# AI Engineer Miami — Tuesday Notes - Date: Tuesday, April 21, 2026 - Venue: Hyatt Regency Miami - Main guide: https://pancake.thefocus.ai/ai-engineer-miami/ ## 8:00 AM — Check In and Breakfast Program / transition block. Notes - Tweet ideas - Questions / follow-ups - ## 9:00 AM — Welcome to Day 2 Program / transition block. Notes - Tweet ideas - Questions / follow-ups - ## 9:10 AM — Transforming Programming Mindsets: Case Studies in Agentic Coding Adoption In the rapidly evolving landscape of AI, skilled programmers often face an existential crisis, questioning the value of their expertise as their profession adopts agentic coding. This talk delves into the personal journeys of individual engineers working on a high-profile G2i project who not only adapt but thrive through agentic development. Drawing from the human-centered perspective of the counseling profession, these case studies reveal that agentic coding doesn't diminish the value of existing skills; instead, it amplifies and enriches them. Attendees will discover how empathy, adaptability, and deep human insight can enhance AI agent integration, ultimately proving that the richness of human expertise is more valuable than ever. Through these narratives, we’ll explore how AI can be a powerful amplifier of human skill, turning potential anxieties into opportunities for growth and innovation. People - [David House](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#david-house) — G2i / Engineering Manager Notes - Tweet ideas - Questions / follow-ups - ## 9:35 AM — Help! We're DEEP in (latency) Debt In software engineering, "technical debt" refers to the accumulated cost of shortcuts and slop code that works today but creates problems tomorrow. You move fast, auto-accept AI suggestions, and defer the cleanup. Latency debt works the same way. Over the past several years, we've spent enormous resources making AI models more capable, bigger, smarter, more contextually aware. What we haven't done is make the infrastructure keep pace. We optimized for intelligence. We deferred the cost of speed. That bill is now due. People - [Sarah Chieng](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#sarah-chieng) — Cerebras / Head of DevX Notes - Tweet ideas - Questions / follow-ups - ## 10:00 AM — Ambient Generative AI: Deploying Latent Diffusion Models on Mobile NPUs Most "AI-powered" mobile apps are thin wrappers around hosted APIs, tethered by high latency, cloud costs, and privacy concerns. This talk demonstrates a radical alternative: a 100% offline, sensor-driven image generator running locally on the Samsung Galaxy Z Fold 7. We will explore the technical journey of bridging React Native (Expo) with the device's NPU using ONNX Runtime and the Android Neural Network API (NNAPI). By mapping real-time hardware sensor data (Ambient Light) to latent space prompts, I demonstrate a new UX pattern for offline "Zero-Prompt" generative experiences. This session is a deep dive into the engineering required to move generative models from data centers to our pockets and good practicies how to scale that to other devices with powerful neural processing units such as iPhones. People - [Lech Kalinowski](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#lech-kalinowski) — CallStack / Senior AI System Engineer Notes - Tweet ideas - Questions / follow-ups - ## 10:25 AM — Morning Break Program / transition block. Notes - Tweet ideas - Questions / follow-ups - ## 10:55 AM — Everything is Models Given the same compute budget, does a single frontier model outperform a system of specialized models? Our research says no. We trained three task-specific models for the subtasks budget, multi-model wins: every frontier model we pair with hits #1 on SWE-Bench Pro, 15% cheaper and 28% faster than running alone - with just WarpGrep. As frontier models saturate tasks, those tasks should move to smaller models with custom inference engines. The expensive model reasons. The cheap models do the mechanical work. This talk covers the CUDA kernels, RL training, and speculative decoding behind that split, and why it's the natural way intelligence organizes under compute constraints. People - [Tejas Bhakta](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#tejas-bhakta) — Morph LLM / Founder Notes - Tweet ideas - Questions / follow-ups - ## 11:20 AM — Coding Agents Ate the World A huge portion of the industry spent the last two years building the wrong agents. We got chains, workflows, better chatbots. A hundred VC-funded frameworks gave us the illusion of agency wrapped in brittle control structures and old school determinism. Meanwhile, the teams actually winning kept