The Control-vs-Magic Spectrum Building Agents

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 // MLOps Podcast #382 with Thiago Cardoso, Director of Data & AI at iFood🤖 WHAT WE COVER:🔹 Control vs. Magic — Thiago's spectrum model for thinking about AI agents, from deterministic pipelines to fully autonomous systems🔹 iFood Pago Explained — How iFood's embedded fintech arm uses AI agents to provide credit, loans, and financial services to restaurants🔹 WhatsApp as an AI Interface — Why WhatsApp is the primary channel for merchant interactions in Brazil and how agents are deployed there🔹 Multi-Agent Architecture — Why single monolithic agents break down and how to split them into sub-graphs with specialized contexts and tool sets🔹 Context Engineering — Why what you put in the agent's context window is more important than the model itself🔹 Human-in-the-Loop Design — How to build trust with merchants while minimizing friction in agentic workflows🔹 LangGraph in Production — How Thiago's team uses LangGraph to build stateful, multi-agent pipelines🔹 Debugging with AI — Generating on-the-fly HTML/JavaScript visualization tools to investigate data pipeline problems🔹 The Cost of Software Going to Zero — What happens to demand when software becomes nearly free to build🔹 Personalization at Scale — Serving millions of restaurants with AI that knows their business context🎯 This episode is for AI engineers, ML practitioners, and fintech builders who want to understand what production agentic AI looks like beyond the demos.🔗 LINKS & RESOURCES:Thiago Cardoso on LinkedIn: https://www.linkedin.com/in/thiagoncc/iFood: https://www.ifood.com.briFood Pago: https://ifoodpago.com.brZenML iFood Case Study: https://www.zenml.io/llmops-database/building-a-hyper-personalized-food-ordering-agentLangGraph: https://www.langchain.com/langgraph⏱️ TIMESTAMPS[00:00] Control vs Magic in AI[00:18] Foodpago Fintech Ecosystem[08:59] Scaling Personalization with AI[15:04] Chat UI Evolution[20:22] Context Layer in Systems[26:39] Agent Growth Dynamics[33:39] Job Evolution with Open Claude[39:54] AI and Software Costs[41:50] Wrap up#AIAgents #Fintech #iFood

Sherwood Callaway is the founder of Sazabi (YC P26), the AI-native observability platform built for engineering teams who ship fast. He previously founded and exited a YC company — now he's back, betting that logs are all you need to replace Datadog.Logs Are All You Need: Rethinking Observability with AI Agents // MLOps Podcast #381 with Sherwood Callaway, the Founder of Sazabi🔑 What's covered:🪵 Logs vs. The Three Pillars — Sherwood makes the case that the traditional observability stack (metrics, logs, traces) is overkill. In 2026, with AI agents in the loop, logs alone are sufficient — and dramatically simpler to instrument.🚨 AI-Generated Alerts, Not AI-Evaluated Alerts — Instead of using AI to triage your noisy alert stream, Sazabi generates the alerts autonomously from your logs and codebase — so you never configure a monitor again.🤖 Agent Sandboxing & Bash Access — How Sazabi gives its AI agent a persistent bash sandbox with CLI tool access, why every other action routes through that sandbox, and how RLS database permissions keep the agent from doing damage.🧠 Agentic Memory via Git — Sazabi's novel approach to persisting agent memory across threads using Git branches — enabling multiple parallel sub-agents to share findings without bloating the context window.🔀 Multi-Agent Parallelization — How Sazabi spawns sub-agents and background agents on-demand to investigate production issues in parallel, the way Claude Code displays a live to-do list of agent work.📊 Why Evals Are Hard (and What They Built Instead) — An honest conversation about the difficulty of evaluating agentic systems, log-based eval proxies, and why Sazabi still doesn't buy third-party eval tooling.⚡ MCP Servers, Skills Bloat & Context Management — The tradeoffs between MCP servers and local skill files, progressive tool disclosure, and why context window management is the hidden bottleneck in production agent systems.🎯 Building a Moat in 2026 — Sherwood and Demetrios debate what a defensible advantage actually looks like when every AI tool can be cloned fast. Spoiler: "We built it first" is not a moat.🚀 Beta Launch & Who It's For — Sazabi is in closed beta and opening the waitlist. If your team uses Cursor or Claude Code and you have production traffic you can't afford to break, this is built for you.👉 Perfect for: AI engineers, SREs, DevOps teams, and founders building production-grade agent systems who are questioning whether their current observability stack is overbuilt.🔗 Links & Resources🌐 Sazabi: https://sazabi.com📄 Sazabi on Y Combinator: https://www.ycombinator.com/companies/sazabi💼 Sherwood Callaway on LinkedIn: https://www.linkedin.com/in/sherwood-callaway📰 SiliconANGLE coverage: https://siliconangle.com/2026/04/08/startup-sazabi-bets-on-logs-and-ai-agents-to-replace-traditional-observability-stacks/💻 MLOps.community: https://mlops.community⏱️ Timestamps [00:00] Genetic Agent Evolution[00:33] Dethroning Datadog[03:13] Sazabi vs Traditional Observability[10:47] MCP vs CLI Paradigm[15:12] Sandbox Usage for Agents[24:28] Genetic Prompt Optimization[32:34] Eval and Agent Spawning[38:45] RL Environment Tensions[45:40] Sazabi is hiring![46:10] Wrap up#Observability #AIAgents #DevTools

Joe Maionchi (Co-founder & COO) and Rod Christensen (Co-founder & Chief Architect) of RocketRide join the MLOps Community to walk through AIDE — the AI Integrated Development Environment. RocketRide is an open-source AI pipeline platform that lets developers build, debug, and run production-grade agentic AI workflows directly from their IDE, with support for 13+ LLM providers, 8+ vector databases, and full multi-agent orchestration.AI Is Fast. AI Projects Are Slow. Let's Fix That. // MLOps Podcast #378 with JRocketRide's Joe Maionchi (Co-founder & COO) and Rod Christensen (Co-founder & Chief Architect)A huge shout-out to  ⁨RocketRide⁩  for this collaboration!🔑 What's covered:🏗️ Why AI infrastructure needs standardization — how coding agents produce inconsistent "glue code" across projects and why a typed node graph fixes it⚡ Efficiency AI vs. Opportunity AI — the two paths companies take with generative AI, and which one actually compounds growth🔀 Multi-agent pipeline orchestration — running CrewAI, LangChain, and DeepAgent side-by-side to benchmark which works best for your use case💰 Cutting LLM costs in half — design-time strategies for routing tasks to cheaper models without sacrificing output quality🔍 Pipeline observability & debugging — logging every node step in dev and production so you can pinpoint exactly where a 10-step pipeline breaks🖼️ Beyond text: image, video & audio nodes — frame grabbing, OCR, Whisper transcription, and speech-to-text running on shared GPU infrastructure🚀 RocketRide Cloud — one-click deploy from local to cloud with dynamic GPU scaling and cost-efficient shared inference🧠 Intentionality in agentic development — why moving fast with AI agents creates "crappy code fast" and how skills/context files change the equation🔌 MCP support & framework-agnostic design — swap any model, tool, or framework without rewritesThis episode is essential for AI engineers, ML practitioners, and developers building production LLM applications who want to stop reinventing infrastructure and start shipping.🔗 Links & Resources:• RocketRide website: https://rocketride.ai• RocketRide open source (GitHub): https://github.com/rocketride-org/rocketride-server• AIDE VS Code Extension: https://rocketride.org• MLOps Community: https://mlops.community• Discord: https://discord.gg/Hd4PukFt2H⏱️ Timestamps[00:00] Cost Savings in AI[00:21] AI, Developer, and Software Development Evolution[02:51] Intentionality in Software Development[10:51] Model Skill Optimization[17:08] Primitives in AI Systems[29:00] Coding Agent Challenges[37:09] RocketRide Inspiration[44:42] Coding Agents and Documentation[47:40] RocketRide Cloud Overview[56:27] Wrap up

BuzzHPC Roundtable episode: Architecting Modern AI Systems: Platforms, Agents, and Integration Join the Community: https://go.mlops.community/YTJoinInGet the newsletter: https://go.mlops.community/YTNewsletterMLOps GPU Guide: https://go.mlops.community/gpuguideBig shout-out to BuzzHPC for the collaboration!// AbstractAs 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 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 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 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.// BioAllen RoushAllen has held senior technical and AI leadership roles at companies like Oracle and Intel. He's very active in the AI research space and open source communities. He's passionate about improving the creativity and coherence of AI systems.Frédéric BénardFrédéric is Senior Director of AI Applications Development at Mila (Quebec AI Institute), where he leads a team focused on building the engineering foundations for applied AI systems. His work centers on translating cutting-edge research into scalable applications, including AI-driven platforms and agent-based systems used across research and industry collaborations.Shuo WangShuo leads the Responsible AI Office for Bell Canada, where all AI use cases are reviewed and assessed for potential harm and bias. Previously, he led a team of data scientists to expand a large-scale ML program to improve customer support effectiveness.// Related LinksWebsite: https://www.buzzhpc.ai/~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExploreJoin our Slack community [https://go.mlops.community/slack]Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)] Sign up for the next meetup: [https://go.mlops.community/register]MLOps Swag/Merch: [https://shop.mlops.community/]Connect with Demetrios on LinkedIn: /dpbrinkmConnect with Allen on LinkedIn: /allen-roush-27721011b/Connect with Frédéric on LinkedIn: /benard/Connect with Shuo on LinkedIn: /shuow/

Big news: the MLOps Community is joining the Linux Foundation to become the official user community of the new Agentic AI Foundation (AAIF). The AAIF is the neutral home for open source projects like the Model Context Protocol (MCP), goose, and AGENTS.md, co-founded by Anthropic, Block, and OpenAI. With that governance and scaffolding now in place, the open source agent ecosystem has room to scale, and the MLOps Community is right in the middle of it.Everything you love about the community from the past six years keeps going, and we are adding even more on top.What this means:- Official user community: MLOps Community becomes the user community of the Agentic AI Foundation under the Linux Foundation.- The projects: MCP, goose, and AGENTS.md now live under one open, neutral governance structure built to scale.- Nothing goes away: The podcast, the global meetups, the weekly newsletter, the Slack workspace, and the virtual events all continue.- New: Ambassador Program: Just opened for applications, so you can get more involved in the community.- AgentCon EU: September 17 and 18 in Amsterdam.- AgentCon North America: October 22 and 23 in San Jose.- A possible new name: The podcast may become "Agentic Conversations," because honestly all we talk about is agents. Tell me what you think in the comments.If you build with AI agents or follow the open source agent ecosystem, this is the update to bookmark. This is MLOps Community 2.0.Links and Resources:- MLOps Community: https://mlops.community- MLOps Community 2.0: https://mlops.community/blog/mlops-community-2-0- Agentic AI Foundation: https://aaif.io- Ambassadors: https://aaif.io/ambassadors- Linux Foundation AAIF announcement: https://www.linuxfoundation.org/press/linux-foundation-announces-the-formation-of-the-agentic-ai-foundation- AgentCon and MCPCon events: https://events.linuxfoundation.org/aaif-events/- Model Context Protocol (MCP): https://modelcontextprotocol.io- goose: https://goose-docs.ai- AGENTS.md: https://agents.mdTimestamps (approximate, adjust before publishing):00:00 The big announcement00:12 Joining the Linux Foundation's Agentic AI Foundation00:30 Why it matters: MCP, goose, and AGENTS.md00:48 What is not changing: podcast, meetups, newsletter, Slack01:15 What is new: the Ambassador Program01:30 AgentCon EU in Amsterdam and North America in San Jose01:55 A new name for the podcast: Agentic Conversations?02:10 MLOps Community 2.0#AgenticAI #MCP #LinuxFoundation

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 // MLOps Podcast #377 with Just Eat Takeaway.com's Guthrie Cooper (Senior Group Product Manager, AI & Robotics) and Nidhi Sharma (Global Head of Engineering AI & Incubation)🤖 Delivery Robots — How JET partnered with RIVR and DELIVERS.AI to deploy physical AI ground robots in Zurich, Milton Keynes, and Bristol, and what the first pilots taught the team🧠 AI Incubation at Scale — How Nidhi's team built a dedicated incubation unit to fast-track AI experiments without the red tape of a large enterprise🎙️ AI Voice Assistant — The story behind JET's new voice-first food ordering experience, and the ML challenges of building a conversational concierge at scale🦾 Physical AI vs. Software AI — Why deploying wheeled-legged robots in real cities is fundamentally different from shipping a model update, and the MLOps implications🚀 Corporate Innovation Playbook — The frameworks