Einstein’s Zebra Puzzle is a great exercise for agentic reasoning and decision-making. Solving it requires no domain knowledge — just pure constraint satisfaction. Real world examples, though, are much messier. For example, whether or not to approve a loan application has a combination of hard and soft rules, and maybe allowance for loan officer discretion. […]
If you remember Chapter 4 of Trustworthy Online Controlled Experiments—the one with the blue HIPPO on the cover and the crawl–walk–run–fly maturity model—this session brings that chapter to life. It tells the story of how we intentionally progressed our experimentation platform from “walk” to “run,” navigating build-vs-buy trade-offs, architectural constraints, and organizational realities along the […]
Most AI agent systems fail not because the models are weak, but because they lack an operational foundation. This session explains AgentOps around two core pillars: MLflow as the system of record for agent lifecycle management, and an AI Gateway as the control plane for routing, governance, and cost management. We will explore how to […]
Generative AI is transforming industries by enabling businesses to create content, automate decision-making, and enhance user experiences. But how can organizations effectively build and deploy AI-powered solutions while maintaining security, efficiency, and scalability? In this session, we will explore the fundamentals of Generative AI models, their real-world applications, and how they can be leveraged to […]
As global financial platforms evolve, the “Trust Gap” becomes an engineering challenge. Scaling a product to millions of users requires more than just better models—it requires a fundamental shift from manual heuristics to automated, high-fidelity intelligence. We’re moving beyond the basics of model training to explore the “Last Mile” of production ML: the infrastructure of […]
When does it make sense to run your own LLM inference infrastructure instead of paying per-token to third-party APIs like OpenAI or Anthropic? This session gives you a practical framework for that decision and the technical foundations to execute it. We’ll ground everything in three concrete use cases – interactive chat, batch document processing, and […]
For well over 50 years, our machines, our data, and our (private/working) lives have coexisted in well-insulated boxes. However, the emergent behaviours of AI and robotics, along with our needs as individuals and a society, demand a full symbiosis if we are to succeed in a future where technology-driven change maintains its exponential growth. So […]
Google Trends data is messy. It’s normalised, it’s abstracted and it’s aggregated to a very coarse layer. In this talk we’ll discuss how to turn Google Trends snapshot into large datasets you can actually use to compare terms across countries in a meaningful way by using a chaining methodology and borrowing tech from the world […]
Data scientists are deeply invested in producing trustworthy insights but as AI becomes more powerful and autonomous we’re being confronted with the question: How do we know our insights are truly reliable? While explainable AI techniques have helped make black-box models more interpretable, interpretability alone doesn’t guarantee trustworthiness. In this talk, we’ll explore why trustworthy […]