Aipeiron

Accounting, Financial Modeling and Budgeting, and Tax Compliance, all automated with AI and ML. 1000x faster, 100x cheaper, and just as effective as an accountant.

Comment

Inspiration

Back when I was a freshman, I started working at Rangeview, an aerospace manufacturing startup. There I handled operations, which included accounting. I had absolutely no clue how to do taxes or accounting so I decided to hire an accounting firm. But the process was all very confusing to me. They would ask me for financial documents, or ask to do historical bookkeeping for our LLC, but no matter how many people I asked, I never had a solid grasp of what accounting was. So I decided to drop all of my classes and sign up for some accounting ones. A month into those classes, I realized what the accounting firms were doing was easy, and that I shouldn't be paying them so much money to do a task I could easily do myself, so I fired them and took up the task of being rangeviews sole accountant.

Accounting today is broken. Companies with less than 100k in their bank account are expected to pay thousands of dollars a month for an accounting firm, and that’s not to mention the thousands more that they’ll charge you once you register to do your taxes or other special tasks. This is because accounting is a foreign word to most founders. Many of them don’t even know if accounting is legally required, let alone the processes that go behind the scenes of the accounting firm they hired. And thus, accounting firms can get away with low effort and sub-par results. Something has to change.

What it does

Aipeiron to automates accounting, financial modeling, and compliance with the power of AI. With Aipeiron, any company will be able to get the insights that an accounting firm could provide 1000x faster and 100x cheaper and just as effectively. And the founder has full control and ownership every step of the way. Doing so is simple: by connecting your bank account, transactions flow automatically from your bank into our finetuned GPT-4 model, which then outputs categorized transactions, exactly what an accountant would do. From that data, you can generate financial models and budgets, or chat with our chatbot trained on the IRS’s instructions to talk about how you would file taxes, because taxes are confusing.

How we built it

We used NextJS14. The account creation step was done with NextAuth and Google OAuth. The Bank connection and free flow of transactions was done through Plaid. The plaid transactions then flow into our GPT-4-turbo model, and out comes a categorized transaction through hundreds of parallel calls. We also feed it embeddings of correctly classified transactions to imrpove the accuracy of the model. Our database is Postgres, and we used Prisma as an ORM and Amazon RDS to host it on the cloud. Everything from company and user information to the Plaid data, to the classified transactions, have all been stored in Amazon RDS. We create the graphs through react-charts, and speed up hundreds of transaction calls at once through clever caching and fetching.

Challenges we ran into

We originally used Supabase to host our data, however, the fetches for the database was very slow. We spent a good amount of time simply working on the fetching and caching logic, trying different things like local storage, fetching all the data in one call and storing it as a dictionary, running a parallel api calls through a promise, to get the transaction fetching, categorization, and budget creation fast enough to not bore the user. We got it down from an initial 2 minutes to a single second. OpenAI's API also gave us some issues.

Accomplishments that we're proud of

Getting the datafetching 100x faster was a huge milestone for us as it meant we could present our product without having to worry about taking up the entire demo time with just a single transaction fetch.

What we learned

We learned about different APIs like plaid, the pros and cons of different databases, and how to best handle massive amounts of relational data.

What's next for Aipeiron

We want to keep building this idea, and turn it into an actual company. The code right now works, but lacks refine. We will build the product fully, launch it, test it out with various companies, see if we can raise money, and try to turn it into an actual startup.

Built With

Share this project:

Updates