "Prompt Injection as Role Confusion: Rethinking Agent Security" argues that models can confuse the source of text with the role that text appears to imitate. Lucas explains attacks that append fabricated reasoning to a harmful request or place...
Agentic DX: Bringing IDP into your IDEAdnan Vahora describes how Motorola Solutions tried to increase adoption of an Internal Developer Platform used by more than 4,000 monthly active users. The platform had only 22% adoption, so the team moved its agent experience into the IDE through...
Before the Agent Calls: Source-level Findings from 100 MCP ServersAkash Sathish examines MCP security before an agent makes its first tool call. He describes how malicious instructions can enter through prompts, connected MCP servers, or retrieved documents, then shows how an LLM can steer an MCP server toward dangerous...
The model works when you run the notebook.
Two models use a feature with the same name, but different calculations.
The endpoint is healthy, yet recommendations are empty or one customer group receives worse predictions.
You built the platform, but data scientists still run their own scripts and ask colleagues how to deploy.
What data can a model use, and what should it be allowed to do? Privacy and governance discussions meet newer problems with prompt injection and agent permissions.
What can an agent do on its own, and which tools should it get? Once it starts acting, someone needs a way to find out when it goes wrong.
How do you tell whether a model still works once people depend on it? Speakers look for answers in drift statistics, production traces and evals, including the disputed practice of asking one model to judge another.
Who builds the platform data scientists use, and how big should that team be? Then comes the recurring discovery that building it does not make anyone use it.
138K views2System Design for Recommendations and Search
95K views3Does AgenticRAG Really Work?
39K views4Exploring the Latency/Throughput & Cost Space for LLM Inference
29K views5Stop Shipping on Vibes: How to Build Real Evals for Coding Agents
26K views
Every talk and pack page also exists as plain Markdown: add .md to any talk or pack URL.