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 optimization at scale.

Ambud walks us through his Five Layer Cake framework - a structured approach to driving efficiency across every level of the AI stack, from silicon and hardware procurement to model selection, inference engine design, and governance. We explore how decisions compound across layers to unlock real business growth, and how the wrong choices can lock you into expensive commitments for years.

We stress test the framework against two very different business models: what the stack looks like if you are building the next Cursor, and how it changes entirely if you are building the next YouTube. Along the way we cover hardware immutability, inference engine warm-up costs, GPU occupancy, context switching, quantization trade-offs, model routing, and why experimentation discipline is the only thing that keeps AI infrastructure costs from getting out of control.

We also look at how this framework holds up in the emerging agent era, what changes when agent-to-agent communication becomes the norm, and why agent traffic just passed bot traffic on Cloudflare. The conversation closes on a deceptively simple takeaway: there is no silver bullet, and experimentation at every layer always comes first.

Pinterest: https://about.pinterest.com/

Alex Salkever: https://www.linkedin.com/in/alexsalkever

Ambud Sharma: https://www.linkedin.com/in/ambud

Timestamps:

[0:00] Introduction and the controversial keynote

[2:09] The five-layer cake explained

[4:30] Why hardware decisions are irreversible

[6:47] Two business models: building Cursor vs YouTube

[10:42] Applying the five layers to a YouTube-style company

[14:23] Experimentation as the core efficiency method

[17:09] Inference stack: context switching and warm-up costs

[20:07] Model layer: why changing models breaks everything

[24:10] When you should not use an LLM at all

[26:41] Governance and routing: right model for the right task

[29:20] Horror stories of unchecked token spend

[31:37] Experimentation discipline without stifling innovation

[34:35] How the five layers change in the agent era

[36:05] Agent-to-agent communication and governance complexity

[38:27] Core takeaway: experimentation first at every layer

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 Foundation, joins us to explain why, and what it means for anyone building something that doesn't look like Claude Code.

Drew walks through his "Winchester Mystery House" idea: what happens once code gets so cheap to write that the only real bottleneck left is feedback. From there we dig into DSPy: signatures, the GEPA optimizer, and the brand-new Flex optimizer, which rewrites your code instead of just your prompt, complete with a real before-and-after on cost and accuracy. We also get into why so many AI-built apps and websites end up looking identical, the actual difference between an agent and a workflow, what Drew learned a year after shipping a code library with no code in it, and why he thinks the most valuable thing you can do right now is close the laptop and go talk to people.

CMPND: https://www.cmpnd.ai

Drew Breunig: https://www.linkedin.com/in/drewbreunig/

Demetrios: https://www.linkedin.com/in/dpbrinkm

Timestamps:

[0:00] Cold open: when Claude Code tries to call itself

[1:19] Biggest AI news: labs trading diversity for reliability

[2:35] How harnesses get trained into models over time

[5:41] The problem: your harness starts fighting the model

[9:13] When do you need your own harness?

[10:02] The Winchester Mystery House warning

[16:13] The blank page problem: why everything looks the same

[20:50] Infrastructure vs appliances: the thesis lands

[22:40] Current tool loadout: GLM, Kimi, Claude Code, Pi

[27:04] The Raspberry Pi personal agent running on Slack

[31:00] Crystallizing tasks: when to replace AI with pure code

[33:10] DSPy explained: separating what from how

[35:23] How prompt optimizers actually work

[39:31] DSPy pre-dates ChatGPT: model-agnostic programs

[44:00] Why you still need to ship the code, not just the spec

[50:00] Don't plan more than a month ahead anymore

[54:00] Coaching agents all day feels productive — it isn't

[57:58] The dopamine of building with agents vs. why you still need human feedback

