Uploaded June 2026 | Updated November 2026, 1 minute ago
[2026 - DAY 2 - CODING AGENTS] Most AI coding agents top out at short, interactive sessions - a few minutes of back-and-forth before context degrades. At Factory, we built a system that sustains autonomous software development for hours, days, and even weeks. An orchestrator decomposes large projects into features, spawns focused workers with clean context, coordinates through git, and validates at every milestone. This talk covers the architecture behind multi-day agentic workloads: managing context limits, multi-model orchestration, balancing serial reliability with parallel speed. We also share production data on what actually changes when agents shift from 8-minute conversations to 16-day autonomous runs.
SPEAKER:
Eno Reyes - CTO, Factory
👉 Sign up for our "No BS" Newsletter to get the latest technical data & AI content: aicouncil.com/newsletter
ABOUT AI COUNCIL:
AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools.
FIND US:
Website: aicouncil.com
LinkedIn: linkedin.com/company/aicouncilconf
X: https://x.com/aicouncilconf
[2026 - DAY 2 - CODING AGENTS] Most AI coding agents top out at short, interactive sessions - a few minutes of back-and-forth before context degrades. At Factory, we built a system that sustains autonomous software development for hours, days, and even weeks. An orchestrator decomposes large projects into features, spawns focused workers with clean context, coordinates through git, and validates at every milestone. This talk covers the architecture behind multi-day agentic workloads: managing context limits, multi-model orchestration, balancing serial reliability with parallel speed. We also share production data on what actually changes when agents shift from 8-minute conversations to 16-day autonomous runs.
SPEAKER:
Eno Reyes - CTO, Factory
👉 Sign up for our "No BS" Newsletter to get the latest technical data & AI content: aicouncil.com/newsletter
ABOUT AI COUNCIL:
AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools.
FIND US:
Website: aicouncil.com
LinkedIn: linkedin.com/company/aicouncilconf
X: https://x.com/aicouncilconf
![What It Takes to Build Reliable AI Systems for Production Operations | Resolve AI
[2026 - DAY 3 - APPLIED AI] As AI systems move from assisting engineers to taking action across production workflows, the technical bar rises fast. Real-world environments are noisy, fragmented, and high-stakes, making reliability, context, and control core design problems rather than afterthoughts.
In this talk, Steven Karis, Chief Architect at Resolve AI, will share practical lessons from building AI systems that operate across incidents, debugging, and daily production operations. He will cover the architectural patterns required to make these systems useful in practice, including context aggregation across fragmented tools, coordinated reasoning and planning, and enforcement of safe action boundaries in complex environments. The session will also explore a broader industry shift: engineers are moving from being direct operators to supervisors who define policy, review decisions, and manage exceptions. The goal is not just to make AI more capable, but to make it dependable for engineers to collaborate with and delegate to.
SPEAKER:
Steven Karis - Chief Architect, Resolve AI
👉 Sign up for our No BS Newsletter to get the latest technical data & AI content: https://aicouncil.com/newsletter
ABOUT AI COUNCIL:
AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools.
FIND US:
Website: https://aicouncil.com/
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
X: https://x.com/aicouncilconf What It Takes to Build Reliable AI Systems for Production Operations | Resolve AI](https://i.ytimg.com/vi/USe4fZk1mag/mqdefault.jpg)
![Welcome to Our Data Benchmark, Where Everythings Made Up and the Points Dont Matter
[2026 - DAY 2 - ANALYTICS & DATA SCI] SPIDER, DSBench, and every other analytics benchmark treat data work like a pub quiz: heres a question, heres the answer, did you match? But real analytics is arguing about whether revenue means bookings or collections, discovering that Stripe amounts are in cents while your platform stores dollars, and figuring out why the numbers dont tie to last quarters deck. Current benchmarks cant express any of that—they just check if you got 47.3. Worse: smarter models keep making the same mistakes. Opus is clearly more intelligent than Sonnet, but it falls into the same traps—path of least resistance, accepts the first answer, doesnt ask clarifying questions. Well show specific examples where industry standard benchmarks fail (including our own) and share some ideas for evals that test what analysts actually do: learn a messy warehouse over time, not answer a frozen question on day zero.
SPEAKER:
Izzy Miller - AI Engineer & AI Research Lead, Hex
👉 Sign up for our No BS Newsletter to get the latest technical data & AI content: https://aicouncil.com/newsletter
ABOUT AI COUNCIL:
AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools.
FIND US:
Website: https://aicouncil.com/
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
X: https://x.com/aicouncilconf Welcome to Our Data Benchmark, Where Everythings Made Up and the Points Dont Matter](https://i.ytimg.com/vi/UwqyN-6tPKo/mqdefault.jpg)
![Optimizing Iceberg Table Layouts at Scale A Multi Objective Approach
[2025 - Day 1 - Data Eng & Infra] Sumedh Sakdeo and Jesus Camacho Rodríguez share insights from managing data layout for 100K+ Iceberg tables, exploring automated reorganization as a multi-objective optimization problem. This talk offers valuable perspectives on balancing storage efficiency, minimizing costs, and maximizing impact through intelligent table scoring and ranking within reorganization budgets, particularly valuable for engineers scaling table management or optimizing query performance.
