Uploaded June 2026 | Updated November 2026, 54 minutes ago
[2026 - DAY 2 - AI ENGINEERING] Pricing AI Agents is a highly practical talk on how to design pricing systems for AI-native products where cost, value, and customer behavior change continuously. As AI agents move from experiments to mission-critical workflows, pricing can no longer be static. It must be engineered.
In this session, a team from Orb explains how to build pricing infrastructure with extreme accuracy, high transparency, and the intelligence to make fast, iterative pricing changes. The talk covers why precise cost attribution matters even when AI features are not directly monetized yet, how transparent usage and controls build customer trust, and why flexibility is essential as workloads, margins, and buying processes evolve.
The session is grounded in real-world examples from high-growth AI and SaaS companies. It shows how teams are pricing AI agents in practice using usage-based models, prepaid credits, outcome-aligned pricing, and guardrails that protect margins as scale increases. Attendees will leave with concrete guidance on how to design pricing as a system that aligns incentives, adapts over time, and turns AI pricing into a durable competitive advantage.
SPEAKERS:
Ellen Perfect - Product Marketing Lead, Orb
Eduardo Olivares - Senior Technical Support Engineer, Orb
π 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 - AI ENGINEERING] Pricing AI Agents is a highly practical talk on how to design pricing systems for AI-native products where cost, value, and customer behavior change continuously. As AI agents move from experiments to mission-critical workflows, pricing can no longer be static. It must be engineered.
In this session, a team from Orb explains how to build pricing infrastructure with extreme accuracy, high transparency, and the intelligence to make fast, iterative pricing changes. The talk covers why precise cost attribution matters even when AI features are not directly monetized yet, how transparent usage and controls build customer trust, and why flexibility is essential as workloads, margins, and buying processes evolve.
The session is grounded in real-world examples from high-growth AI and SaaS companies. It shows how teams are pricing AI agents in practice using usage-based models, prepaid credits, outcome-aligned pricing, and guardrails that protect margins as scale increases. Attendees will leave with concrete guidance on how to design pricing as a system that aligns incentives, adapts over time, and turns AI pricing into a durable competitive advantage.
SPEAKERS:
Ellen Perfect - Product Marketing Lead, Orb
Eduardo Olivares - Senior Technical Support Engineer, Orb
π 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 Happens to BI in an AI-First World? | Evidence
[2026 - DAY 2 - ANALYTICS & DATA SCI] Are dashboards dead? Will BI tools disappear? Will analytics move entirely to chat? In this session, weβll run a thought experiment: in a world where AI is exceptionally good, what do organizations actually need from data - and what does the data stack look like to support it? This exercise reveals a new operating model for analytics: much of the technical work becomes automated, and data teams shift toward managing systems of AI agents that generate and refine data products. A similar shift is already underway in software engineering, where teams are building self-reinforcing feedback loops that continuously improve software. Drawing on real examples from our teamβs development workflows, weβll explore how data teams can apply these patterns to analytics - and how they can prepare for an AI-first future while maintaining strong governance and security.
SPEAKER:
Sean Hughes - Co-Founder, Evidence
π 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 Happens to BI in an AI-First World? | Evidence](https://i.ytimg.com/vi/HUrHMyb_D84/mqdefault.jpg)
![DuckDB + PostgreSQL: Building a Data Warehouse Inside Your Favorite Database
[2025 - Day 3 - Databases] Marco Slot shares insights from combining transactional and analytical database capabilities, exploring how embedding DuckDB into PostgreSQL creates a unified platform for both OLTP and OLAP workloads. For architects building modern data platforms or simplifying complex data stacks, this talk offers valuable perspectives on the motivations, benefits, and challenges of fusing supremely extensible OLTP with supremely embeddable OLAP databases.
ABOUT THE SPEAKER:
Marco Slot, Software Imagineer, Crunchy Data
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ DuckDB + PostgreSQL: Building a Data Warehouse Inside Your Favorite Database](https://i.ytimg.com/vi/HZArjlMB6W4/mqdefault.jpg)
![Make Vibe Coding Safe: How to Test with Playwright | Amazon AGI Lab
[2026 - DAY 3 - LIGHTNING TALK] Vibe coding is fast, but it often skips the safety rails: features look fine in a demo and then break in real user flows. Especially when you iterate on them. This talk shows how to make vibe-coded web apps reliable by adding end-to-end tests with Playwright that are quick to write, stable in CI, and focused on what actually matters.
A big shift is that modern coding assistants like Cursor and Claude Code can run commands and iterate on real failures. Whats missing is the glue, between e.g. Claude Code to run a test and gets its state. I will show practical workflows for writing tests faster using MCP Skills and Playwright MCP, both in an editor and inside Claude Code environments.
Based on lessons from building multiple websites over the last months, I will share a repeatable approach for growing a small, high-signal test suite that keeps up with rapid development and gives you the confidence to ship more changes without fear.
SPEAKER:
Max Schmitt - Member of Technical Staff, Amazon AGI Lab (and prior core contributor to Microsoft Playwright)
π 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 Make Vibe Coding Safe: How to Test with Playwright | Amazon AGI Lab](https://i.ytimg.com/vi/H_1bo-vM1vc/mqdefault.jpg)
![Democratizing Analytics via Self Service
[2026 - DAY 1 - DATA ENG & DATABASES] Visualization tools like Tableau have long been essential for data analysis, but their steep learning curves often make them inaccessible to non-technical business users, slowing decision-making and hindering opportunities. The future of data analytics lies in empowering business and non-technical users to interact with data, draw insights, and make real-time decisions, without relying on expertise working with complex visualization tools. Semantic layers are key to this transformation, abstracting metric definitions and forming the foundation for no-code self-service analytics solutions. This session will explore how semantic layers bridge the gap between data silos and business needs. Attendees will gain insights into designing metrics with semantic layers and building high-performance, low-latency data storage solutions to enable seamless self-service analytics, empowering teams to make faster, more effective data-driven decisions.