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 finance problem and start treating it as an engineering one.The story that sticks with you: a team was burning $400k a month on an LLM-driven workflow, until they flipped the whole thing on its head - hard-coded logic doing the heavy lifting, AI called in only when it's actually needed. New spend: $80k. It's the kind of move that only makes sense once you realize more agentic autonomy isn't always the win it's sold as.From there we get into the machinery Wayfair has built to make cost ownership feel less like a punishment and more like a superpower: guardrails baked straight into coding copilots, predictive alerts that catch a team blowing its budget before the month even ends, a "spend captain" system that pushes budget decisions down to the people closest to the work, and a genuinely strange new question every tech leader is starting to ask: if you were staffing a company with a team of AI agents instead of people, what would that org chart even look like?Wayfair: https://www.wayfair.comBrent Eubanks: https://www.linkedin.com/in/brenteubanksDemetrios: https://www.linkedin.com/in/dpbrinkmTimestamps:[00:00] Intro & teaser [01:14] Meet Brent (FinOps Architect, Wayfair) [02:34] Making AI adoption easy for developers [03:30] Three-area cost governance framework [04:45] Automated FinOps guardrails in pull requests [07:29] Predictive analytics: 400% over budget warnings [08:26] The 400% spender: asset or liability? [10:06] The "spend captain" model [12:13] The goal: 1000x more token use in two years [13:05] The thought experiment [15:08] The $400k workflow rebuilt for $80k [16:42] Hardcoded first, LLM as fallback [19:49] Engineers now own their full cost stack [20:13] The FinOps companion that works overnight [24:10] Guardrails injected before the pull request [26:17] Recurring tasks become automated skills [27:46] Sankey diagram: cost per agent step in real time [28:40] "The bill didn't blow up - that doesn't happen by accident"

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.

The conversation moves through building an AI-powered morning brief that reads every email, Slack message, and tweet before you've even opened your laptop, letting pinned threads check in on themselves every 30 minutes, and a skills system built to mirror how a person actually writes and reviews code. There's a close look at the guardrails and permission layers that keep an autonomous agent from pushing to the wrong repo or replying to the wrong tweet, how a codebase merging thousands of pull requests a day survives thanks to self-healing review before anything hits CI, and the idea of AI deference - when an agent should push through a task alone versus stop and ask for help.

The back half gets personal: why developing taste and vocabulary now matters more than working harder, what it actually takes to delegate to an agent the way you'd onboard a new employee, and why this might be the year voice-orchestrated computer use finally makes everyone feel like they're talking to Jarvis.

OpenAI: https://openai.com

Monaco: https://www.monaco.com

Jason Liu: https://www.linkedin.com/in/jxnlco

Mihail Eric: https://www.linkedin.com/in/mihaileric

Demetrios: https://www.linkedin.com/in/dpbrinkm

Timestamps:

[00:00] Intro and guest backgrounds

[01:36] Why computer use beats plain API calls

[09:11] Building an AI-powered morning brief

[10:17] Self-monitoring threads that check in on their own

[18:26] How OpenAI reviews thousands of PRs a day

[19:42] Self-healing pull requests before CI even runs

[23:07] Building review skills from teammates' habits

[30:52] Why hard work stops being the differentiator

[35:03] Introducing the idea of AI deference

[42:44] Learning to delegate like hiring your first assistant

[46:22] Why voice beats typing for giving agents context

[50:56] The Tony Stark Jarvis analogy for this year

AI is eating enterprise budgets faster than anyone modeled for, and DraftKings is trying to get ahead of it before it becomes a headline. In this episode, Rick LaFaver, Director of FinOps Cloud at DraftKings, joins us straight from the conference floor to talk about what's actually changed in the economics of running AI at scale — and why the playbook that worked for cloud cost optimization doesn't translate cleanly.

We get into the token density problem: models are charging more per token while packing less meaning into each one, and Rich breaks down what that's doing to the real cost of "good enough" output versus frontier-model output. He walks through how his team built an internal cost data warehouse that lets anyone query spend like a Snowflake analyst, and how they bent the DORA framework into something that actually measures whether AI is paying for itself — not just how much it costs.

From there, the conversation opens up into culture and strategy: why DraftKings never had to police "token maxing" because ownership did the work policy couldn't, how they spot the engineers quietly getting 10x more value out of the same models, and why Rich thinks manual model selection is already a dead end. We also touch on the pull of vendor lock-in, OpenAI's background agent swarms doing QA and cleanup work nobody assigned, the "just because we can doesn't mean we should" instinct that's starting to show up in engineering reviews, and Rich's longer-term bet on building a fully autonomous FinOps function.

