Uploaded June 2026 | Updated November 2026, 17 hours ago
[2026 - DAY 1 - AGENT INFRASTRUCTURE] Most AI agents work in demos. Few survive in production. LLMs are stateless. Infrastructure fails. Context windows reset. Real-world objectives span hours or days. Building long-running autonomous agents requires durability engineered across the entire system.
This talk compares and contrasts dominant approaches to durability for agents and presents three pillars of durable agentic systems.
1. Durable Execution
Agents must survive crashes, retries, and partial task completion. Durable execution engines like Temporal persist workflow state and enable deterministic replay. Graph-based orchestrators such as LangGraph model control flow as explicit state machines. These approaches reflect different assumptions about recovery, replayability, and operational resilience, and directly shape how agents behave under failure.
2. Durable Autonomy
Autonomous systems inevitably encounter ambiguity and incomplete information. Durable autonomy means designing agents that recognize uncertainty, escalate intelligently to humans when necessary, and resume coherently without losing progress. Weโll examine architectural patterns for human-in-the-loop integration that preserve control while maintaining forward momentum.
3. Durable Statefulness
Long-running agents cannot rely on ever-growing prompts. Some systems serialize state into resumable bursts using patterns like Anthropicโs Git-Commit approach. Others externalize cognition into layered memory architectures - separating working, episodic, semantic, or procedural memory through memory virtualization. Different workloads and time horizons demand different state strategies.
Viewers will leave with a deeper understanding of agent durability and a practical architectural framework for building resilient agents, systems designed not just to respond, but to endure.
SPEAKER:
Parminder Singh - Co-founder and CEO, Rescope AI
๐ 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 1 - AGENT INFRASTRUCTURE] Most AI agents work in demos. Few survive in production. LLMs are stateless. Infrastructure fails. Context windows reset. Real-world objectives span hours or days. Building long-running autonomous agents requires durability engineered across the entire system.
This talk compares and contrasts dominant approaches to durability for agents and presents three pillars of durable agentic systems.
1. Durable Execution
Agents must survive crashes, retries, and partial task completion. Durable execution engines like Temporal persist workflow state and enable deterministic replay. Graph-based orchestrators such as LangGraph model control flow as explicit state machines. These approaches reflect different assumptions about recovery, replayability, and operational resilience, and directly shape how agents behave under failure.
2. Durable Autonomy
Autonomous systems inevitably encounter ambiguity and incomplete information. Durable autonomy means designing agents that recognize uncertainty, escalate intelligently to humans when necessary, and resume coherently without losing progress. Weโll examine architectural patterns for human-in-the-loop integration that preserve control while maintaining forward momentum.
3. Durable Statefulness
Long-running agents cannot rely on ever-growing prompts. Some systems serialize state into resumable bursts using patterns like Anthropicโs Git-Commit approach. Others externalize cognition into layered memory architectures - separating working, episodic, semantic, or procedural memory through memory virtualization. Different workloads and time horizons demand different state strategies.
Viewers will leave with a deeper understanding of agent durability and a practical architectural framework for building resilient agents, systems designed not just to respond, but to endure.
SPEAKER:
Parminder Singh - Co-founder and CEO, Rescope AI
๐ 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
![AI Needs a New Kind of OLTP: Lakebase & Serverless Postgres in the Agent Era | Databricks
[2026 - DAY 1 - DATA ENG & DATABASES] AI agents are driving a new category of operational databases, creating workloads that look nothing like traditional SaaS traffic. In Lakebase today, over 80 percent of new databases are created programmatically by agents rather than humans, resulting in extreme burstiness, highly ephemeral environments, and large volumes of short lived databases. These patterns push classic OLTP assumptions, including always on instances, steady traffic, and tightly coupled storage and compute, beyond their limits. In this talk, we will explain why existing databases struggle with agent workloads and how a new OLTP design emerges from separating storage and compute, enabling fast autoscaling, true scale to zero, and database branching that allows agents to run experiments and roll back state instantly. Using Lakebase and serverless Postgres as a concrete example, we will share practical design lessons for anyone building data infrastructure in the agent era.
SPEAKER:
Stas Kelvich - Principal Software Engineer, Databricks & Neon.com co-founder
๐ 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 AI Needs a New Kind of OLTP: Lakebase & Serverless Postgres in the Agent Era | Databricks](https://i.ytimg.com/vi/b1ND5zxrmWU/mqdefault.jpg)


![Your Database Wasnt Built for This | CockroachDB
[2026 - DAY 2 - WORKSHOP] Databases were built for a world where humans were the primary users. That world is changing fast. As AI moves from copilots to autonomous systems, agents are starting to create environments, test queries, assist migrations, coordinate workflows, and make operational decisions at a speed and scale that humans cannot match. One useful way to think about this shift is that traditional software is crystallized intelligence: fast, reliable, and optimized for known paths. Agents are fluid intelligence: less optimized step by step, but far better at adapting to new situations and conditions. Production systems will increasingly need both, which means databases will need to serve not only human developers and operators, but also agents acting on their behalf.
