Uploaded May 2025 | Updated September 2026, 2 weeks ago
[2025 - Day 3 - GenAI Applications] Ethan Brown shares insights from building an LLM-powered data analytics bot at Amazon IVS/Twitch Video, exploring how to augment data operations through Slack integration and familiar chat interfaces. Whether you're automating data workflows or building internal AI tools, this practical walkthrough offers valuable perspectives on implementing SQL query generation, chat summarization, and account lookups using standard AWS services.
ABOUT THE SPEAKER:
Ethan Brown, Data & Applied Science Director, Twitch / AWS -
🎟️ GET YOUR TICKET TO AI COUNCIL 2026 🎟️
Meet the world's top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
→ aicouncil.com/sf-2026
⚡ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: linkedin.com/company/aicouncilconf
Website: aicouncil.com
[2025 - Day 3 - GenAI Applications] Ethan Brown shares insights from building an LLM-powered data analytics bot at Amazon IVS/Twitch Video, exploring how to augment data operations through Slack integration and familiar chat interfaces. Whether you're automating data workflows or building internal AI tools, this practical walkthrough offers valuable perspectives on implementing SQL query generation, chat summarization, and account lookups using standard AWS services.
ABOUT THE SPEAKER:
Ethan Brown, Data & Applied Science Director, Twitch / AWS -
🎟️ GET YOUR TICKET TO AI COUNCIL 2026 🎟️
Meet the world's top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
→ aicouncil.com/sf-2026
⚡ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: linkedin.com/company/aicouncilconf
Website: aicouncil.com
![Unbundling of the Cloud Data Warehouse
[2025 - Day 3 - Databases] Tanya Bragin shares insights from the transformation of the modern data stack, exploring how open-source technologies and data lake standards are providing alternatives to proprietary cloud data warehouses. This session offers valuable perspectives on leveraging platforms like ClickHouse and Iceberg to enable more flexible, cost-effective, and diverse data workflows, particularly relevant for teams dealing with performance bottlenecks or vendor lock-in challenges.
ABOUT THE SPEAKER:
Tanya Bragin, VP Product, ClickHouse -
🎟️ 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/ Unbundling of the Cloud Data Warehouse](https://i.ytimg.com/vi/9wo4ZYge23k/mqdefault.jpg)
![From Postgres to ClickHouse and Back: Building a Unified OLTP + OLAP Database for AI Workloads
[2026 - DAY 1 - DATA ENG & DATABASES] Databases are starting to look a lot less “either OLTP or OLAP” and a lot more “both, at once”. Data volumes are growing faster than most application architectures were designed for, and teams are being pushed to adopt OLAP systems earlier in their lifecycle. At the same time, AI-driven products are creating new workloads that need low-latency transactional behavior and high-throughput analytics together. The result is a clear trend: OLTP and OLAP are converging, and the idea of a unified database stack is becoming practical.
Working on ClickHouse’s managed Postgres effort, I have a front-row seat to this shift. Before ClickHouse, I co-founded PeerDB, where we saw data movement from Postgres to ClickHouse accelerate by orders of magnitude over the last couple of years, and it is still growing. That growth is not just about ETL, it signals what users actually want: transactional simplicity with analytics-grade performance, without stitching together a dozen systems.
In this talk, I will explain the pattern we are seeing, why it is accelerating now, and what it implies for the next generation of database platforms. I will then walk through the approach ClickHouse is taking, including managed Postgres, tighter Postgres and ClickHouse integration, and new primitives like pg_clickhouse and pg_stat_ch. We will also cover the replication story (including new “logical replication v2” style ideas), and the set of levers required to get closer to sub-second freshness and low operational overhead.
Finally, I will zoom out to the bigger picture: a unified database is not just “Postgres + OLAP”. It requires re-architecting parts of the stack so applications do not have to carry the abstraction burden. I will share what “world-class” looks like here, the remaining technical challenges, and a realistic path to making unified OLTP + OLAP the default for fast-growing AI workloads.
SPEAKER:
Kaushik Iska - Engineering Lead, Managed Postgres, ClickHouse
👉 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 Postgres to ClickHouse and Back: Building a Unified OLTP + OLAP Database for AI Workloads](https://i.ytimg.com/vi/A2M6gWYBuYU/mqdefault.jpg)
![AI Launchpad 2025: Guilde
[2025 - Day 1 - AI Launchpad] Schuyler Brown and John Tokash share insights from Guildes platform that provides instant awareness of data models, load, and dependencies, exploring how to eliminate knowledge silos accidentally created by specialized DevOps and security teams. For organizations struggling with disconnected application developers and database operations, this session offers valuable perspectives on arming everyone with technical tribal knowledge to reduce bugs, latency, and incidents, especially critical as AI code generation amplifies these challenges.
ABOUT THE SPEAKERS:
Schuyler Brown, Co-Founder, Guilde
John Tokash, CTO, Guilde -
🎟️ 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/ AI Launchpad 2025: Guilde](https://i.ytimg.com/vi/A3ngyDReuh0/mqdefault.jpg)
![Scalable Continuous Monitoring for Large scale A/B Experimentation
[2025 - Day 1 - Data Science & Algos] Chenyu Qiu shares insights from building Ubers end-to-end continuous experiment monitoring platform, exploring how to overcome peeking problems and detect performance degradation across thousands of A/B experiments. This talk offers valuable perspectives on anytime-valid inference, eliminating noise while preserving true signals, and accelerating data-driven decisions at scale, crucial for teams scaling experimentation or implementing regression-adjusted estimators.
