On the spend management side of things, I've found pretty remarkable success in letting LLMs check "does this receipt match this reimbursement request and based on all the information about the user, the request, and our policy, is it appropriately allocated to appropriate GL, Location, Department, and Project codes?" If the verification step fails, it kicks it back and the user can either override it (which gets it flagged for AP review), or fix it. It does substantially better than the naive Bayes classifier I was using before.

▲

ofjcihen 3 hours ago | parent [-]

I’m not saying your implementation is bad or anything but my visceral reaction to this was “I’m glad I’m not on the other side of that”

▲

JamesSwift 3 hours ago | parent | next [-]

Why? It sounds exactly like the design I would hope for. It automates what I'm going to do already without needing to wait. And it allows you to bypass it entirely and just revert to the manual process (along with waiting).

▲

sholladay 2 hours ago | parent [-]

That all sounds reasonable until you realize that the same logic is how we ended up with customer support systems that try to walk you through a phone tree and if you are lucky, you will be able to press 0 to speak to a human without answering a bunch of questions first and being referred to the online help articles.

Do you enjoy using any of those systems? Do you want the world to be that way?

	▲	JamesSwift 2 hours ago \| parent \| next [-]
		Maybe we are interpreting the GP differently. In this scenario, the phone tree is doing the same questions that the human agent is going to do but does it immediately when I call rather than "waiting for an operator" to ask me those questions. And as long as I can "press 0 to eject" (just like I can in the accounting scenario, then its completely kosher to me.
	▲	KellyCriterion an hour ago \| parent \| prev [-]
		Regarding customer support on phone: I usually have lock with just waiting and not responding to the tel bot, very often you are routed to a human at the end :-D

▲

mikeyouse 3 hours ago | parent | prev | next [-]

In many businesses, the employee is responsible for inputting most of that. If a LLM can get to 95% accuracy and flag exceptions, the employees (and AP team) would actually have less work and bureaucracy.

Though we’ve had a few incidents where employees have submitted AI-generated receipts for reimbursement which is another issue..

▲

infecto 3 hours ago | parent | prev [-]

What is your point? This is pretty normal expense management in any company setting. I don’t know what is so bad about being on the other side of that. Hope I am not too inflammatory by asking what is the point but genuinely you pointed it out like it’s some archaic process flow but it’s part of almost every expense system.

▲

ofjcihen 2 hours ago | parent [-]

I guess my current company’s processes may be easier to deal with than others. That or my position affords me some extra catering to.

The system is currently using a simple app to submit expenses and any issues gets a simple human chat request and a call if requested.

They try to avoid kicking anything back and if they do they make sure it’s reviewed first to make sure that it’s needed and to make sure the reason is understood.

Our company is also very large so I’m not sure how they manage but they do. People rave about the process instead of hating it.

	▲	infecto 2 hours ago \| parent [-]
		Thanks for the thoughtful reply. To add some color… most expense systems are setup so that the user has to input a couple fields like the category or GL code. Some of the fields might be auto populated. Some companies might not care about the classification but usually the intent is to capture things like travel or software etc. What was described earlier is really not painful for users most of the time but a LLM helps automate so much of it these days.