SPEAKER:
Bhargavi Reddy Dokuru - Staff Data Engineer, Netflix
π 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 Democratizing Analytics via Self Service](https://i.ytimg.com/vi/HotbjSIgLOM/mqdefault.jpg)
![AI-Powered Automation: Supercharge Data Intensive Workflows with Intelligent Agents
[2025 - Day 1 - Workshops] Skip Everling shares insights from transforming unstructured data into actionable insights using AI agents, exploring how to automate data-intensive workflows for analysts, compliance officers, and knowledge workers. This interactive workshop offers valuable perspectives on streamlining document-heavy processes through compliance assessments, contract analysis, and risk evaluation, crucial for professionals dealing with large volumes of PDFs, contracts, and regulatory documents.
ABOUT THE SPEAKER:
Skip Everling, Head of Developer Relations, Kolena -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ AI-Powered Automation: Supercharge Data Intensive Workflows with Intelligent Agents](https://i.ytimg.com/vi/I-2VvU60tPY/mqdefault.jpg)
![Identity Is the Bottleneck: Why Agents Force a New Security Model | Keycard
[2026 - DAY 3 - AI SECURITY & SAFETY] Agents donβt just call APIs. They plan, iterate, and take action across systems. As they move into real workflows, they expose a core issue: identity and access systems werenβt built for software that behaves like this. The current model assumes stable actors, predictable workflows, and permissions defined ahead of time. Agents donβt fit that model. Theyβre dynamic, they cross boundaries, and they operate in ways that canβt be fully anticipated.
This talk breaks down where that gap shows up and why it matters. It then looks at what needs to change. Identity becomes the control plane, with access decisions made at execution time using the full context of the user, the agent, and the environment, and enforced on every action.
SPEAKER:
Jared Hanson - Co-founder, Keycard
π 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 Identity Is the Bottleneck: Why Agents Force a New Security Model | Keycard](https://i.ytimg.com/vi/I69W6cuBKzM/mqdefault.jpg)
![Chaos By Design: Simulation Based Testing for AI Agents
[2025 - Day 3 - Lightning Talks] Willem Pienaar shares insights from building AI agents for complex operational scenarios, exploring why traditional testing approaches fail for agents tackling real-world problems without predefined playbooks. This talk offers valuable perspectives on creating deterministic simulation environments for testing agents in scenarios like distributed systems root cause analysis, crucial for teams building agents that must navigate dynamic systems without ground truth answers.
ABOUT THE SPEAKER:
Willem Pienaar, Co-Founder & CTO, Cleric -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Chaos By Design: Simulation Based Testing for AI Agents](https://i.ytimg.com/vi/Ir3jLWvauNk/mqdefault.jpg)

![How Open Frontier Labs Actually Train Their Models | Prime Intellect
[2026 - DAY 3 - MODEL SYSTEMS] Training a large language model is an exercise in tradeoffs you didnβt expect, where choices made for pre-training can shape post-training, agentic RL, and inference much later.
Should you spend a week optimizing infrastructure and architecture, or just start training when every design choice affects rollout speed, memory use, and serving cost?
This talk covers how to think about mdeol decisions: why architecture changes are rarely just about accuracy and almost always about performance, how inference choices determine what is feasible for post-training, and how frontier open labs design models for RL-heavy, agentic workloads.
Weβll walk through the full lifecycle of a model, from pre-training to mid-training to post-training RL, examining how decisions at each stage shape the next and why tradeoffs around efficiency, capability, and inference cost rarely have clean answers
SPEAKER:
Sami Jaghouar - Head of Research, Prime Intellect
π 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 How Open Frontier Labs Actually Train Their Models | Prime Intellect](https://i.ytimg.com/vi/JEoG1v62APM/mqdefault.jpg)

![Make Too Much Knowledge Just Enough Massive Scale RAG & GraphRAG w Open Source
[2025 - Day 3 - GenAI Applications] Skyler Thomas shares insights from building real-world RAG and GraphRAG systems that scale to hundreds of millions of documents, exploring the complex orchestration beyond trivial extract-and-search approaches. Whether youre designing production RAG systems or debugging complex vector workflows, this talk offers valuable perspectives on scaling to billions of vectors and using open standards like OpenTelemetry for monitoring distributed RAG orchestrations.
ABOUT THE SPEAKER:
Skyler Thomas, Co-Founder & CTO, Cake AI -
ποΈ GET YOUR TICKET TO AI COUNCIL 2026 ποΈ
Meet the worlds top AI infrastructure minds where architects of AI share what works. Three days of high-quality technical talks and meaningful interactions.
β https://aicouncil.com/sf-2026
β‘ FIND US:
X: https://x.com/AICouncilConf
LinkedIn: https://www.linkedin.com/company/aicouncilconf/
Website: https://aicouncil.com/ Make Too Much Knowledge Just Enough Massive Scale RAG & GraphRAG w Open Source](https://i.ytimg.com/vi/JiW9rX1CBZs/mqdefault.jpg)