Talks, workshops, events, and training for AI Engineers.
AI companies are growing three times faster than traditional SaaS but face unique pricing challenges due to unpredictable compute costs and razor-thin margins, requiring a shift from static subscription models to flexible hybrid pricing that prioritizes rapid iteration and customer-perceived value over technical metrics.
This workshop demonstrates how to bridge the gap between AI prototypes and production systems using Brain Trust's observability platform, featuring Trainline's experience deploying multi-agent AI applications serving 27 million users.
Google DeepMind engineers Thor Schaeff and Philipp Schmid demonstrate building conversational agents using the new Gemini Interactions API, a unified interface that supports both direct model inference and complex autonomous agents like Deep Research with server-side state management and asynchronous execution.
David Gomes from Cursor details how they replaced 15,000 lines of complex git work tree management code with a 200-line markdown skill using agent primitives, drastically reducing maintenance while enabling multi-repo support and flexible model comparisons, though requiring new approaches to ensure agent isolation.
OpenAI's Katia Gil Guzman and Vaibhav Srivastav unveil Codex's evolution into a full software engineering agent, demonstrating new plugins that bundle workflows, automations for background task scheduling, and subagent capabilities powered by mini models to handle complex parallel development tasks.
Paige Bailey demonstrates Google DeepMind's rapid release of the Gemini 3.1 model series and AI Studio tools, showcasing how developers can leverage multimodal capabilities, sandboxed code execution, and real-time screen sharing to build production AI applications with exceptional cost efficiency.
Maxime Labonne explains that small language models (350M–24B parameters) for edge deployment face unique architectural and training challenges distinct from simply scaling down large models, requiring specialized solutions like short convolutions, massive over-training, and targeted reinforcement learning to overcome memory constraints and 'doom looping' while excelling at agentic tool use.
Eric Zakariasson from Cursor details the roadmap to building autonomous "software factories," outlining six levels of AI coding autonomy and the practical infrastructure—modular codebases, dynamic guardrails, and verifiable systems—required to evolve from writing code to managing AI agents.
![[FULL WORKSHOP] AI Coding For Real Engineers - Matt Pocock, AI Hero (@mattpocockuk )](https://i.ytimg.com/vi/-QFHIoCo-Ko/hqdefault.jpg)
Matt Pocock demonstrates how traditional software engineering principles apply to AI coding, teaching engineers to manage LLM limitations through "smart zones," avoid "specs-to-code" traps, and use structured interrogation techniques to achieve true alignment with AI agents.
Sander Dieleman from Google DeepMind explains the technical foundations of training large-scale generative image and video models like Veo, emphasizing that meticulous data curation and learned latent representations are as critical as the diffusion architecture itself. He details how diffusion models reverse a noise corruption process through iterative refinement rather than single-step prediction.
This workshop demonstrates how to build production-grade deep research agents by navigating the spectrum from rigid workflows to autonomous systems, emphasizing strategic context management and hybrid architectures to automate high-quality technical content creation while avoiding generic 'AI slop'.
OpenAI engineer Ryan Lopopolo explains how AI agents have made code generation abundant and free, requiring a fundamental shift from writing implementations to designing systems, documentation, and guardrails that enable agents to execute software engineering tasks autonomously.