Blog Archives

29 Jan 2026

What Recommender Systems Really Optimise For: Metrics, Feedback Loops and Echo Chambers

Recommender systems sit behind almost every feed and “For You” page, yet most teams still optimise them for a narrow set of metrics like CTR or watch time. The result is a gap between what dashboards say is “good” and what users, regulators and society actually care about: satisfaction, trust, and not being trapped in […]

29 Jan 2026

Beyond Benchmarks 2.0: A Practical Framework for Measuring Multimodal and Agentic AI Success

While most enterprise AI projects start with excitement, only 20% survive the move from demo to production. This updated session evolves the “Beyond Benchmarks” framework for 2026, moving beyond text-only RAG to address the complexities of multimodal and agentic systems. We will explore how to measure success when AI interacts with images and complex documents, […]

26 Jan 2026

Applied AI at Work: Building and Training Agentic Systems

This talk covers two complementary techniques for applied AI: (1) building an agentic research system that gathers and synthesizes information, and (2) training a small reasoning model — first with supervised fine-tuning to learn structure, then reinforcement learning to improve judgment quality. Together they form an end-to-end pipeline, but each technique solves a different problem. […]

07 Jan 2026

Modeling Ad Creative at Scale: From Representations to Ranking Impact at Meta

Most recommendation systems focus on ranking the main item—whether it’s the perfect product, ad, or video. But in high-impact environments like Meta, optimizing the presentation of that item can be just as critical. Which image best complements an ad? Which text overlay (“Best Seller,” “Limited Time”) will drive engagement? These “non-product” recommendations are often overlooked, […]

05 Dec 2025

Optimizing EV Charging Stations: A Live Code-Along in Zerve

Join Greg Michaelson and Jason Hillary for a fully interactive, hands-on code-along where you’ll build an end-to-end optimization project from scratch using Zerve’s new notebook view. You’ll write code with us step by step, ask questions as you go, and learn how to model a synthetic city, generate EV charging demand, define an optimization objective, […]

04 Dec 2025

Build Context-Aware AI Agents with Amazon Bedrock AgentCore and Snowplow Signals

Kick off the year by moving beyond experimentation and into real-world AI delivery. This free, live virtual workshop is a rare opportunity to get hands-on with production-ready AI agents, real-time customer data, and the architectures teams are using right now. Seats are limited and this session is designed to be highly interactive, so early registration […]

08 Oct 2025

Data Vibe Coding with AI: Prompting Strategies That Actually Work

How do you get the best results when coding with AI? Should you craft one big, complex prompt and hope for the best, or start small and refine as you go? In this hands-on session, we’ll explore “vibe coding,” the art of shaping your AI prompts so that your code agent works with you instead […]

11 Sep 2025

Data Leaders Roundtable: Hiring, Developing, and Leading for Impact

Growing and sustaining high-performing data teams is one of the most important and most challenging responsibilities for today’s data leaders. This exclusive evening event, hosted by the Data Science Festival in partnership with Deliveroo, brings together an intimate group of managers and senior practitioners for an interactive programme of lightning talks and breakout discussions. Three […]

21 Aug 2025

From Questions to Career: How Curiosity and Empathy Helped Me Find My Place

Figuring out what kind of work really suits you isn’t always straightforward. In this talk, I’ll share my own journey of finding a role that felt like the right fit. What helped me most along the way were two things: curiosity and empathy. Instead of focusing on job titles, I started asking different questions- like, […]