Databricks

Effective enterprise data agents require search that is both accurate and fast. That’s why we’re introducing 𝗔𝗱𝗮𝗽𝘁𝗶𝘃𝗲 𝗜𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗲𝗱-𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗲𝗿, which combines the speed of parallel retrieval with the performance of sequential search while maintaining strict cost and latency guarantees. The goal is simple: spend additional search steps only when they are useful.