Draft Kings: https://www.draftkings.com

Rick LaFaver: https://www.linkedin.com/in/ricklafaver Demetrios: https://www.linkedin.com/in/dpbrinkm

Timestamps:[0:00] Cold open: the $100M AI spending horror stories[1:16] Meet Rich, Director of FinOps Cloud at DraftKings[1:42] Building an AI-powered cost data warehouse[2:59] Getting ahead of AI spend with an early RFP[4:34] What value actually means in an AI context[7:32] Surprises after a year of value realization data[9:27] Why token density is dropping as prices rise[10:44] Right-sizing models from Haiku to Opus[12:49] Why some AI builds should stay off your roadmap[13:04] Big spenders vs the golden path of value[16:49] The risk of locking into one AI vendor[17:56] OpenAI's autonomous agent swarms explained[18:58] Because we can doesn't mean we should[21:33] The skill optimization that saved millions a day[24:10] A simple framework for prioritizing AI bets[25:44] Why model routing needs to be automatic[27:30] Not every problem needs an LLM[30:45] The secret menu of Claude Code features[32:57] Building a fully autonomous FinOps engine

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 discuss how AI token costs dropped 80% in two years, why that trend has sharply reversed with frontier models doubling in price, and how Josh rebuilt a single LLM workflow that cost $400k a month down to $80k by rethinking the architecture. He also shares how a cost calculator built in 15 minutes transformed the way his team estimates spend before running experiments, and why research-led optimization is the only kind that works without degrading the product.

Along the way, we cover hidden costs most teams miss, the trade-off between Azure reserved capacity and OpenAI Priority Processing, why fixed subscription pricing is broken in an AI-native world, vendor lock-in risk, and what OpenAI's Guaranteed Capacity announcement really signals about where vendor relationships are heading next.

Superhuman: https://superhuman.com

Josh Collier: https://www.linkedin.com/in/josh-collier-945b7029/

Demetrios: https://www.linkedin.com/in/dpbrinkm

Timestamps:

[00:00] OpenAI Guaranteed Capacity: what's really going on

[01:04] Josh's path into AI FinOps

[02:48] Token costs: the 80% price drop

[04:16] Why costs will only go up

[05:06] External LLMs as financial risk

[07:16] Why subscription pricing is dead

[08:22] The data residency fee nobody notices

[09:33] The cost calculator built in 15 minutes

[10:24] How it changed dev team speed

[13:00] Tracking costs by service and team

[15:33] $400k workflow rebuilt for $80k

[17:13] Why only research can optimize tokens

[20:00] Speculative decoding win

[23:11] One bad query, $40k gone

[26:00] Why Azure PTU was exhausting

[28:59] Shadow traffic load testing

[29:07] Priority processing: no brainer

[31:10] Guaranteed capacity: lock-in signal?

[32:18] The danger of multi-year AI deals

[33:28] Vendor-agnostic proxy as exit strategy

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 foundation for the next generation of AI agents.

We discuss why MCP is moving toward stateless communication, what developers misunderstand about state, sessions, and transport layers, and how lessons from real-world deployments at massive scale have shaped the protocol's future. We also dive into MCP v2, SDK migrations, protocol design, extension architecture, governance, developer experience, and how Anthropic thinks about balancing simplicity with long-term flexibility.

Along the way, we explore progressive disclosure, tool search, programmatic tool calling, context bloat, forward compatibility, long-running AI tasks, protocol evolution, open-source governance, observability, and why the future of AI infrastructure will depend on designing protocols that can evolve without breaking the ecosystem.

Timestamps:

[00:00] Introduction

[01:59] Why MCP Had to Become Stateless

[04:28] The Tradeoffs of Stateless Design

[06:13] What We Learned About Agent State

[08:04] Sessions, Models & Implicit State

[09:33] Migrating to MCP v2

[12:19] Lessons from HTTP & Open Source Standards

[18:16] Shipping Fast Without Breaking Everything

[20:35] The Future Complexity of MCP

[22:44] Core Features vs Extensions

[26:47] Progressive Disclosure Explained

[28:16] Solving Context Bloat

[30:50] Why Tool Search Beats Progressive Disclosure

[32:10] The Biggest MCP Anti-Pattern

[34:25] Designing for Forward Compatibility

[38:41] Why "Tasks" Matter

[40:53] JSON, Tokens & Better Tool Calling

[44:44] Observability & Tracing AI Agents

[47:34] Will MCP Ever Be Finished?

[50:22] What's Next for MCP

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, he breaks down why most enterprise AI programs stall — and the playbook the winners are using instead.

Huge thanks to PwC for supporting this episode!

