AI/ML
How to Build a Real-Time Voice Agent
Monday Nov 16 / 01:35PM PST
A voice agent looks like a chatbot with a microphone.
Sahil Yadav
Software Engineer @Together AI - Building Real-Time Production Voice Agents
Skills, Memory, or Fine-Tuning? The Engineering Loop Behind Production Agents
Tuesday Nov 17 / 10:35AM PST
After deploying and improving hundreds of production agents, each handling millions of requests, we've seen the same patterns emerge in what works (and what doesn't) when trying to make agents better.
Abhinav Sinha
CEO @Lucidic AI, Previously @Stanford AI Lab, @Citadel and Susquehanna International Group, and @Apple
Lessons from Building a $100M Product in Six Weeks at OpenAI
Tuesday Nov 17 / 02:45PM PST
Engineering is shifting from synchronous, line-by-line implementation to an asynchronous model in which agents execute, verify, and retry while humans own intent, architecture, constraints, and release decisions.
Brian Yang
Member of Technical Staff @OpenAI
Product Engineering: When code costs nothing, what's next?
Wednesday Nov 18 / 01:35PM PST
Coding agents produce 741% more code, and only 30% more software ships as a result. The gap is human review: people top out around 400 lines an hour and agents are not slowing down. This talk is for engineering leaders trying to decide what to do about that.
Laurie Voss
Head of Developer Relations @Arize AI, Co-Founder of npm, Inc., Developer for 30+ Years
Avoiding Prompt Debt & Other Context Failures
Wednesday Nov 18 / 03:55PM PST
As agents evolve, prompts get unruly. Edge cases are patched with one-line hotfixes, or with stacked instructions of escalating severity when an issue proves stubborn. Over time, those instructions pile up into a brittle artifact, overfit to an aging model.
Drew Breunig
CEO & Cofounder CMPND, Editor of O'Reilly's "Context Management Handbook", Writer on AI & Data at dbreunig.com, Previously Data Science & Product Lead PlaceIQ