The Control-vs-Magic Spectrum Building Agents

The Control-vs-Magic Spectrum Building Agents

Author: Demetrios June 5, 2026 Duration: 43:18

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.br

iFood Pago: https://ifoodpago.com.br

ZenML iFood Case Study: https://www.zenml.io/llmops-database/building-a-hyper-personalized-food-ordering-agent

LangGraph: 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


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

Agentic Conversations (formally mlops.community)
Podcast Episodes
The Creator of FastMCP Explains the Future of MCP [not-audio_url] [/not-audio_url]

Duration: 55:11
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 headin…
What Happens When Every Developer Has 20 AI Agents? [not-audio_url] [/not-audio_url]

Duration: 34:37
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, bu…
AI Agents Should Be Treated Like Hackers [not-audio_url] [/not-audio_url]

Duration: 31:35
In this episode, we're joined by Matt DeBergalis, CTO and Co-Founder of Apollo GraphQL, to explore what happens when AI agents start interacting with enterprise systems that were never designed for them.We dive into the…
Developers May Stop Depending on Libraries [not-audio_url] [/not-audio_url]

Duration: 46:52
In this episode of Agentic Conversations, we're joined by Shaun Smith, software engineer, open source advocate, and contributor at Hugging Face, to explore how AI coding has changed almost overnight.We dive into reinforc…
10 Cities. 4 Countries. One Unexpected MCP Lesson. [not-audio_url] [/not-audio_url]

Duration: 22:18
In this episode, we're joined by Ben Morss, Developer Advocate at DeepL, who spent months traveling across North America and Europe teaching developers about MCP, building MCP servers, and helping teams understand how AI…
The Next Programming Language Is English [not-audio_url] [/not-audio_url]

Duration: 38:13
In this episode, we're joined by Cornelia Davis, Developer Advocate at Temporal and a longtime software architect who has spent decades helping shape modern cloud-native systems.We explore how programming has evolved fro…
Omnigent: Composition, Control, and Collaboration for AI Agents [not-audio_url] [/not-audio_url]

Duration: 58:16
Denny Lee is PM Director, Startups & Ecosystem at Databricks, a longtime Apache Spark, MLflow, and Delta Lake contributor — and one of the people behind Omnigent, the open-source meta-harness Databricks just released und…
The Current State of Agentic Retrieval - Qdrant Roundtable [not-audio_url] [/not-audio_url]

Duration: 58:54
Qdrant Roundtable episode: The Current State of Agentic RetrievalJoin the Community: https://go.mlops.community/YTJoinInGet the newsletter: https://go.mlops.community/YTNewsletterMLOps GPU Guide: https://go.mlops.communi…
AI Agents in Healthcare? [not-audio_url] [/not-audio_url]

Duration: 39:28
Kingsley Madikaegbu is the founder of HealID, a startup building agentic AI on top of the Model Context Protocol (MCP) for one of the most heavily regulated environments there is: healthcare.Recorded at MCP Dev Summit No…
Coding Agents Are Secretly General Agents [not-audio_url] [/not-audio_url]

Duration: 1:12:02
In this episode:🧠 Coding agents are generalist agents — why "positive transfer" means an agent that's better at code is better at everything, and how that makes them "AGI-complete"⏳ "Code will be solved in a year" — what…