💰 The 30% benchmark — What "good" actually looks like: real efficiency gains clients are reporting across engineering, finance, HR, and supply chain

🔄 Workflows, not use cases — Why isolated pilots and POCs never show up in EBITDA, and how end-to-end workflow redesign does

🧪 Champion vs. challenger — Running a control group against your AI-automated process so ROI is demonstrated, not guessed

📞 Why customer care agents are still freaking hard — Context, CDP integration, billing systems, and voice-to-voice latency

💸 Tokenomics & FinOps — Consumption-based cost surprises, model selection, prompt engineering, and enforcing cost-per-workflow budgets

🔍 Auditing agentic behavior — Using AI to test AI, the missing "SOC 2 for agents," and certifying agents for sensitive use cases

👤 Human in the loop as an evolving scale — From reviewing 50% of outputs down to 10% as trust builds

🧠 88% do AI, 33% scale it — Building a culture of innovation, and why AI usage is showing up in performance reviews

💼 Jobs, reskilling & the operating model reset — Why 75%+ of jobs will be reskilled, not replacedIf you're an AI leader, platform engineer, or exec trying to turn AI experiments into P&L impact, this one's for you.

Links & Resources:

Connect with Manish: https://www.linkedin.com/in/manishdasaur/

PwC AI: https://www.pwc.com/us/en/tech-effect/ai-analytics.html

PwC's 2026 AI Business Predictions: https://www.pwc.com/us/en/tech-effect/ai-analytics/ai-predictions.html

Timestamps:

[00:00] AI Hype vs Business Value

[00:44] API Spend Tracker Widget

[02:18] Tokenomics and FinOps for AI

[06:19] Measuring AI Impact Objectively

[11:07] AI in Support Workflows

[18:05] AI Innovation Culture

[27:16] MCP Servers and SOC 2

[29:14] Human in the Loop in evolving scale

[35:44] AI and Workforce Efficiency

[39:59] AI Transformation and Mindset

[42:19] Wrap-up

In this episode, we're joined by Jeremiah Lowin, Founder & CEO at Prefect and the creator of FastMCP, to explore how one of the most influential projects in the MCP ecosystem came to be - and where the protocol is heading next.

We discuss the accidental origin of FastMCP, why Anthropic adopted it into the official SDK, what developers are getting wrong about MCP, and why Chris believes the biggest opportunity for AI agents isn't customer-facing applications, but internal enterprise systems. We also dive into MCP Apps, developer experience, protocol design, AI tooling, Python, and why building great abstractions is often more valuable than exposing more configuration.

Along the way, we explore the rapid growth of the MCP ecosystem, how FastMCP became the default way many developers build MCP servers, why "too much magic" can actually hurt developer experience, and what the next generation of AI-powered applications will look like as agents move beyond simple tool calling into rich, interactive experiences.

Prefect: https://www.prefect.io

Jeremiah Lowin: https://www.linkedin.com/in/jlowin

Demetrios: https://www.linkedin.com/in/dpbrinkm

Timestamps:00:00 Lost My Entire Talk00:47 The Story Behind FastMCP02:08 Anthropic Adopted FastMCP02:34 When MCP Took Off04:10 FastMCP vs The Official SDK05:43 Is MCP Actually Dead?06:42 What Everyone Gets Wrong About MCP08:11 MCP's Biggest Use Case10:25 Building Internal AI Systems12:00 Why FastMCP Exploded13:29 Making Complex Software Simple15:10 Can Software Be Too Magical?20:11 MCP Apps Explained23:42 Why Python Needed MCP Apps27:54 The Future of AI Interfaces34:18 AI Should Generate UIs40:11 AI Deleted My Presentation43:30 The AI Assistant We Actually Need48:00 Personal AI vs SaaS52:28 The Future of AI Agents55:06 Final Thoughts

In this episode, we're joined by Stephen O'Grady, Co-Founder and Principal Analyst at RedMonk, to explore one of the biggest shifts happening in software engineering: AI is making code dramatically cheaper to produce, but everything downstream is becoming the new bottleneck.

We discuss why SaaS isn't dead despite the hype, the explosive rise of MCP, why AI agents are overwhelming developer infrastructure, and what happens when every engineer suddenly has dozens of AI developers working alongside them. Stephen explains how package managers, code reviews, security, governance, and enterprise systems are all struggling to keep pace with AI-generated software.

Along the way, we dive into AI coding tools, MCP adoption, developer productivity, infrastructure scaling, enterprise software, open source, package repositories, governance, and why the hardest problems in software may no longer be writing code—but managing everything that comes after.

RedMonk: https://redmonk.com

Stephen O'Grady: https://www.linkedin.com/in/sogrady

Demetrios: https://www.linkedin.com/in/dpbrinkm