OpenAI’s New Agent Stack: Computer Use, Decisions API, UltraFast, Dots—Ari Weinstein & Nikunj Handa
Recorded immediately following OpenAI DevDay, Ari Weinstein and Nikunj Handa join the hosts to detail OpenAI's newest agent and API announcements. Weinstein explains how Computer Use evolved to become faster than average human users through multimodal representations, code-driven multi-step execution, and cloud Linux VMs in Dots. Handa outlines the developer API stack updates, including the Decisions API, parallel batching, WebSockets, UltraFast inference, compaction techniques, and extended prompt caching.
- Raw screenshots hide critical structured data from language models, including hyperlink URLs and truncated calendar text. Read →
- OpenAI introduced 12-hour prompt cache guarantees to slash costs for persistent agent loops that outlive standard 30-minute eviction windows. Read →
- OpenAI built the Decisions API in under four weeks without training a single new model weight. Read →
- OpenAI provisions each Dots assistant with its own dedicated Linux virtual machine in the cloud, bypassing the limits of simple browser scraping. Read →
- Synchronous tool calls create artificial latency bottlenecks; async function calling lets the model reason and generate continuously while external operations execute. Read →
- Early Computer Use systems trapped agents in slow loops: take a screenshot, scroll down, take another screenshot, and guess the next pixel coordinate. Read →