arriving at the same uncomfortable answer: give the agent a code environment, and everything else solves itself. Coding agents aren't a developer tool. They never were. Code is the universal execution harness, it composes, it calls, it verifies, it spawns other agents, it runs at 3am without asking for clarification. No other AI modality does all of that. Not chatbots. Not RAG. Not your carefully orchestrated "multi-agent" workflow (which is really RPA) that demos beautifully and falls apart in week two. In this talk we'll trace the arc from deterministic pipelines to genuine agency, name the wrong turns, and make a claim that will make some people in this room uncomfortable: This is not a developer skill anymore. It's a leadership primitive. People - [Rick Blalock](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#rick-blalock) — Agentuity / Founder Notes - Tweet ideas - Questions / follow-ups - ## 11:45 AM — Effective Context Engineering Techniques for AI AI systems need more than intelligence; they need context. Without it, even the most advanced models can misinterpret information, lose track of details, or arrive at conclusions that don’t hold up. Context engineering is emerging as a discipline that shapes how AI perceives, recalls, and reasons about information. This talk will explore how context provides the foundation for reasoning, problem solving, and explainability in AI. We will look at techniques such as connected memory, contextual retrieval, and graph-based knowledge representation that give large language models a more reliable way to connect information and draw logical conclusions. Attendees will come away with a practical understanding of how to design effective context pipelines that align AI with real-world knowledge and user intent, and why context engineering is becoming a central part of building trustworthy and impactful AI systems. People - [Nyah Macklin](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#nyah-macklin) — Neo4j / Senior Developer Advocate Notes - Tweet ideas - Questions / follow-ups - ## 12:10 PM — Lunch Program / transition block. Notes - Tweet ideas - Questions / follow-ups - ## 1:35 PM — My Robot Thinks You’re a 10: Engineering Zero-Shot Compliments with Reachy Mini We talk about "agents" constantly, but most are still trapped behind a glass screen. This session explores the engineering challenges of Embodied AI by turning the Reachy Mini into a real-time, multimodal Hype Robot. We will move past simple scripted movements to a solution where the robot perceives the audience and generates contextual, physical responses. I’ll dive into the technical stack required to bridge the gap between high-level LLM reasoning and low-level servo actuation. Attendees will learn how to manage latency in vision-to-action loops and how to build something interesting and fun with an open source robot connected to an LLM. People - [Lena Hall](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#lena-hall) — Akamai / Senior Director of Developer Relations Notes - Tweet ideas - Questions / follow-ups - ## 2:00 PM — Your next user won't have eyes Devtools have always had APIs, but the polish goes to dashboards, keyboard shortcuts for power users, and per-seat pricing. Meanwhile, agents are reading your docs more than humans are, wiring up services, spinning up sub-agents, and digging through logs at 3am while you snooze. They don't need a dashboard. They don't have eyes. This talk is about designing for that user: skills generated from your docs, clipboard payloads agents can act on, and error messages that tell them exactly what to fix. Your role is shifting from operator to architect. Come find out what that looks like. People - [Dave Kiss](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#dave-kiss) — Mux / Sr. Community Engineering Lead Notes - Tweet ideas - Questions / follow-ups - ## 2:25 PM — Kill Your Retrieval Pipeline: Agentic Memory Is the New State of the Art The retrieval pipeline is the default architecture for AI memory: embed, index, search, rerank, hope the right context makes it through. It's also a dead end. The next paradigm for AI memory is agentic. Instead of building elaborate infrastructure to compensate for what models can't do, let the model do the work. This talk covers how this approach produced a new state of the art on the most widely used long-term memory benchmark in conversational AI, why the field got stuck building workarounds, what it looks like when you stop, and where AI memory is actually heading. People - [Alvin Pane](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#alvin-pane) — OutRival / Engineering Lead Notes - Tweet ideas - Questions / follow-ups - ## 2:50 PM — Skills Issues There is an enormous difference in quality and efficiency of outcomes when building or using agentic systems. We've talked about context engineering, competing standards and protocols, waves of interfaces and harnesses being 'dead' with another wave of similar shapes and techniques temporarily taking the hyped limelight...but what's missing in all these conversations is a common, clear-headed, unhyped set of intuitions and expectations we all can rely on to build great agentic things. To enjoy the new good old-fashioned engineering. People - [Erik Thorelli](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#erik-thorelli) — CodeRabbit / Head of DX Notes - Tweet ideas - Questions / follow-ups - ## 3:15 PM — Afternoon Break Program / transition block. Notes - Tweet ideas - Questions / follow-ups - ## 3:45 PM — Using OSS models to build AI apps with millions of users In this talk, Hassan will go over how he builds open source AI apps that get millions of users like roomGPT.io (2.9 million users), restorePhotos.io (1.1 million users), Blinkshot.io (1 million visitors), and LlamaCoder.io (1.4 million visitors). He'll go over his journey in AI, demo some of the apps that he's built, and dig into his tech stack and code to explain how he builds these apps from scratch. He’ll also go over how to market them and go over his top tips and tricks for building great full-stack AI applications quickly and efficiently. This talk will start from first principles and give you a glimpse into Hassan’s workflow of idea -> working app -> many users. Attendees should come out of this session equipped with the resources to build impressive AI applications and understand some of the behind the scenes of how they’re built and marketed. This will hopefully serve as an educational and inspirational talk that encourages builders to go build cool things. People - [Hassan El Mghari](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#hassan-el-mghari) — Together AI / Director of Developer Experience Notes - Tweet ideas - Questions / follow-ups - ## 4:10 PM — The Multi-Model Future is Open Source There are more great AI models than ever, and the best one changes every few weeks. But most AI coding tools were built to lock you into a single provider. In this talk, I will share what we're seeing over the thousands of enterprise conversations and their shift toward efficiency and control. The winners will be the tools that give developers the freedom to choose. Multi-model and open source aren't features. They're the foundation of what comes next. People - [Stefan Avram](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#stefan-avram) — OpenCode / Head of Business Notes - Tweet ideas - Questions / follow-ups - ## 4:35 PM — MCP vs. Command Line: A Head-to-Head Evaluation of Agent Tool Integration Patterns As AI agents become increasingly capable, a critical architectural question emerges: how should we give them access to tools and capabilities? Two competing patterns have gained traction—Model Context Protocol (MCP), which enables dynamic, runtime tool discovery and execution, and the command line, including skill files, which embed structured instructions and best practices directly into the agent's context. But which approach actually produces better outcomes? In this talk, I'll present results from a rigorous evaluation comparing agent performance across both paradigms. I'll show how each approach affects task completion rates and output quality across document generation, data analysis, and multi-step workflows. People - [Laurie Voss](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#laurie-voss) — Arize AI / AI Engineer / Head of Devrel Notes - Tweet ideas - Questions / follow-ups - ## 5:00 PM — IDEs are dead. Long live IDEs We've been hearing a lot about how IDEs are dying. But, are they really dead? My view is that the definition of what an IDE is will change. There are still essential IDE-like features which are necessary for productive software engineers to do their job, but there are also a million other things which are not required anymore. I'll go through some fun examples from my experience at Cursor, and show you some of our explorations for the future of the IDE interface. People - [David Gomes](https://pancake.thefocus.ai/ai-engineer-miami/speakers.html#david-gomes) — Cursor / Software Engineer Notes - Tweet ideas - Questions / follow-ups - ## 7:00 PM — Afterparty Program / transition block. Notes - Tweet ideas - Questions / follow-ups - ## End-of-day capture ### Biggest ideas - ### People to follow up with - ### Tweet thread ideas -