Dayjob: Tax – evaluating AI agents on 50 professional tax assignments
https://surgehq.ai/blog/dayjob-taxAnd to be clear: my vision here isn't "have an agent do your taxes", it's to have agents build a hardened and thoroughly verified deterministic tool that can help you navigate the (somewhat bewildering) forms and instructions decision tree when filing your own taxes.
https://www.irs.gov/filing/where-to-file-paper-tax-returns-w...
(If a painter knew that the camera was coming out I would not want them to throw their canvas away)
That's not a fair comparison because the painter produces different work, whereas tax computations will be the same.
There's an article about it here https://biggo.com/news/202510160717_IRS-Fact-Graph-Public-Re...
These were artifacts from the IRS Direct File program (RIP)
Maybe your project could (re)productionize this dataset.
- It's oriented toward the IRS's internal XML API in a way that's not really useful for this project, since no consumer of my code is going to digitally submit to the IRS.
- The semantics of FactGraph are largely undefined, and the maintainers themselves seem to acknowledge that its development trajectory went off in a bad direction and it needs major divisions.
- It's super verbose.
- It's the year of Lean, so I wanted to find an excuse to use Lean.
Other work has been done in this domain, though. The biggest example is Catala[0], though Prof. Sarah Lawsky at Northwestern seems to have made some strides toward formalizing the Internal Revenue Code.
I feel like we're going to get to a point where it's mandatory to use AI for certain tasks - humans just can't be trusted to get things right that require a level of precision.
Feed previous year returns into Astra and find out! It's not too late for amended returns, you have 3? years from original date of filing
Top tier tax professionals can do pretty well on this benchmark (better than agents) but won't hit 100%.
The kind of people spending time preparing oodles of returns would not do very well on this metric, though (especially midway through that pile of returns, as opposed to "think carefully about this trick question").
1. found errors, e.g. where I used the incorrect exchange rate (and managed to work out how I had made that error, which I was impressed by)
2. found items which would appear to be errors except for context it did not know
3. flagged areas where it disagreed with me as to the correct tax treatment, but accepted that the law is ambiguous (and in some cases I preferred its interpretation after additional research and in other cases I did not)
4. flagged areas where it disagreed with IRS guidance, and only acknowledged said guidance after I provided links to it
5. provided highly inaccurate estimated tax calculations, and not been able to fix its estimates even when challenged
So my takeaway is that it is a very useful tool for tax, but perhaps unsurprisingly, it is not good enough to dump all your paperwork into and expect a shiny return you don't need to check. (Possibly it is if you just have a W-2 and no other substantial income, but I can't speak for that scenario.)
I think what helped is giving it 100+ pdf and csv documents of my full situation so it knew everything about me and could cross-reference with all my bank statements.
I no longer do consulting on the side so I just use online tax software. It is about $150 but I do that more out of laziness as it integrates with my brokerage and payroll company to import everything automatically. Also I have carry forward losses and such that it already knows about.
Most people’s taxes are simpler than mine but I am sure there are lots of folks here with much more complex tax situations
I have foreign income and foreign businesses, my partner has foreign income from two countries. The tax law is then based on tax treaties, most tax preparers do not have sufficient knowledge to complete a return, and tax software doesn't handle these cases.
The tax treaties are not clear, tax professionals will disagree on interpretation, and tax benefits in one country will not apply to another.
Then there is a thing called AMT, alternative minimum tax, which is a second way to calculate your taxes that you need to submit as well.
Same situation as you. I have a local accountant in the country I'm in plus my US accountant. Claude/ChatGPT have been a huge help for checking, explaining, and finding issues. They also found websites with pertinent information that Google did not, which surprised me.
it's the most ai-native tax experience for US citizens abroad
(It would also help to know if you had a financial interest in or prior experience with this company)
What do you mean by "cost you $20K"? That your tax liability was calculated by the accountant to be higher than it actually should have been? Or that the accountant calculated your liability too low, which was caught and billed by the IRS?
In the first case, you can still file for a refund within 3 years (I'm omitting some technical details), but in the latter case, as mentioned by others, you still owe the tax whether it was correctly reported on your original return or not.
The real issue is that accountant most likely has a track record of those kinds of mistakes - but you have no info on other clients. So you weren’t as informed at the time you chose them vs the new one.
I think the red flag should have been when he printed out all my tax returns and made me pick them up in person, and didn't even send a digital copy.
Seems like simplify or just erradicting the tax code would be more just at this point.
Normally it doesn’t get to that point though. CPAs do not want to be known as the person that misfiled taxes and got a court to rule them negligent. They carry insurance for errors so mostly just end up queitly making it right when there is an error.
I am not aware of setups available to me that would transfer liability onto accountant.
So in either case I am taking liability.
(also, I am pretty sure that if corporation loses 10 millions over accountant making bad decisions, they are not going to recover that funds either)
And there was no real path to recovering funds, except small part, after long court case.
At least they were able to fire them without severance pay.
https://blog.nawaz.org/posts/2022/Nov/do-you-trust-your-tax-...
There is no such thing as "failing" an IRS audit. You either under reported income, overstated deductible expenses, or your "accountant" changed the numbers you provided and committed fraud, which would have resulted in immediate legal proceedings by the IRS against the preparer. So did you "fail" because your preparer committed federal tax fraud or did you underreport your income?
The statement that the one time you used an accountant you got audited implies that you are confusing causation with correlation. There are about 6 ways that the IRS selects returns for audit but only 3 are actually relevant here.
- Information Matching (ie. if your W2 does not match the W2 submitted by your employer). This mostly used for your basic W2, 1099DIV, etc. kind of taxpayer and is usually just a letter from the IRS telling you your numbers are wrong and you need to amend your return.
