Get it on Google Play

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

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

Author: Demetrios June 9, 2026 Duration: 55:54
Agentic Conversations (formally mlops.community)
Technology

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 // MLOps Podcast #383 with James Everingham, CEO and Co-founder of Guild.ai


In this episode, James unpacks what actually breaks when you move from a single AI agent to a fleet of them — and what engineering leaders need to build before it's too late.


🎯 Single-Agent vs. Multi-Agent Systems — Why "single-player" AI workflows don't survive contact with production reality, and what the shift to multi-agent coordination actually demands from your infrastructure.

🔍 The Agent Control Plane — What it is, why every engineering org needs one in 2026, and how Guild.ai is building the neutral layer to deploy, govern, and share agents across any framework or model.

⚠️ Non-Determinism at Scale — Why AI agents behave like employees, not software, and why you need workforce-style governance — not just observability tooling — to manage them.

💸 Token Spend & Cost Visibility — How teams running agents in production are flying blind on cost, and what Guild shows you that your current stack doesn't.

🏗️ Lessons from Meta's DevMate — How Meta's AI coding agent went from experiment to submitting 50% of all diffs, and what that journey teaches every engineering leader about scaling agents safely.

🚦 Agent Identity & Governance — Why every agent needs an identity, what happens when they don't have one, and how agent sprawl becomes a governance crisis fast.

🔄 Sharing Agents as Infrastructure — Why Guild treats agents as shared production infrastructure rather than one-off scripts, and how that changes the economics of AI investment.

🛠️ Framework Agnosticism — Why betting on a single agent framework is a losing strategy, and how to build for a multi-model, multi-framework world from day one.

Essential viewing for engineering leaders, AI platform teams, and founders building production-grade agentic systems.


🔗 Guild.ai: https://guild.ai

🔗 James on X/Twitter: https://x.com/jevering

🔗 James on LinkedIn: https://www.linkedin.com/in/jameseveringham

🔗 Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/


⏱️ Timestamps

[00:00] Context Transfer Challenges

[00:51] Control Plane for Agents

[02:17] Effective Agent Policies

[09:23] Agent Governance Policies

[15:34] Developer Tool Adoption

[22:02] Knowledge Sharing and Open Source

[24:59] Simulated Deployments and Confidence

[29:36] Agent Workloads vs Human Workloads

[39:55] AI as a Customer

[47:59] Agent Hub vs Autonomy

[53:21] Wrap up


#AgenticAI #AIAgents #AIEngineering


Hosted by Demetrios, MLOps.community is a space for honest, meandering talks about the real work of making artificial intelligence systems actually work. This isn't about hype or theoretical papers; it's about the messy, practical, and often surprising journey of taking models from a notebook into a live environment. You'll hear from engineers and practitioners who are in the trenches, discussing the tools, the frustrations, and the occasional breakthroughs that define the day-to-day. The conversations are deliberately relaxed, covering everything from traditional machine learning pipelines to the new world of large language models and even the intangible "vibes" of team culture and process. Each episode peels back a layer on what "production" really means, whether that involves deploying a predictive service, managing an agentic system, or maintaining reliability as everything scales. Tuning into this podcast feels like grabbing a coffee with colleagues who aren't afraid to dig into the technical nitty-gritty while keeping the tone conversational and accessible. It's for anyone who builds, manages, or is just curious about the operational backbone that allows AI to deliver value, offering a grounded perspective often missing from the broader conversation.
Author: Language: en-us Episodes: 50

Official website RSS
Agentic Conversations (formally mlops.community)
Podcast Episodes
Skills over MCP on the streets of Tokyo [not-audio_url] [/not-audio_url]

Duration: 32:30
Tool descriptions tell an agent what a tool does. They don't tell it how to use five tools together, in the right order, following your conventions. That gap is where this conversation lives.Filmed at AGNTCon + MCPCon in…
Walking Tokyo Talking Agent Protocols [not-audio_url] [/not-audio_url]

Duration: 28:49
Two people, a wrong turn into a back alley, a community garden, and about thirty minutes of arguing about protocols on the streets of Tokyo.The guest is Angie Jones, VP of Developer Experience at the Agentic AI Foundatio…
Why Cost Per Million Tokens Is A Useless KPI? [not-audio_url] [/not-audio_url]

Duration: 38:49
A year ago, Palo Alto Networks built dashboards to track AI spend. Today those dashboards are useless, and the team that built them thinks that's the whole story.Recorded at FinOps X in San Diego, this conversation bring…
The Five-Layer Cake Approach to Scaling AI Without Wasting Money [not-audio_url] [/not-audio_url]

Duration: 38:55
In this episode of Agentic Conversations, we sit down with Ambud Sharma, Principal Engineer at Pinterest, responsible for general technology efficiency, fresh off delivering a controversial keynote on AI infrastructure o…
The Winchester Mystery House Problem in AI Development [not-audio_url] [/not-audio_url]

Duration: 59:41
AI models are starting to act like appliances, locked into one narrow way of working, instead of the flexible infrastructure they used to be. Drew Breunig, an AI and data strategist working with the Overture Maps Foundat…
How Predictive Analytics Stops Budget Overruns Before They Happen? [not-audio_url] [/not-audio_url]

Duration: 29:23
Every engineer at Wayfair can now see, in real time, exactly what their code costs, and that's on purpose. Brent Eubanks, FinOps Architect at Wayfair, walks us through what happens when you stop treating AI spend as a fi…
How To Delegate To An Agent Like You Would An Employee? [not-audio_url] [/not-audio_url]

Duration: 55:15
OpenAI's Codex developer experience lead sits down with a former comedian turned ML engineering lead for a conversation about what happens when computer use agents stop being a novelty and start actually running your day…
Why Your AI Bill Will Double Before It Gets Better [not-audio_url] [/not-audio_url]

Duration: 32:24
In this episode, we're joined by Josh Collier, FinOps Lead at Superhuman (formerly Grammarly), to explore what it really costs to run AI at scale and why the rules of the game changed faster than anyone expected.We discu…
MCP Goes Stateless [not-audio_url] [/not-audio_url]

Duration: 52:27
David Soria Parra is an Engineering Lead at Anthropic and one of the core maintainers of the Model Context Protocol (MCP). We explore the biggest evolution of the protocol since its launch, and why MCP is becoming the fo…
AI Hype vs. Real Value [not-audio_url] [/not-audio_url]

Duration: 42:37
Manish Dasaur is a Managing Director at PwC with over 20 years in data and AI, having helped 100+ clients navigate AI disruption and extract real business value from data, AI, and agentic AI initiatives. In this episode,…

12345»