Guthrie and Nidhi use to move from idea to pilot in weeks, not quarters, inside a large org📦 Innovation as a Platform — How JET is thinking about turning its delivery infrastructure and AI capabilities into a reusable platform for new business lines🔗 Startup Partnerships — What makes a good external innovation partner (vs. building in-house), and how JET evaluates robotics and AI startups for pilots⚡ Agentic AI & Accessibility — How agentic AI is being used to make food ordering genuinely accessible for blind and low-vision usersWhether you're an ML engineer at a large company trying to get AI into production, a product leader navigating corporate innovation, or a startup founder looking to partner with a platform player — this conversation is packed with practical lessons.🔗 Links & Resources:Just Eat Takeaway.com: https://www.justeattakeaway.comRIVR (physical AI delivery robots): https://www.rivr.aiDELIVERS.AI (UK delivery robots): https://www.delivers.aiProsus (JET parent company): https://www.prosus.comMLOps.community: https://mlops.community⏱️ Timestamps[00:00] AI Innovation Incubator Strategy[03:16] Everyday Convenience Expansion[07:03] Context Ownership in Ecosystems[17:35] LLM Integration and Discovery[24:02] Whoop Notifications Grievances[33:01] Expanding Beyond Food[48:20] Innovation Lab Failures[51:22] Rory Sutherland's Alchemy[1:03:23] Latency and Conversational Design[1:13:42] Drone Delivery Efficiency[1:18:06] Wrap up#AgenticCommerce #VoiceAI #DroneDelivery

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.Huge thanks to ⁠PwC⁠ for supporting this episode!Autonomous Agents at Work: From OpenClaw Hype to Enterprise Reality // MLOps Podcast #378 with Pramod Krishnan, Managing Director - AI Managed Services at PwC US.🔑 OpenClaw & the Agentic Hype Cycle — Why the fastest-growing open-source agent project in history (190K+ GitHub stars in weeks) is a forcing function for enterprise AI governance, and what most organizations are getting wrong.🏗️ 3-Tier Work Classification — Pramod's framework for categorizing any agentic task as reversible, sensitive, or consequential — and how the approval gates, controls, and blast radius differ for each tier.🛡️ The Guardrails Stack — A concrete list of non-negotiable guardrails: allow-listed tool calls, prompt injection defense, credential protection, toxic output filtering, and more — straight from PwC's production deployments.🔍 5-Part Auditability Framework — How to make AI agents truly auditable across quality (LLM-as-judge), performance, safety, cost, and security — and why OpenTelemetry alone isn't enough.💰 Agent Cost & ROI Tracking — Why successfully deployed agents are generating the hardest financial measurement problems enterprises have ever faced, and what a real cost-tracking architecture looks like.🔒 Agent Security in Depth — From API key harvesting attacks to credential leakage to malicious actor scenarios: what security controls PwC requires before any agent goes live.⚙️ The Minimum Control Stack — The non-negotiables Pramod would walk in with on a Monday before clearing any agent for production: what they are, why they matter, and how to implement them.🔄 Human-in-the-Loop Design — The difference between "human in the loop" (approves every action) and "human on the loop" (monitors and intervenes) — and how to choose the right pattern based on consequence level.🤝 AI as a Force Multiplier — How Pramod thinks about AI ownership, intellectual authorship, and making sure humans remain deliberate and responsible even as agents accelerate output.This episode is essential for ML engineers, platform architects, CIOs, and AI product managers who are moving beyond demos into real enterprise agentic deployments.🔗 Links & ResourcesPramod Krishnan on LinkedIn: https://www.linkedin.com/in/pramod-potti-krishnan/MLOps.community: https://mlops.communityOpenClaw project: https://openclaw.aiBCG on OpenClaw + Enterprise: https://www.bcg.com/publications/cios-openclaw-and-the-new-wave-of-ai-agentsPwC 2026 AI Business Predictions: https://www.pwc.com/us/en/tech-effect/ai-analytics/ai-predictions.htmlTimestamps:[00:00] AI in Enterprise[02:04] AI System Failures[08:01] Agent Decision Tracing[13:07] Agent Design Tension[16:21] Agent Control Stack Essentials[20:20] LLM Cost and FinOps[26:16] Agent Attack Surfaces[30:00] Tools as Attack Vectors[33:47] Human in the Loop[37:00] AI Ownership and Accountability[41:42] Wrap up. Shoutout to Pramod and PwC!