This talk explores what that shift means for the data layer. As agents create more databases, generate machine scale traffic, run constant experiments, and operate continuously across systems and regions, old assumptions begin to break down. Databases must work efficiently across many scales, from tiny agent created databases to very large production systems. They must support safe sandboxes for experimentation, whether through instant cloning, isolated environments, or strong resource governance within shared systems. They must provide fine grained, on demand scoped permissions, strong governance, and full auditability for autonomous actions. And they must stay available through outages and failures, while providing the resource accounting and automatic cleanup needed for a world of temporary, agent driven infrastructure. The core argument is simple: production AI systems need more than a familiar transactional database. They need truth, governance, and control at machine scale, with the resilience to handle concurrency, growth, experimentation, and failure without losing correctness. Attendees will leave with a practical framework for thinking about database architecture in the agent era and what it takes to support agents and workflows in production.
SPEAKER:
Andy Kimball - Fellow, CockroachDB
๐ 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 Your Database Wasnt Built for This | CockroachDB](https://i.ytimg.com/vi/c0TUB9uez8k/mqdefault.jpg)
![Look Ma, No Data Warehouse!
[2025 - Day 1 - Lunch & Learn] George Fraser shares insights from building queryable analytics powerhouses using open-source tools, exploring how to combine DuckDB, Fivetran, and Polaris Catalog to get cloud warehouse ease without the cost and lock-in. For teams frustrated with expensive data warehouses or restrictive platforms, this session offers valuable perspectives on leveraging Iceberg open table format and new dbt adapters for advanced analytics and AI applications.
ABOUT THE SPEAKER:
George Fraser, Co-Founder & CEO, Fivetran -
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
โ https://aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Look Ma, No Data Warehouse!](https://i.ytimg.com/vi/cPsmPAPwpAY/mqdefault.jpg)
![Why GPUs Keep Getting Faster While CPUs Stalled - And What It Means for Your Code
[2025 - Day 1 - AI Engineering] Charles Frye shares insights from understanding GPUs for data science workloads, exploring the most important facts and intuitions about GPU architecture that impact system performance. For data scientists working with neural networks on GPU accelerators, this talk offers valuable perspectives on features and phenomena that affect latency and throughput, from silicon layer fundamentals to high-level frameworks like PyTorch and vLLM.
ABOUT THE SPEAKER:
Charles Frye, Developer Advocate, Modal Labs
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
โ https://aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Why GPUs Keep Getting Faster While CPUs Stalled - And What It Means for Your Code](https://i.ytimg.com/vi/ch2ODgbJjlA/mqdefault.jpg)
![Write Less More: How Dagster Rebuilt Our Docs From the Ground Up
[2025 - Day 3 - Lightning Talks] Pedram Navid shares insights from rebuilding Dagsters documentation from the ground up using Docusaurus, exploring how to tackle documentation challenges that incremental improvements couldnt solve. For teams struggling with maintaining technical documentation, this talk offers valuable perspectives on when and how to undertake complete rewrites, presented in the style of a Fresh Prince narrative about flipping docs upside down.
ABOUT THE SPEAKER:
Pedram Navid, Head of Data Engineering & Developer Relations, Dagster Labs -
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
โ https://aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Write Less More: How Dagster Rebuilt Our Docs From the Ground Up](https://i.ytimg.com/vi/dVB5hLPyHCM/mqdefault.jpg)
![We Solved Agent Building | Vercel
[2026 - DAY 3 - LIGHTNING TALK] The evolution of building our successful internal text-to-SQL agent that currently fields over 1200 requests a day from Vercel. From a simple prompt, to sophisticated agent, and all the steps we built and learned along the way.
SPEAKER:
Andrew Qu - Chief of Software, Vercel
๐ 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 We Solved Agent Building | Vercel](https://i.ytimg.com/vi/e8uqeCtoSFw/mqdefault.jpg)
![Engineering Earths Largest Biological Data Pipeline
[2025 - Day 3 - Lightning Talks] Saif Ur-Rehman shares insights from building Basecamp Researchs proprietary digital twin of life on Earth, exploring how their global biological data supply chain enables next-generation foundation models. This talk offers valuable perspectives on tackling the 99.9% knowledge gap in life sciences through heterogeneous multilayer data representations, crucial for teams working with complex experimental workflows and state-of-the-art AI models in biological research.
ABOUT THE SPEAKER:
Saif Ur-Rehman, Data Engineering Lead, Basecamp Research -
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
โ https://aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Engineering Earths Largest Biological Data Pipeline](https://i.ytimg.com/vi/ecIT0YLHH7Q/mqdefault.jpg)
![Trillions-to-Reality: How SambaNovaโs Memory-Centric Design Powers Agentic AI & GenAI Workflows
[2025 - Day 3 - Keynote] Sumti Jairath shares insights from building SambaNovas revolutionary memory-centric architecture, exploring how their innovative design powers trillion-parameter models and multi-agent systems with record-breaking performance. This talk offers valuable perspectives on overcoming the memory wall challenge and optimizing data access for enterprise AI applications, crucial for teams scaling generative AI or building autonomous systems.
ABOUT THE SPEAKER:
Sumti Jairath, Chief Architect, SambaNova Systems -
๐๏ธ GET YOUR TICKET TO AI COUNCIL 2026 ๐๏ธ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
โ https://aicouncil.com/sf-2026
โก FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Trillions-to-Reality: How SambaNovaโs Memory-Centric Design Powers Agentic AI & GenAI Workflows](https://i.ytimg.com/vi/eduTe244Na8/mqdefault.jpg)
