AI Engineer

Beyond Transcription: Building Voice AI That Understands Conversations — Hervé Bredin, pyannoteAI

Text Diffusion — Brendan O’Donoghue, Google DeepMind

The Art & Science of Benchmarking Agents — Vincent Chen, Snorkel AI

SWE-rebench: Lessons from Evaluating Coding Agents — Ibragim Badertdinov, Nebius

AI Engineer Melbourne 2026 Keynote Livestream | Day 2

Beyond Components: Designing Generative UI for MCP Apps — Ruben Casas, Postman

Benchmarking semantic code retrieval on Claude Code — Kuba Rogut, Turbopuffer

BDD, ADR, PRD, WTF: Capturing Decisions for Humans and AI Alike — Michal Cichra, Safe Intelligence

AI Engineer Melbourne 2026 Keynote Livestream | Day 1

What Lies Beneath the API — Benjamin Cowen, Modal

Task Fidelity Scaling Laws — Kobie Crawdord, Snorkel

How Lovable self-improves every hour — Benjamin Verbeek, Lovable

20 days of compute vs 7 hours: rethinking what state-of-the-art means — Bertrand Charpentier, Pruna

What if the network was the sandbox? — Remy Guercio, Tailscale

How to talk to statues — Joe Reeve, ElevenLabs

Can LLMs generate Enterprise Quality Code? — Prasenjit Sarkar, Sonar

Engineering voice agents: Latency, quality, and scale — Rishabh Bhargava, Together AI

Spec-Driven Testing for Agents With A Brain the Size of A Planet — Steven Willmott, SafeIntelligence

How I deleted 95% of my agent skills and got better results — Nick Nisi, WorkOS

Building AI systems that ship requires moving beyond simple prompting toward robust, verifiable engineering harnesses. By implementing state machines to manage agent workflows—covering implementation, verification, and retrospective analysis—developers can ensure agents perform tasks accurately rather than hallucinatin...

How We Built Zeta2: Training an Edit Prediction Model in Production — Ben Kunkle, Zed