Encyclopedia Evalica / Deployment / Streaming
Streaming
/'stree.mihng/A response delivery mode where output tokens are sent to the client incrementally as they are generated. Streaming improves perceived latency even when total completion time is unchanged. (noun)
“Streaming made the assistant feel faster even though the full answer took several seconds.”
Related Deployment terms
From the docs
Get started with Evals
Braintrust is the observability platform for agents in production. By actively applying intelligence to agent traces and automatically surfacing critical patterns, Braintrust helps teams at Notion, Stripe, Box, OpenAI, and Cloudflare ship quality agents at scale.
Start building