Hamza Tahir, co-founder of ZenML, joins the show to cut through the hype around long-running agents — arguing that at the end of the day, an agent is just a while loop that talks to a model, calls a tool, and writes to a file system. He covers the architecture of agent harnesses (inner and outer), what durable execution actually guarantees (and what it doesn't), and why the ML pipeline paradigm is a cleaner mental model than transactions for most agent workloads.Hamza also announces Kitaru — ZenML's new open-source execution runtime for async Python agents — built on five years of running ML workloads in enterprise environments.What we get into:Agents are while loops: The surprising simplicity under all the tooling: a brain (LLM), hands (tool calls), and a file system, stacked recursivelyInner harness vs outer harness: Why Pydantic AI owns the inner loop while production deployment needs a separate runtime layerWhat "long-running" actually means: Why the infrastructure we need to build is about extrapolating the future, not defining a time window todayDurable execution demystified: What checkpointing actually guarantees (infra failures, pod death, network drops) vs. what it never will (external state, bad LLM outputs, Snowflake rollbacks)ML pipelines vs transactions: Why bursty containers in Kubernetes map more naturally to agent workloads than microsecond-latency queue workers — and why Hamza argues against the complexity taxAnthropic opening the harness: Why letting other models run Claude Cowork is a "boss move," and what it means for the one-harness vs one-model debateHuman-in-the-loop, done right: The pod-kill-and-resume pattern, and why warm pools matter less when your agent runs for daysKitaru: ZenML's new open source durable execution runtime: zero-config local, Kubernetes/SageMaker/Vertex in production, built on Pydantic AI integrationArguing with Claude about Temporal: Hamza's story of spending hours getting an LLM to admit ZenML and Temporal solves the same problemIf you're architecting agents for production, picking between Pydantic AI, LangGraph, and Temporal, or just want to understand what "durable execution" actually means — this is the episode.// LINKS & RESOURCESKitaru on GitHub: https://github.com/zenml-io/kitaruKitaru launch blog post: https://www.zenml.io/blog/kitaru-launchKitaru on Hacker News: https://news.ycombinator.com/item?id=47520115Hamza Tahir on LinkedIn: https://www.linkedin.com/in/hamzatahirofficial/ZenML: https://www.zenml.io/ Timestamps[00:00] While Loop Checkpointing[00:24] Long-Running Agents Explained[01:28] Agent Harness Model Definitions[06:30] Durability and State Recovery[11:03] Agent Systems Layers[18:45] Durability in Agent Systems[22:07] ML Pipeline vs Transactions[29:23] Durability vs Guarantees[33:13] Durability vs Chaos Engineering[39:50] Kitaru Naming and Purpose[40:38] Wrap up#AIAgents #DurableExecution #OpenSource

Rafael (Head of Innovation, iFood) and Daniel (Data and AI Manager, iFood) pull back the curtain on ILO-Agent — iFood's conversational AI ordering system built for 200 million users across Latin America. Recorded live at AI House Amsterdam, this conversation goes deep into the engineering and product decisions behind building recommendation systems and agentic AI, and why the speed of your AI's response might actually be destroying user trust.The Latency Goldilocks Zone Explained // MLOps Podcast #376 with iFood's Rafael Borger (Head of Innovation) and Daniel Wolbert (Data and AI Manager)🍕 Recommendation Systems at Scale — Why personalizing for 200M users with wildly different food tastes, budgets, and cultures is a fundamentally different problem than standard ML🤖 ILO-Agent Deep Dive — What iFood's conversational AI agent actually does, how it handles open-ended requests ("a romantic dinner for two, my wife hates onions"), and where it's headed⏱️ The Latency Goldilocks Zone — The fascinating insight that LLM responses can be too fast (users don't trust them) or too slow (users abandon) — and how to find the sweet spot🧠 Perceived vs. Actual Latency — Why showing progress indicators and partial results can make a 6-second response feel instant, and how iFood uses this in production🛒 The Tinder for Food Experience — How iFood is experimenting with swipe-based discovery to solve "I don't know what I want to eat" for millions of undecided users🗣️ Voice vs. Text AI Interfaces — Why voice ordering limits you to 6 items in 30 seconds, and why text-based agents need radically different output design🔗 Agent-to-Agent (A2A) Architectures — What happens when your customer support agent and your ordering agent need to collaborate, and the standardization challenges ahead📊 Measuring Product-Market Fit for AI — Why the Sean Ellis / Chanel score method breaks down in Brazil, and what iFood uses instead🏗️ Scalability vs. Ecosystem Health — The real tension between consuming partner APIs aggressively and keeping the food delivery ecosystem sustainable🌎 Building AI for Global-Local Markets — Why one-size-fits-all AI products fail and how iFood builds for cultural and economic diversity simultaneously. This episode is for ML engineers, AI product managers, and data scientists building production AI systems at scale — especially if you're working on recommendation, retrieval, or agentic systems in consumer apps.