ABOUT THE SPEAKER:
Chenyu Qiu, Staff Scientist, Uber -
🎟️ 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/ Scalable Continuous Monitoring for Large scale A/B Experimentation](https://i.ytimg.com/vi/ADaPkGbpp7Y/mqdefault.jpg)
![Trimming the Long Tail of Production Model Ownership at Hinge
[2025 - Day 2 - MLOps & Platforms] Jonathan Jin shares insights from approaching model serving as a long-term ownership problem at Hinge, exploring how focusing on the long tail of model ownership creates sustainable AI platforms. Whether youre building model serving infrastructure or tackling observability challenges, this talk offers valuable perspectives on creating a golden path that empowers AI teams to innovate and scale their modeling investments without operational drag.
ABOUT THE SPEAKER:
Jonathan Jin, Staff Machine Learning Engineer, Hinge -
🎟️ 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/ Trimming the Long Tail of Production Model Ownership at Hinge](https://i.ytimg.com/vi/AaEMUlmKO4s/mqdefault.jpg)
![Agents Break Data Security — And Heres What You Do About It | Skyflow
[2026 - DAY 1 - WORKSHOP] AI Engineering teams are trying to secure AI systems built from components that didnt exist a year ago: agents, tools, memory, context graphs, orchestration frameworks. Traditional security wasnt built for any of this.
Here are 3 things practitioners are getting wrong right now:
- Agents are the new microservices
- Memory is where sensitive data goes to retire
- Your AI supply chain just got bigger than your software supply chain.
This session covers real architectures, real failure modes, and what runtime data control actually needs to look like when agents are making access decisions you never anticipated.
SPEAKER:
Amruta Moktali - Chief Product Officer, Skyflow
👉 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 Agents Break Data Security — And Heres What You Do About It | Skyflow](https://i.ytimg.com/vi/Abh6CW0jvLQ/mqdefault.jpg)
![Context Engineering 2.0: Unifying MCP, Agentic RAG, and Memory | Redis
[2026 - DAY 2 - AI ENGINEERING] As AI systems move from single-shot chatbots to long-running, autonomous agents, the biggest bottleneck is no longer model capability—it’s context. Most production failures today stem from agents having the wrong information, at the wrong time, in the wrong shape. Prompt engineering and basic RAG pipelines were enough for early demos, but they collapse under real-world requirements like state, memory, structured data access, and safety.
This talk introduces Context Engineering 2.0: a systems-level approach to building agentic AI where context is treated as first-class infrastructure. We’ll explore why traditional RAG is insufficient on its own, why text-to-SQL and naive tool calling are brittle (and often dangerous), and why REST-style APIs are a poor abstraction for agent reasoning. From there, we’ll examine three foundational pillars for modern agent systems: agentic RAG (retrieval that adapts to an agent’s plan), memory (short- and long-term, searchable and governed), and MCP-style semantic access layers that allow agents to safely explore and reason over structured data.
The core argument is simple but consequential: scalable agentic systems require a context engine—a unified layer that dynamically assembles state, memory, structured and unstructured data, and constraints into the model’s working context. Attendees will leave with a clearer mental model for designing agent architectures that are more reliable, extensible, and aligned with how reasoning systems actually work—independent of any specific framework or vendor.
SPEAKER:
Simba Khadder - Head of Context Engine, Redis & Founder of Featureform
👉 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 Context Engineering 2.0: Unifying MCP, Agentic RAG, and Memory | Redis](https://i.ytimg.com/vi/AhKFNkgl760/mqdefault.jpg)
![Beyond the API: Modern Inference for Modern Workloads
[2026 - Day 2 - KEYNOTE] Practitioners from the companies at the frontier of inference and model development sit down to unpack what application developers need to understand right now: why fine-tuning is quietly resurging under the name RL, how smart teams are compressing inference costs by shaping smaller specialized models, who owns the model routing problem, and why inference capacity is structurally behind demand — possibly for years.
PANELISTS:
Tuomas Rintamaki - Research Scientist, NVIDIA
Charles Zedlewski - Chief Product Officer, Together AI
Charles Frye - Member of Technical Staff, Modal
Bryan Bischof - Head of AI, Theory Ventures (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 Beyond the API: Modern Inference for Modern Workloads](https://i.ytimg.com/vi/B3axq9qPOVw/mqdefault.jpg)
![A SQL Based Metrics Layer for DuckDB and ClickHouse
[2025 - Day 2 - Analytics & BI] Mike Driscoll shares insights from building Rills SQL-based metrics layer using DuckDB, exploring how to aggregate raw data into summarized metrics and enable dimensional slicing through declarative SQL expressions. This talk offers valuable perspectives on implementing fast OLAP engines for real-time data access with sub-second response times, essential for analytics teams seeking to define metrics using familiar SQL dialect as part of a BI-as-code philosophy.
ABOUT THE SPEAKER:
Mike Driscoll, Co-Founder & CEO, Rill Data -
🎟️ 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/ A SQL Based Metrics Layer for DuckDB and ClickHouse](https://i.ytimg.com/vi/B5jPz4xqQLg/mqdefault.jpg)

![How a Netflix Side Project Became the Universal Standard for Data Tables
[2025 - Day 1 - Data Eng & Infra] Ryan Blue shares insights from creating Apache Iceberg, exploring its origins at Netflix and evolution into a universal table format thats transforming the analytic database industry. This primer from Icebergs original creator offers valuable guidance on how these technologies are changing modern analytics and why theyre more relevant than ever today, making it essential viewing for anyone working with open table formats or building data lake architectures.
ABOUT THE SPEAKER:
Ryan Blue, Apache Iceberg Creator, Technical Staff, Databricks
🎟️ 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/ How a Netflix Side Project Became the Universal Standard for Data Tables](https://i.ytimg.com/vi/BTwVhkQcg7g/mqdefault.jpg)