Jev is exciting because you can make agentic experiences so-much-faster. John shows you how you can do it with some real-life stuff.
Looking at agents "thinking" feels like having to wait for an image to load pixel by pixel in the early days of the web.
John on our team got a docs agent down to a 0.5s median answer by moving decisions from the LLM to @typesafeai's Jev:
→ Pick the right knowledge base entry
00:00
