[sbolt]

Sean here, author and EM of the recon team at Modern Treasury. I completely agree, we us AI to surface suggestions to users during manual review so there's full transparency and human confirmation at every step. Our automatic recon doesn't use LLMs for the reasons you outlined.

[benreesman]

I’ve made a couple of critical comments and I hope I wasn’t too rude.

The way you present the case in this comment is vastly better than in the post.

There are ambiguous cases in certain accounting treatments, and hinting a resolution is, well it still makes me nervous but it’s not crazy.

[sbolt]

All good, and thank you for the feedback!

[aidenn0]

If the AI is right 99% of the time, what are the odds a human detects the remaining 1% rather than just being complacent?

[spookie]

From a human-computer interaction standpoint you do raise a fair point.

Even if in reality the AI misses _considerably more_ than that, there's a good argument to be made that such hints may steer the human from their initial, correct assumptions, or even reasoning.