ABOUT THE SPEAKERS:
Sumedh Sakdeo, Senior Staff Engineer, LinkedIn
Jesus Camacho Rodríguez, Principal Engineering Manager, Microsoft Grey Systems -
🎟️ GET YOUR TICKET TO AI COUNCIL 2026 🎟️
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
→ https://aicouncil.com/sf-2026
⚡ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Optimizing Iceberg Table Layouts at Scale A Multi Objective Approach](https://i.ytimg.com/vi/V2uG0PYGqHU/mqdefault.jpg)
![Legal Agency: Building Domain Specific Agents for Enterprise
[2025 - Day 3 - GenAI Applications] Niko Grupen shares insights from building agents for real-world knowledge work, exploring the delicate balance of AI and Human-Computer Interaction required for vertical problem spaces like law. Whether youre developing domain-specific agents or creating frameworks that mirror human processes, this talk offers valuable perspectives on leveraging domain expertise, mapping model problems to real-world challenges, and maximizing quality in production environments.
ABOUT THE SPEAKER:
Niko Grupen, Head of Applied Research, Harvey -
🎟️ GET YOUR TICKET TO AI COUNCIL 2026 🎟️
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
→ https://aicouncil.com/sf-2026
⚡ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Legal Agency: Building Domain Specific Agents for Enterprise](https://i.ytimg.com/vi/VKDjQnwpI6E/mqdefault.jpg)
![OpenAI’s Responses API: A New Foundation for Building with Models & Tools
[2025 - Day 2 - Foundation Models] Nikunj Handa shares insights from building OpenAIs Responses API, exploring how this programmatic agent API radically simplifies integration by transforming hundreds of lines of code into just a few. This talk offers valuable perspectives on the design decisions and engineering challenges behind creating an API uniquely engineered for agent-like use cases with built-in state management and semantic streaming, particularly relevant for developers building AI applications or integrating advanced reasoning capabilities.
ABOUT THE SPEAKER:
Nikunj Handa, Product Lead, OpenAI -
🎟️ GET YOUR TICKET TO AI COUNCIL 2026 🎟️
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
→ https://aicouncil.com/sf-2026
⚡ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ OpenAI’s Responses API: A New Foundation for Building with Models & Tools](https://i.ytimg.com/vi/Vb1bf3bFJFI/mqdefault.jpg)

![From Prediction to Uplift: Causal Modeling for Better Decisions | Intuit
[2026 - DAY 2 - ANALYTICS & DATA SCI] Most AI/ML systems in production rely on predictive models. Businesses score users for churn risk, conversion likelihood, or click probability, and then make decisions based on those scores. But accurate predictions do not imply better decisions. A model that answers the question “Who will convert anyway?” very well is often a terrible guide for deciding who to target with an offer, notification, or intervention. More often than not, what we really care about is answering the question “Whose behavior will actually change because of our intervention?” rather than “Who will do X?”.
This gap between prediction and decision-making shows up in more and more places, such as marketing campaigns, product experiments, and even healthcare and risk interventions. Uplift modeling is a way to bridge this gap by estimating the causal effect of an intervention at the individual level—who is persuadable, who is a sure thing, who is a lost cause, and who might even be harmed or annoyed if we intervene. At Intuit, we use uplift modeling to enhance targeting and experimentation, helping us allocate marketing and product interventions more effectively across millions of customers.
In this talk, I will introduce uplift modeling as a practical form of causal AI that fits into existing experimentation and ML workflows. I will start by contrasting predictive and causal thinking, followed by core concepts like treatment effects and counterfactuals, using concrete examples. After that, I will dive into uplift modeling techniques, specifically using meta-learners in Python. Finally, we will go over evaluation techniques that are unique to uplift modeling and causal inference, and how they differ from standard ML metrics like F1 score or AUC.
This talk is aimed at data scientists and ML engineers at any level, including those with no background in causal inference. Basic familiarity with Python and machine learning concepts is helpful but not required. Attendees will leave with a clear mental model of when predictive models are not enough, an intuitive understanding of uplift modeling and its causal foundations, and a sense of how to start applying uplift models in their own AI/ML systems to target the right people.
SPEAKER:
Avik Basu - Staff Data Scientist, Intuit
👉 Sign up for our No BS Newsletter to get the latest technical data & AI content: https://aicouncil.com/newsletter
ABOUT AI COUNCIL:
AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools.
FIND US:
Website: https://aicouncil.com/
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
X: https://x.com/aicouncilconf From Prediction to Uplift: Causal Modeling for Better Decisions | Intuit](https://i.ytimg.com/vi/VrwJqbysoUU/mqdefault.jpg)
![The World Is Not Enough: RL’s Environment Problem
[2026 - Day 1 - KEYNOTE] While researchers may still opine about access to compute, most are hitting a new bottleneck: access to high-quality environments in which to post-train agents. Expanding agent capabilities will depend on how we curate and utilize data, much of which exists only in the minds of human experts today. This panel will explore the challenge of building environments, including the need to improve infrastructure reliability, the obstacles posed by subjective domains, and the challenge of achieving high variety. We’ll also discuss future opportunities, such as environments for long-horizon reasoning and continual learning, and what it will take to evolve environment design from a bespoke craft into a more automated, scalable discipline that consistently drives generalization.
PANELISTS:
Nic Ouporov - Co-founder & CEO, Fleet
Vincent Weisser - Co-founder & CEO, Prime Intellect
Thais Castello Branco - Founder & CEO, Taste
Sarah Catanzaro - General Partner, Amplify Partners (Moderator)
👉 Sign up for our No BS Newsletter to get the latest technical data & AI content: https://aicouncil.com/newsletter
ABOUT AI COUNCIL:
AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools.
FIND US:
Website: https://aicouncil.com/
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
X: https://x.com/aicouncilconf The World Is Not Enough: RL’s Environment Problem](https://i.ytimg.com/vi/WDDwOsY9rw8/mqdefault.jpg)
![OAKS: Open Agentic Knowledge Stack
[2025 - Day 3 - Lightning Talks] Alexy Khrabrov shares insights from the Open Agentic AI Knowledge Stack (OAKS), exploring how Knowledge Graphs power GraphRAG and bridge enterprise AI adoption with startup innovation around structured knowledge. This talk offers valuable perspectives on organizing domain knowledge for Small Specialized Models and Domain Expert Agents, particularly relevant for teams working on structured AI architectures with graph-based agentic workflows and scalable message passing frameworks.
ABOUT THE SPEAKER:
Alexy Khrabrov, AI/ML Community Architect, Neo4j -
🎟️ GET YOUR TICKET TO AI COUNCIL 2026 🎟️
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
→ https://aicouncil.com/sf-2026
⚡ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ OAKS: Open Agentic Knowledge Stack](https://i.ytimg.com/vi/WgZA1FHSuLA/mqdefault.jpg)
![Breaking the Proof-of-Concept Cycle: Stop Prototyping and Get Into Production | GitLab
[2026 - DAY 3 - APPLIED AI] Most organizations are experimenting with AI at work. Proof of concepts are thriving in small-scale silos, but how can you scale those wins across an enterprise? This talk discusses the symptoms that trap teams in the cycle of perpetual prototyping and provides a practical framework for breaking through common technical, organizational, and cultural barriers to scale. Learn how to plan for production from day one and turn your AI experiments into solutions that stick.
SPEAKER:
Naheil McAvinue - Director, Enterprise Analytics & Data Science, Gitlab
👉 Sign up for our No BS Newsletter to get the latest technical data & AI content: https://aicouncil.com/newsletter
ABOUT AI COUNCIL:
AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools.
FIND US:
Website: https://aicouncil.com/
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
X: https://x.com/aicouncilconf Breaking the Proof-of-Concept Cycle: Stop Prototyping and Get Into Production | GitLab](https://i.ytimg.com/vi/Wkpt2MDCaxI/mqdefault.jpg)
![Build Trustworthy LLM Apps Powered by Agentic Evals | Meta
[2026 - DAY 3 - LIGHTNING TALK] Agentic AI has certainly secured mindspace of industry. As more & more people continue to play with LLMs, they begin developing an intuition aka vibes around whether LLM is performing the task at hand well or not. While usecases like math problem, classification are easier to verify; generative content creation etc are not. Adding agents to the mix makes things lot more complex. This talk will highlight the particular challenges one may face as they continue their journey towards productionizing their Agentic application: outputs are non deterministic, ground truth is hard to find, and what used to work before no longer does. Yet LGTM isnt a deployment strategy.
While typical LLM chatbot can be seen as a more sophisticated Google search, were beginning to expect more from Agents: Dont just give an answer but actually perform the task. Security, bias, privacy etc suddenly become non-negotiable. Only after we handle these complexities, we can unblock real usecases in healthcare, finance, legal etc.
This talk tackles why agent evaluation is fundamentally harder than traditional ML testing: multi-step reasoning chains, tool use side effects & more. How to build evaluation datasets that actually reflect production scenarios, not just cherry-picked examples. Well cover automated evaluation pipelines using LLM-as-judge patterns, and when you can not avoid human in the loop. The session addresses detecting regressions before users do: setting up continuous evaluation that catches model degradation. Tricky cases when agent aces public evals but fails in production, and how to build evaluations that predict real-world performance.
SPEAKER:
Rushabh Mehta - Tech Lead, Meta
👉 Sign up for our No BS Newsletter to get the latest technical data & AI content: https://aicouncil.com/newsletter
ABOUT AI COUNCIL:
AI Council brings together the brightest minds in data to share industry knowledge, technical architectures and best practices in building cutting edge data & AI systems and tools.
FIND US:
Website: https://aicouncil.com/
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
X: https://x.com/aicouncilconf Build Trustworthy LLM Apps Powered by Agentic Evals | Meta](https://i.ytimg.com/vi/XZwbeuwZxSk/mqdefault.jpg)