Rebecca Le and Zach Daniel, co-authors of the Ash Framework book, discuss how their Tunez-based guide was built to introduce concepts in the order a real project needs them, how writing it forced the addition of generator-based testing to Ash, and why Ash's extensibility, Cinder's rapid development, and AI-assisted onboarding make its steep but flattening learning curve worthwhile.
Meenakshi Kodati discusses how AI is transforming software engineering, shifting the focus from coding to critical decision-making. As AI rapidly generates code, the true challenge and value lie in architectural choices, system-level understanding, governance, testing, and continuous quality assurance to deliver meaningful business outcomes, emphasizing human judgment over mere implementation.
Nubank, serving 135 million customers, uses AI agents for support. The talk reveals how simulated data for evaluations (evals) has enabled them to ship AI agents 20x faster. By addressing the bottleneck of multi-turn, stateful eval data, Snowglobe's grounded simulations create realistic customer interactions, allowing rapid testing, derisking, and significant improvements in customer satisfaction and self-service rates, even for open-source model experimentation.
Philipp Schmid from Google DeepMind emphasizes the critical, often-overlooked need for rigorous evaluation of AI agent skills. He argues that shipping skills without testing is akin to deploying code without unit tests, leading to unreliable agent behavior. The talk covers what defines an agent skill, strategies for writing effective and correctly triggering skills, and a practical guide to building lightweight evaluation harnesses to catch failures proactively.
Trisha Gee delivers a compelling talk on Developer Productivity Engineering (DPE) for testing, dissecting common pain points in writing, troubleshooting, and running tests. She advocates for strategic use of IDEs, advanced tooling like build caches and predictive test selection (leveraging ML), and a disciplined approach to test design to overcome these challenges, emphasizing that good tests serve as crucial living documentation.
Michal Cichra from Safe Intelligence explains how to maintain consistency in AI-driven software development by capturing decisions and enforcing rules. He argues for reviving Behavior-Driven Development (BDD) with Cucumber to close the loop left by spec-driven development. The core idea is to enforce architectural and product decisions (ADRs, PRDs) through an automated loop of git hooks and CI, ensuring both human and AI developers adhere to established standards.