Gabe Pereyra(@gabepereyra):Awesome research by @engramlab using the synthetic law firm we built. They trained a 27B Qwen model on synthetic client matters and used the learned knowledge to do online search more efficiently. The trained model outperforms frontier models at 10x lower cost per query. The results are promising for scaling up enterprise search and personalization.

2026.08.17 21:26

Awesome research by @engramlab using the synthetic law firm we built. They trained a 27B Qwen model on synthetic client matters and used the learned knowledge to do online search more efficiently. The trained model outperforms frontier models at 10x lower cost per query. The results are promising for scaling up enterprise search and personalization.

Engram@EngramLab

2026.08.17 19:50

Today we're publishing our first research blog, Understanding a Law Firm through Study. We're sharing a glimpse of a future where agents are trained with native memory: