Marketplaces are about to get weird.

With Pedro Chaves and Donné Stevenson: agents picking your house, negotiating deals, even talking to other agents for you.

Less browsing. Less choice. More automation.

Convenience… or giving up control?

A New Kind of Marketplace

A new paradigm is emerging for building applications that process large volumes of data, run for long periods of time, and interact with their environment. It’s called Durable Execution and is replacing traditional data pipelines with a more flexible approach.
Durable Execution makes regular code reliable and scalable.

In the past, reliability and scalability have come from restricted programming models, like SQL or MapReduce, but with Durable Execution this is no longer the case. We can now see data pipelines that include document processing workflows, deep research with LLMs, and other complex and LLM-driven agentic patterns expressed at scale with regular Python programs.

In this session, we describe Durable Execution and explain how it fits in with agents and LLMs to enable a new class of machine learning applications.

Durable Execution and Modern Distributed Systems

Chaigent combines Chainlit and Vertex AI to deliver a code-first, serverless AI agent platform that avoids costly per-seat licensing fees. It empowers developers to build highly customizable, enterprise-grade agents using a scalable pay-as-you-go architecture.

Chaigent: An affordable alternative to Gemini Enterprise on Google Cloud

mAIdAI is a lightweight personal AI assistant built with Google Chat, Cloud Run, and Vertex AI, designed to automate repetitive micro-tasks. By grounding the model with a local markdown context file, it provides highly personalized workflow assistance directly within your chat environment.

mAIdAI: Building a Personal Assistant with Google Cloud and Vertex AI

This panel discusses the real-world challenges of deploying AI agents at scale. The conversation will explore technical and operational barriers that slow production adoption, including reliability, cost, governance, and security._________________________________________________________________________The panelists will also examine how LLMOps, AIOps, and AgentOps differ from traditional MLOps, and why new approaches are required for generative and agent-based systems. _________________________________________________________________________Finally, experts will define success criteria for GenAI frameworks, with a focus on robust evaluation, observability, and continuous monitoring across development and staging environments. [<a href="https://home.mlops.community/public/events/operationalizing-ai-agents-from-experimentation-to-production-ps4tmp6g3o" rel="noopener noreferrer" target="_blank">Register now!</a>]

Operationalizing AI Agents: From Experimentation to Production

<h2>There's a specific set of problems that show up after the demo:</h2>Agent decisions that look reasonable in isolation but compound into failures across turns. Multi-agent handoffs that silently lose context. Security models that scan prompts but miss intent. Retrieval that's fast in staging and unreliable in production. Pricing models that can't survive contact with finance.Ship Agents is a two-hour virtual conference where practitioners share the failures, fixes, and production patterns they've earned the hard way - from securing agent intent across multi-turn interactions, to building data architectures that keep retrieval reliable past the demo stage, to designing APIs that actually work for tool calling and MCP integrations.Speakers from major tech companies and early-stage startups. Every talk grounded in systems that are live and serving real users. If you're past the prototype phase and deep in the "why does this keep breaking" phase, this is your event.

Ship Agents: A Virtual Conference

Coding Agents Lunch &amp; Learn - Session 6 Community Benchmarking for AI Coding Agents In this session, we’ll explore ideas for building a community-driven benchmark for AI coding agents. The goal is to test how different LLMs and agent setups perform when solving the same tasks using shared prompts and tools. We’ll discuss the concept of agent harnesses, how they enable consistent testing across frameworks, and how the community could contribute benchmark examples through a shared repository. We’ll also dive into hooks, how they work, how to use them effectively, and how they can enhance agent workflows. As part of this, we’ll open the floor for participants to share creative and practical ways they’re using hooks in their own setups. Finally, we’ll begin drafting a few example benchmark tasks together during the session and discuss how this could evolve into a collaborative LLMOps benchmark dataset for evaluating coding agents.

Coding Agents Lunch & Learn, Session 6

Coding Agents Lunch &amp; Learn, Session 5Managing a Team of Coding AgentsFeaturing Rob Ennals, creator of Broomy (<a href="https://broomy.org" rel="noopener noreferrer" target="_blank">https://broomy.org</a>)We've spent the last few sessions talking through how people are actually using coding agents, plus the frameworks, harnesses, and workflows they're building around tools like Claude Code and others.This one feels like the natural next step: what happens when you go from one agent to several running in parallel?I met Rob at a coding agents event last week and knew I had to bring him in. He built Broomy (<a href="https://broomy.org" rel="noopener noreferrer" target="_blank">https://broomy.org</a>), an open source tool for managing multiple coding agents at once, and he has a lot of real opinions on how to make parallel workflows useful without letting them turn into chaos.If you've been hearing more people talk about parallel agents, orchestration, worktrees, and multi-agent workflows and wondering what that actually looks like in practice, this is the session for you.We'll keep it conversational, practical, and useful whether you're just getting curious or already experimenting on your own.We'll be getting into things like:• What parallel coding agents actually look like in day-to-day development• Why orchestration starts to matter once you move past a single agent• What gets messy fast - overlap, merge pain, and knowing when an agent needs help• How to stay involved without hovering over every step• What Rob has learned building and using Broomy

Coding Agents Lunch & Learn, Session 5

Coding Agents - Lunch &amp; Learn (Session 4)In this one-hour virtual session, we’re bringing the focus back to coding agents, specifically how to evaluate them effectively in real-world environments. We’ll explore practical approaches to evals for coding agents, what teams are learning from production use, and how to measure performance beyond demos. We’ll also briefly recap insights from our recent Coding Agents conference and open the floor for discussion. This session is designed to be focused, practical, and interactive, ideal for engineers building or testing coding agents in production.

Coding Agents Lunch & Learn, Session 4

The MLOps Community is where machine learning practitioners come together to define and implement MLOps.
Our global community is the default hub for MLOps practitioners to meet other MLOps industry professionals, share their real-world experience and challenges, learn skills and best practices, and collaborate on projects and employment opportunities. We are the world's largest community dedicated to addressing the unique technical and operational challenges of production machine learning systems.

MLOps Community

Home

Forum

Events

Content

People

Contributors

Albums

Clubs

Chat

Channels

Tools

Help

Login to the MLOps Community community to connect with others, attend community events, and more!

Login or Sign Up for even more

To unlock all parts of the community and get the best experience, complete your profile.