Low-latency AI for developer workflows | ODSP930

From the creator

Developer experience leaders from Cerebras and OpenAI show how low-latency inference changes coding agents, voice-driven workflows, slide generation, and workplace automation. See what you can build when responses land in seconds. 𝗦𝗲𝘀𝘀𝗶𝗼𝗻 𝗜𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻: This is one of many sessions from the Microsoft Build 2026 event. View even more sessions on-demand and learn about Microsoft Build at https://build.microsoft.com ODSP930 | English (US) | Developer tools & frameworks Pre-recorded | (100) Foundational #MSBuild Chapters: 0:00 - Preview of demos showcasing Codex Spark speed 00:00:29 - Jason’s first automation project at OpenAI 00:00:40 - Automation for monitoring topics and product launches 00:00:57 - Sub-Agents Analyze Slack, Google Drive, and Meets Data 00:01:19 - Detecting Duplicate Issues and Tracking Project Pipeline 00:01:35 - Comparing Codex workflow speed and productivity challenges 00:02:04 - Adding a 'See More' link to the bottom right of every cell 00:02:59 - Overview of multiple ways to leverage Spark within the Codex app 00:03:05 - Shift in thinking: Spark as always-on infrastructure

Published 2026-06-03 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.