Stanislas Polu is Co-Founder & CTO of Dust — the enterprise AI agent platform used by 51,000 workers at 3,000+ companies. Before Dust, he spent three years on OpenAI's research team under Ilya Sutskever, working on mathematical reasoning in language models, and prior to that was an engineer at Stripe. He brings a rare combination of frontier AI research and product-building experience to the enterprise agent space.

MCP, Agents & the $40M Bet on Multiplayer AI

James Everingham is the CEO and Co-founder of Guild.ai — the AI agent control plane for production teams. With roots at Netscape, Instagram (Head of Engineering), and Meta (Head of Dev Infra, leading a 1,000-person org), James brings rare, hard-won expertise to the challenge of operating AI agents at scale.

From Single-Player to Multi-Player: Operating AI Agents at Scale

The blog breaks down human memory into functional layers and maps them to the architectural requirements of AI systems. It shows how separating sensing, storage, context, and reasoning leads to more robust agents, and why today’s embedding‑only approaches fall short.

Human Memory As The Perfect Template For AI Memory

Thiago Cardoso is the Director of Data & AI at iFood and the architect behind iFood Pago's AI agent platform. This fintech system serves millions of restaurants across Brazil through WhatsApp and the iFood app. In this episode, he breaks down what it actually takes to ship agentic AI in production at scale.

The Control-vs-Magic Spectrum Building Agents

<p>Come to this session to hear an open discussion about the advances, challenges, and opportunities for agents when retrieving context. This session will focus on vector search applications in the area, including agent tools, embedding methods, agentic evals, agentic memory, and more.</p>

The Current State of Agentic Retrieval

<p>Join us for Session 15 of the Coding Agents Lunch &amp; Learn, our weekly community series exploring the tools, workflows, frameworks, and real-world applications shaping the future of AI coding agents.</p><p>This week, we're exploring one of the most important challenges in agent engineering: how to build AI systems that can retain knowledge, maintain context, and scale without exploding inference costs.</p><p>As agent workflows become more complex, teams are running into the limits of today's architectures. Agents repeatedly reread documents, lose important context, struggle with long-running tasks, and consume increasingly expensive amounts of tokens to maintain performance. While larger context windows have helped, they haven't solved the fundamental problem of how AI systems store, share, and build upon knowledge over time.</p><p>For this session, we're joined by <strong>Devansh, Head of AI at Iqidis and creator of Stateful Swarms</strong>, an open-source architectural paradigm designed to make agent systems more intelligent, cost-efficient, and auditable.</p><p>Instead of forcing agents to repeatedly recompute information and pack everything into ever-growing context windows, Stateful Swarms introduce a persistent, structured memory layer powered by a coordinated blackboard system. Specialized agents collaborate through a shared knowledge base, preserving important discoveries, reducing context loss, and enabling information to be reused across iterations. The result is a more scalable approach to agent engineering that improves reliability while dramatically reducing the cost of execution.</p><p>During the session, Devansh will walk through the design principles behind Stateful Swarms, why persistent memory may be the missing layer in modern agent systems, and how this approach can dramatically improve both performance and cost efficiency. He'll also share benchmark results from Harvey AI's Legal Agent Benchmark, where Stateful Swarms achieved an 83.74% pooled criteria pass rate and a 17.75% strict all-pass rate at a fraction of the cost of previously published approaches.</p><p>Through a live walkthrough and technical deep dive, we'll explore:</p><p>• Why context windows and token costs are becoming major bottlenecks for AI agents• Persistent memory architectures and structured knowledge systems• Blackboard-based coordination for multi-agent workflows• Reducing recomputation and preventing context loss across complex tasks• Building more auditable and observable agent systems• Open-source tooling and implementation details behind Stateful Swarms• Lessons learned from benchmarking and real-world agent deployments</p><p>We'll also discuss the broader shift toward stateful agents, why memory and context management have become foundational challenges in agent engineering, and how the wider Agentic AI Foundation ecosystem is helping shape the next generation of agent infrastructure.</p><p>Whether you're building coding agents, autonomous workflows, AI copilots, or next-generation agent infrastructure, this session will provide practical insights into how persistent memory and stateful architectures could reshape the future of agent engineering.</p><p><br></p>

