“In less than six months, the team went from reviewing hundreds of contracts each month to more than a thousand. And yet we’d only hired one new person. It was obvious that the process wasn’t going to scale,” says Wei An Lee, AI Engineer.

Instead of throwing more people at the problem, our finance and engineering teams built a contract data agent. The design principle was simple: take the repetition out of contract review, keep experts firmly in control.

The output is a dataset that’s immediately useful across finance workflows. What once took hours arrives overnight, annotated and ready for validation. Experts remain in the loop, but their role shifts from manual entry to judgment.

This design ensures confidence: professionals get structured, reasoned data at scale, but their expertise drives the outcome.