What’s Cooking

ModalBlog1d

Endpoint Candidates: evaluate and promote inference endpoints

MilvusBlog5d

Jev vs. LLMs in Agentic Search

ExaBlog5d

ATLAS: Evaluating Agents on Search-Intensive Tasks

DatabricksBlog1w

The lakehouse is a better data warehouse: 2026 benchmarks and proof

UberBlog1w

Designing MCP Gateway Uber's MCP Management Platform

You’re caught up

That’s every post this month in this feed.