Building Real-World AI Systems in Production with OpenAI’s Emre Okcular
Brandon interviews Emre Okcular, a Solutions Architect in Applied AI at OpenAI, about what it actually takes to build and deploy AI systems in production. Emre works directly with organizations to design, evaluate, and deploy AI-powered products and workflows. In this conversation, he explains how Applied AI bridges research, product development, and real-world business value. Topics include: Enterprise AI deployments AI agents and long-running workflows Customer support chatbots, voice agents, and OCR Moving from demo to production LLMOps and observability Loop engineering and evaluations Memory and context engineering Cost, scaling, and adoption One of the key themes of the conversation is non-determinism. Traditional software systems typically return the same output every time. AI systems are different. Building reliable AI systems requires a different engineering mindset. 00:00 Embrace Non-Determinism 00:48 Meet Emre Okcular 01:59 What Applied AI Means 03:24 Enterprise AI Use Cases 07:52 Long-Running AI Agents 09:31 From Demo to Production 12:33 LLMOps Explained 14:17 Loop Engineering & Evals 23:09 Memory for AI Agents 26:15 Tools and Frameworks 27:04 What Engineers Get Wrong About AI 29:30 Cost, Scaling & Adoption 31:21 Advice for Students 32:58 Lightning Round 33:58 Thanks and Subscribe 🎙️ Watch the demo: • How AI Agent Memory Actually Works: Trimmi... ________________________ 𝗖𝗼𝗻𝘁𝗮𝗰𝘁 𝗠𝗲 • LinkedIn: / brandonkrakowsky • Wharton AI & Analytics Initiative: https://ai-analytics.wharton.upenn.edu 𝗣𝗼𝗱𝗰𝗮𝘀𝘁 𝗟𝗶𝗻𝗸𝘀 • Interviews: • Learn the Technology: Interviews • How To Videos: • Learn the Technology: How To Videos • Spotify: https://bit.ly/47JxADO 𝗙𝗼𝗹𝗹𝗼𝘄 𝗠𝗲 • Instagram: / learnthetechnologywithbk • TikTok: / learnthetechnologywithbk • X (Twitter): https://x.com/LearnTechWBK • GitHub: https://github.com/learnthetechnology... 𝗖𝗼𝘂𝗿𝘀𝗲𝘀 𝗼𝗻 𝗖𝗼𝘂𝗿𝘀𝗲𝗿𝗮 • Intro to Programming with Python and Java: https://www.coursera.org/specializati... • How to Use Data: https://www.coursera.org/specializati...

Interview: Building Apps with Google AI Studio

Interview: Inside Serve Robotics -- How Autonomous Delivery Robots Navigate Cities

Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

Interview: Clive Thompson on Coders, AI Coding, and the Future of Software

Interview: AWS SageMaker Features, Use Cases, and Machine Learning Insights

Interview: Exploring UX Research and Design with Mike Hawley

The Missing Pillar in FP&A ft. Paul Barnhurst - The FPandA Guy | ChatFin

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

How to Build a Remarkable Brand in the Age of AI | Seth Godin

How AI Agent Memory Actually Works: Trimming, Compaction & Summarization

Something is jamming GPS over Europe. Here's what we found

Interview: How the Hubble and James Webb Space Telescopes Work | Exoplanets & Brown Dwarfs Explained

Anthropic's Boris Cherny: Why Coding Is Solved, and What Comes Next

From Idea to $650M Exit: Lessons in Building AI Startups

We Tested Anthropic’s Fable 5 for a Week

Don't learn AI Agents without Learning these Fundamentals

The Match That Made Brazilians Hate Germany

Interview: How LinkedIn Built AI Job Search Using Large Language Models (LLMs)

How to Build an AI-Native Services Company

