Optimized AI Conference 2026
2026-03-30..2026-03-31
Atlanta, United States
[Optimized AI Conference 2025, Optimized AI Conference 2026]
| title | author | length |
|---|---|---|
| Context Engineering with Redis and LangChain | Robert Eshelton, Ricardo Ferrei | 52m |
Claims concrete outcomes: a Jupyter lab with an OpenAI key that runs a LangChain/RAG baseline, a Redis for vector search backing both JSON/hash records and… | ||
| Mastering Agentic Coding and GPUs | Anton Alexander | 01h 53m |
Shows an agentic coding platform that rewrote CUDA kernels for EFA networking to adapt Deepseek/DP-style kernels originally built for Infiniband, and reports a… | ||
| Multi Agent Architecture using ADK | Hamza Farooq | 01h 09m |
A clonable ADK codebase demonstrates a working multi‑agent agent-to-agent protocol that wires a judge agent and SQL agent with a masking layer, observability… | ||
| Optimizing LLM Training and Inference Performance on GPUs | Faradawn Yang | 01h 18m |
Workshop shows hands on use of H100 GPUs with Docker and redeemable H100 credits ($30 for ~1.5h) and demonstrates concrete wins: tensor cores cut 64 scalar… | ||
| Optimizing Retrieval for Agentic Systems | Trey Grainger | 01h 30m |
Workshop claims that retrieval moves past naive RAG into agentic search / self-RAG with LLM-driven query formulation and tool selection, demonstrates code labs… | ||
| Deploying Physics Models at the Edge: Quantized AI for Weather & Fluid Simulation | Lennon Shikhman | 11m |
Claim: neural PDE solvers replace iterative numerical methods and run on a palm‑sized Dell Pro Max after pruning and quantization, delivering about one… | ||
| Why Marketing Automation Fails — And How to Fix It | Joshua Cazoe | 17m |
Claims a YouTube creator scales from 30,000 to 250,000 subscribers in one year using Claude and HeyGen clones and Eleven Labs for voice, reports 58–78% of SMBs… | ||
| Building AI Agents | Jared Rhodes, Lamar Rhodes | 18m |
The project builds a custom World of Warcraft server and a dockerized background client that emulates packets and object state so tens to 3,000+ autonomous… | ||
| Mastering Claude Code for Data Professionals | Dawn Choo | 18m |
Claims Claude Code excels for data work but still makes systematic mistakes and tends toward average answers; recommendations come from interviews showing… | ||
| AI-Powered Personalized Discovery with Graph Search and VLM-Enhanced Embeddings | Brianna Lynn King, Hsin-Yi Lin, Anwaar Msehli, Yasel Garces | 22m |
Furniture.com describes a deployed discovery stack: a fine-tuned semantic search hosted on Databricks with VLM-enhanced embeddings that synthesize image and… | ||
| From localhost to Real World: Engineering Production-Ready Agentic Systems | Victor Calderon | 18m |
Concrete claim: a production agent pipeline that scales to 300,000 users per hour with retry, timeout and guardrail patterns implemented. The demo repo wires a… | ||
| From Data to Decisions: Turning Enterprise AI into Real Business Outcomes | Beverly Wright | 24m |
Claim: Gartner finds 5% of projects deliver value despite million‑dollar bets and promised 20x ROI. Root causes are concrete: misdefined problems (the… | ||
| Crafting an Enterprise‑Scale Agent Mesh | Stanislav Stolpovskiy | 17m |
An enterprise agent mesh is a working platform not a paper design: Grid Dynamics reports a production system used daily that started bottom‑up with agents for… | ||
| Disaggregated Intelligence: Scaling AI Agents with Dynamo and Kubernetes | Avinash Ahuja, Vivek Kolasani | 19m |
Evolution from stateless LLMs to tool-augmented agents, memory and session-heavy workflows, and a concrete deployment path: Open Claw plus NeMo Tron Ultra… | ||
| Building Production-Ready AI Agents | Darko Mesaroš | 29m |
Strands is an open source framework for production agents that runs on Python or TypeScript and is model-agnostic. Live coding shows an agent spun up with a… | ||
| Designing Fast & Cost-Efficient Agents: The Power of Caching | Jen Honey Jain Agarwal | 30m |
Claims that straightforward caching cuts LLM agent cost and latency while preserving capability and shows concrete results: a cited $6.80 per complex agent… | ||
| From Copy-Paste to Composition: Building Agents Like Real Software | Jake Mannix | 29m |
