Guthrie Cooper (Senior Group Product Manager, AI & Robotics) and Nidhi Sharma (Global Head of Engineering AI & Incubation) from Just Eat Takeaway.com join the MLOps.community to pull back the curtain on how one of Europe's largest food delivery platforms is running an internal innovation engine. From autonomous delivery robots to agentic AI voice assistants, they share what it actually takes to build like a startup inside a 40,000-person company.

Inside Just Eat's AI Lab: Voice Agents & Agentic Commerce

Once agents can use tools, ordinary business content can become part of the control surface. Documents, tickets, webpages, records, and retrieval results may contain instructions the agent should read as data, not follow as commands. Based on a conversation with Pramod Krishnan from PwC, this piece looks at indirect prompt injection, tool permissions, trace review, and why production agents need a clear separation between content and action.

An Agent Shouldn't Trust Everything it Reads

Pramod Krishnan is a Managing Director - AI Managed Services at PwC, specializing in enterprise AI transformation — helping large organizations move from AI experimentation to production operating models. In this episode with Demetrios, Pramod breaks down exactly what the OpenClaw wave means for enterprises, and the control frameworks PwC uses before a single agent touches production.

Autonomous Agents at Work: From OpenClaw Hype to Enterprise Reality

Production agent ROI is usually calculated too narrowly. The model bill is visible, but the bigger cost often sits in reviewer time, eval maintenance, retrieval, storage, platform work, and process change. Based on a conversation with Rani Radhakrishnan from PwC, this piece argues that the real comparison is not headcount saved minus inference spend, but the full cost of the old process against the full cost of the agent-assisted one.

Agent ROI in Production is Mostly Reviewer Time

As AI systems evolve into more autonomous, agent-driven architectures, the way we design platforms, tools, and infrastructure is rapidly changing. In this session with BuzzHPC, we’ll explore the shifting boundary between platforms and tools, what developers expect platform providers to handle versus what they want to control and build themselves. We’ll unpack what modern agentic stacks look like today, how teams are structuring them in production, and where these architectures are heading as systems become more complex and distributed. A key focus will also be on agent interoperability, how different agents communicate, coordinate, and operate within shared environments. Finally, we’ll share insights and lessons from a recent AI hackathon delivered in partnership with Bell, Buzz, Mila, and KHP, highlighting how these concepts are being tested and applied by builders in real-world scenarios.

Architecting Modern AI Systems: Platforms, Agents, and Integration

This week’s Coding Agents Lunch &amp; Learn will feature a deep dive into collaborative agent workflows, orchestration, and AI-native development environments. Agor creator Max will demo Agor, a collaborative workspace designed to coordinate coding agents across branches, sessions, environments, reviews, and team workflows. The session will explore how agent work, often invisible and fragmented, can become visible, collaborative, and easier to manage through shared workspaces. We’ll walk through practical workflows including spawning agents, tracking progress, forking sessions, comparing approaches, reviewing outputs, and coordinating work across teams in a way that keeps humans meaningfully in the loop. Beyond the demo, Max will share lessons from real-world experimentation around agent orchestration, runtime environments, context and memory management, automation workflows, and how teams are thinking about coding agents beyond traditional software development. As always, this will be an interactive, discussion-driven session designed for engineers, founders, researchers, and practitioners exploring the future of coding agents and AI-native workflows.Featuring Special Guest Max ( The Creator of Agor ) - showcasing <a href="https://agor.live/?utm_source" rel="noopener noreferrer" target="_blank">Agor</a> and practical lessons in coding agent orchestration.

Coding Agents Lunch & Learn Session 13 — Collaborative Coding Agents, Workflows & Community Show-and

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.

Building Real-Time ML Systems with Zipline + Chronon

<h1>Paper: <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></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> </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> </h1><h1>The discussion will be led by Francisco Javier Arceo, co-author 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> </h1>

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

In Session 12 of Coding Agents Lunch &amp; Learn, we’ll explore practical workflows and infrastructure patterns powering modern AI coding agents. This session will feature a deep dive into Hermes, sandboxed execution environments, and the tooling that enables safer and more scalable agent-driven development. We’ll also open up the discussion around advanced developer workflows, including skill evaluations, Git worktrees, multi-agent experimentation, isolated environments, and techniques teams are using to manage increasingly autonomous coding systems in production. As always, this will be a collaborative and interactive session focused on real-world experimentation, practical lessons, and open discussion between developers building with AI agents every day. Topics include: <ol><li data-list="bullet">Hermes and agent orchestration workflows</li><li data-list="bullet">Sandboxed execution environments for coding agents</li><li data-list="bullet">Skill evaluations and agent benchmarking</li><li data-list="bullet">Git worktrees and parallel development workflows</li><li data-list="bullet">Multi-agent experimentation and tooling</li><li data-list="bullet">Open discussion and community Q&amp;A</li></ol> Whether you’re actively building agentic developer tools or exploring advanced AI-assisted engineering workflows, this session is designed to share practical insights you can immediately apply to your own projects.

Coding Agents Lunch & Learn – Session 12: Hermes, Sandboxes & Advanced Agent Workflows

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.