Coding Agents Lunch & Learn Session 15: Building Stateful Agents with Open Source Frameworks

<h1><em>Paper: </em><strong><em><a href="https://arxiv.org/abs/2605.05287" rel="noopener noreferrer" target="_blank">Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use</a></em></strong></h1><h1>Retrieval-Augmented Generation and agentic AI are increasingly common in enterprise deployments, but real enterprise environments introduce challenges largely absent from academic treatments and consumer-facing APIs: multiple tenants with heterogeneous data, strict access-control requirements, regulatory compliance, and cost pressures that demand shared infrastructure. </h1><h1><br></h1><h1>This paper identifies a fundamental problem underlying existing RAG architectures in these settings. Retrieval systems rank documents by relevance, not by authorization, so a query from one tenant can surface another tenant’s confidential data simply because it scores highest. The authors formalize this relevance-authorization gap alongside related shortcomings (tool-mediated disclosure, context accumulation across turns, client-side orchestration bypass) and introduce a layered isolation architecture combining policy-aware ingestion, retrieval-time gating, and shared inference, enforced through server-side orchestration. They validate it through an open-source implementation in OGX, a vendor-neutral OpenAI-compatible Responses API, showing empirically that ABAC gating eliminates cross-tenant leakage while introducing negligible overhead.</h1><h1><br></h1><h1>The discussion will be led by Francisco Javier Arceo and Varsha Prasad Narsing, authors of the paper, joined by co-hosts David DeStefano, Rohan Prasad, and Valdimar Eggertsson, and moderated by Arthur Coleman. They will walk through the problem, the architecture, and the benchmarks, dig into the open-source framework, and open up to a live audience Q&amp;A.​​​​​​​​​​​​​​​​</h1><h1><br></h1>

Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use

<p>Real-time ML use cases like personalization and risk decisioning come with a unique set of challenges: serving fresh feature values at low latency for inference, generating temporally consistent backfills for training, and building complex chains of on-demand, batch, and streaming transformations. In this roundtable, practitioners from Intuit, CreditKarma, Depop, and OpenAI will share how they use Zipline and the OSS Chronon project to solve these challenges and deploy real-time ML use cases in production.</p>

Building Real-Time ML Systems with Zipline + Chronon

<p>Join us for Session 14 of the Coding Agents Lunch &amp; Learn, our weekly community series exploring the tools, workflows, frameworks, and real-world applications shaping the future of AI coding agents.</p><p>This week, we’re diving into what happens when agents move beyond demos and into production workflows.</p><p>We’ll kick things off with a behind-the-scenes case study from Port of Context, where CEO Patrick Kelly will unpack how their team built and evaluated a GTM agent using Goose X Code Mode. Expect a practical look into agent design, performance measurement, token usage, execution time, lessons learned, and what actually matters when evaluating autonomous systems in production. Patrick will also share how manually running this process inspired the creation of the Agent Voyager Project (AVP), an open public specification for agent observability.</p><p>We’ll also hear from Sahil Kathpal for a focused lightning talk on techniques and frameworks for running long autonomous agent sessions reliably, the kind of agent workflows that persist for 60–90 minutes and require robustness, persistence, and orchestration to succeed.</p><p>Whether you’re building coding agents, experimenting with autonomous workflows, or trying to understand what reliable agent systems look like in practice, this session is for you.</p>

Coding Agents Lunch & Learn - Session 14 From Agent Demos to Production Reality

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

Your Privacy Choices

It looks like there is no account associated with the email you provided. The event is for members only. Please complete the application to join our community first.

Thank you for your interest in joining us

Thanks for your interest in joining the event. However, your account is still pending. Once it's approved, you'll be able to register for the event. Please contact us via help@mlops.community if you need support.

Pending Approval

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.

Hey, complete your profile

It looks like there is no account associated with the email you provided. Please complete the application to join our community.

Thank you for your interest in joining MLOps Community.

Thanks for your interest in joining MLOps Community. We will review your request shortly and email you once it's approved. Meanwhile, please feel free to contact us via help@mlops.community for any questions.