Claims that agent runtimes need an adaptation layer not another giant prompt and demonstrates a working virtual tools layer that intercepts MCP tool lists via… | ||
| Evaluating LLMs under Concept Drift in Production | Manisha Arora, Siddharth Ranganathan | 33m |
Claims a new metric called the drift responsiveness score that flags concept drift early by taking the ratio of model performance on a recent “drift” set to a… | ||
| Human above AI | Savneet Singh | 20m |
Argues humans must stay in control as AI adoption jumps from 44% to 55% in one year (a 10% increase) and agent systems start making choices like booking… | ||
| Rethinking CI & CD for Agentic Workflows | Shibashis Mishra | 19m |
AI code generation is overwhelming traditional CI/CD and software supply chains: Adobe observes 55% growth in CI volume in one quarter as non-developer… | ||
| Devcontainers for AI/ML Workflow Optimization | Steven Citron Pousty | 25m |
Claims reproducible AI/ML environments across AMD and NVIDIA hardware by using dev containers and an open dev container template checked into Git. Demo uses… | ||
| Building Reliable Browser-Use Agents for Storefront Optimization | Yuanzheng Zhu | 15m |
Autonomous browser agents shop real Shopify storefronts at scale, using a perceive plan execute update loop and four engineering pillars: episodic memory… | ||
| Agentic Systems: Leadership, Risk, and Accountability | Joshua S, Paige Bailey, Kamelia Aryafar, Khalifeh Al-Jadda | 27m |
Panelists claim real agentic systems act autonomously rather than just chat back and forth and show concrete setups: fleets of agents running 24/7 using… | ||
| Building the Agentic Enterprise: Turning Data into Autonomous Business Systems | Joshua Sutton | 30m |
Claims a reproducible agentic protocol that raises AI-facing time from single digits to 50%+ AFT at scale for hundreds to 160,000 users, with a measurable… | ||
| Beyond Orchestration: An Open Source Architecture for Agentic Systems | Ashok Prakash | 25m |
Concrete reference architecture for open-source agent systems that claims to close the demo-to-production gap: durable agent controller with checkpointing and… | ||
| How companies are adapting AI Agents in their Ecosystem | Jen Honey Jain Agarwal, Christopher Reckord, Mustafa Nisar, Daniel Beecham, Hamza Farooq | 32m |
Home Depot describes a deployed assistant called Magic Apron that answers compatibility and delivery‑risk questions and uses weather signals to reroute… | ||
| Inside AI: What Every Professional Needs to Know to Stay Relevant, Protected, and Ahead | Jess Ramos | 30m |
LinkedIn rolls out an opt-out policy that feeds user posts and metadata into training data while email platforms and social apps embed AI features like… | ||
| Rebuilding the AI Platform: Designing for Today’s Chaos and Tomorrow’s Unknowns | Sura Elamurugu | 32m |
Netflix is rebuilding its AI platform to serve half a billion users in 190 countries and claims a single system can handle classical ML, LLMs, foundational… | ||
| Agents Don’t Ship Themselves | Darko Mesaroš | 15m |
Claims that demos won’t run themselves, backed by an early Rust agentic coding system built on Amazon Bedrock that mostly worked but felt like “sticks and… | ||
| Understanding Context Engineering for Agentic Systems | Robert Shelton | 15m |
Practical framework that names tools and outcomes: uses Redis Specter with LangChain and LangGraph integrations, contrasts a simple RAG pipeline against a… | ||
| New Renaissance of Building | Paige Bailey | 33m |
Demonstrates concrete claims and tools: builds and deploys a working web app in under five minutes using AI Studio with Firebase and Google OAuth and deploys… | ||
| Building Generative Content Understanding Systems | Mike Tamir | 29m |
A deployed generative recommender called Tubi FM generative recommender uses LLM base models, direct token injections, semantic IDs via RQ-VAE, and nightly… | ||
| Scalable GenAI in Production | Kamelia Aryafar | 24m |
Concrete claims and concrete build details: a working Netflix generative search beta and a deployed Gemini Enterprise demo that connects Drive SharePoint and… | ||
| Welcome To The Era Of Claws | Carter Abdallah | 28m |
Claims that agentic tools like Claude Code and OpenClaw are already changing workflows with concrete results: OpenClaw becomes the most-starred GitHub project… | ||
| nothing matches | ||