🔗 Links & ResourcesMLOps.community: https://mlops.communityAI House Amsterdam: https://aihouse.amsterdamiFood: https://www.ifood.com.br/iFood AILO launch coverage: https://tiinside.com.br/en/10/10/2025/ifood-lanca-ailo-assistente-de-ia-que-inaugura-pedidos-por-conversa/iFood AI case study (AWS): https://aws.amazon.com/solutions/case-studies/ifood-bedrock/Related MLOps Community talk — "From Zero to AILO" by Nishikant Dhanuka & Chiara Caratelli: https://home.mlops.community/public/videos/from-zero-to-ailo-lessons-learned-from-building-ifoods-ai-agent-nishikant-dhanuka-and-chiara-caratelli-2025-11-25ZenML LLMOps database write-up on iFood's hyper-personalized agent: https://www.zenml.io/llmops-database/building-a-hyper-personalized-food-ordering-agent-for-e-commerce-at-scale⏱️ Timestamps[00:00] Recommending the unknown[00:18] Ailo Hyperpersonalization Insight[06:24] Predictive Personalization Insights[09:13] "Jet skis" of innovation[17:45] Consumer Behavior and Chatbots[26:33] Perceived Latency and Engagement[33:22] AI-driven UI Evolution[38:17] LCM Voice Mode Inquiry[45:20] Chat as Interface[47:46] Wrap up

Nicolas Alejandro Bogliolo is the AI PM at Despegar, the largest online travel agency in Latin America, and the engineer-product-hybrid behind Sofia, the GenAI travel concierge that beat most of the OTA world to a working multi-agent system. Before MCP was a standard and before LangChain was widely adopted, his team had already shipped their own orchestration layer and tool protocol in production. This conversation is a rare look at what it takes to build an agentic system that actually books trips, runs on WhatsApp, and keeps adding capabilities without falling over.Building MCP Before MCP Existed: Inside Despegar's Sofia Agent // MLOps Podcast #375 with Nicolas Alejandro Bogliolo, AI PM at DespegarWhat we cover:- Chappi, the brain of Sofia: how Despegar built an internal orchestration layer when there was nothing off the shelf- Building "MCP before MCP": the custom tool-calling protocol that predated the Anthropic standard- Multi-agent architecture by vertical: flights, hotels, activities, and cars each own their own flow- Decentralized agent ownership: how any squad in the company can build a flow with central supervision- Sofia on WhatsApp: making messaging the consumer control center, the way Slack became it for the enterprise- The five-phase travel arc Sofia covers: dreaming, planning, anticipation, in-trip, and post-trip- KPI evolution: why "in-scope conversation rate" topped out near 96 percent and what they measure now- The flight-delay-claim use case and why filing claims through a chatbot is a perfect agent task- Group trip planning in WhatsApp groups: the next frontier for travel agents- Sofia as channel of choice: the WeChat-style vision for an agent that handles your entire trip- Why Despegar held off on giving Sofia the ability to bargain with customers, for now. Whether you are building production agents, running an OTA, or just curious about how an AI travel concierge actually works under the hood, this episode is full of grounded, in-production lessons from a team that had to invent the patterns the rest of us are now adopting.Links and Resources:Despegar: https://www.despegar.comSofia announcement: https://investor.despegar.com/news-presentations/news-releases/news-details/2024/Despegar-revolutionizes-the-tourism-industry-introducing-the-regions-first-Generative-AI-Travel-AssistantSofia coverage on PhocusWire: https://www.phocuswire.com/despegar-debuts-genai-travel-assistant-remembers-previous-interactionsMLOps Community: https://mlops.communitySubscribe for more agent and AI infra deep divesTimestamps [00:00] Sophia Travel Concierge AI[00:38] Sophia Multi-Agent System[06:00] AI Limitations in Practice[13:52] Travel Planning Exploration[18:03] Group Travel Decision Making[21:32] Agent Ecosystem Design[30:14] Sofia's Travel Assistant Vision [33:35] Orchestration and MCP Design[40:13] Sophia Negotiation Concerns[40:47] Wrap up#AIAgents #MCP #AgenticAI