- If they are examining a related return (ie. you own a business and another partner in that business is being audited)
- Computer scoring which breaks down into the Discriminant Function System (DIF), basically, how does your return compare to similar returns, and Unreported Income DIF, what is the potential that your return underreported income. This is what is commonly used for businesses and self employed individuals' Schedule C. Basically, when you prepare a business return (1040 Sch. C, 1041, 1065, 1120, 1120S, or 990) you have to report your business industry's NAICS code, and provide a single line explanation what your business does. Using this and the return data, the IRS is able to score a return on the likelihood that profit is understated by comparing a businesses income and expenses to the norm for a similarly sized businesses in that industry. High scoring returns are then reviewed by IRS personnel.
One of those three things happened to you and none of them are the fault of a preparer that is using accurate information provided by the taxpayer.
Finally, you keep saying things like "accountant". You disparaging an entire industry without saying what type of tax preparer you used. Was it a CPA, licensed by a state with experience in tax? An Enrolled Agent, licensed by the IRS directly? Or a tax preparer, an unlicensed person preparing your return either on their own or through something like HR Block or Turbotax? Because if you used an unlicensed tax preparer and are blaming licensed individuals that is like hiring an unlicensed electricians and then when your house burns down from an electrical fire, turning around and saying all electricians are bad
And that's true if all you do is have W-2 income, and RSUs/ESPPs. ESPPs were the most complex thing I had to deal with until I stupidly decided to do things and get K-1s.
Well, you are an accountant :-)
With my K1, the issue was that it was for a real estate investment, and you have to be careful about things like bonus depreciation/cost segregation etc. One tax accountant I used was not carrying over the loss (or perhaps not applying the prior year's loss, or something like that). Another accountant was deducting that loss from my W-2 income, which I can't do as I'm not a real estate professional.
When I finally brought these points up and got all these corrected, I studied the final result and then continued doing them myself. But it was a pain getting the online tax SW (TurboTax, TaxAct, etc) to mimic what they did. I had to be really careful what things I said "Yes" to and what I didn't. I would never have figured it out on my own by reading the relevant tax publications (which I did peruse).
And then later, I formed a partnership with a friend so we could both invest in something. Now I also have to issue K-1s! Not fun! RSUs are much easier.
I consider being audited and the IRS finding corrections to prior returns as a "failure". Once I started doing things myself, I was audited and no corrections found (e.g. a "success"). In the case where I "failed" the audit, it had to do with how expenses were being handled by the accountant. At the time I was a contractor working on a 1099 and was tracking and submitting some business expenses for reimbursement, and some expenses were tracked and taken against my taxes but not reimbursed. What was filed did not align exactly with what was reimbursed, which caused an overstatement of deductions, causing me to owe back taxes. I am not making any claim that they committed fraud, as that's a crime which requires intent, I think they were just incompetent.
> The statement that the one time you used an accountant you got audited implies that you are confusing causation with correlation.
I actually didn't say that, I said the only time I got audited and failed was when I used an accountant, however I realize my style of writing made that unclear. During the time where I received income via a 1099 (and for part of that also had to file from a K-1 briefly for an LLC), I was audited three times in total. Only one time did I "fail", and it was the only time where I had professional assistance. In fact, I found the process of being audited surprisingly kind, the IRS folks involved were very professional and weren't mean about it at all. After my first experience being audited, even though I got the nasty surprise of owing back taxes, I was a lot less fearful of that process. That said, I have never had any understanding of how someone is chosen to be audited, but I have not been selected for an audit since moving to a W-2 for all of my income, which has been quite some time now. The experience of being audited did get me into the habit of storing all my tax related records carefully organized by year long-term, however, which I think is probably a good habit for everyone.
> You disparaging an entire industry without saying what type of tax preparer you used.
My intent isn't to disparage anyone, it's to share my own personal experience. I hired a CPA licensed in the state of Missouri (where I resided at the time) when I previously had a professional handle my taxes.
https://www.accountingtoday.com/news/new-bill-calls-for-irs-...
There is also an IRS form (14157) to report a return preparer complaint, which of course does not include an option to report a faulty AI.
Can't be good getting caught with mistakes and losing customers?
These types of detail-oriented professional tasks seem like they would perform better with task-specific harnesses. The example they give, of Astra missing the property excluded gains requirement, seems easily fixed by scaffolding ensuring that requirements are compiled first, then checked.
If the scaffolding is absent, is this benchmark testing that a model can self-scaffold, or track requirements in-context?
0 - https://huggingface.co/datasets/surgeai/DAYJOB-tax/tree/main...
I've found it so far more effective for preparation than for planning/advice.
I've got a plan to feed the laws and rules and instructions into the machine before the prompts - is RAG still cool? Maybe I should small-language this?
Admittedly, it could be promting issue, lots of context for these decisions.
EDIT: good point that paying accountant does not ensure avoiding it
wonderful, you made a good point that make me dislike situation even more
The plan now is to retrieve the current year's tax forms then have an LLM compare them to stored versions from last year, and look for variances (e.g. new field, new form requirements, etc) all of which an LLM would excel at (whilst basic math it historically did not).
- someone who hates me personally will get access to it (see case where someone put their ex-spouse on no-fly-list etc)
- leak my private info via new version of LLM was trained on it
- sell it to everyone interested (maybe sold after their bankruptcy)
- give it to NSA and whoever else
from obvious ones
I guess my point is these benchmarks unless they are constantly refreshed with new scenarios and not ever having their outcomes written about publicly or available on a public server, will always be prone to being gamed
I'd have honestly never been able to do it myself - its just too tedious.
Pretty sure the LLMs could implement tax calculations better than the average accountant, were they given the rules.
I’m not sure the evidence is on the side of the CPAs. Maybe CPAs with LLM assistance.
I literally gave it your question. What models did you test?