Convert PDF invoices to e-invoice XML using AI in seconds
I got approached by the finance department of a large company. There is a new regulation in Europe that mandates a defined XML-format for e-invoices for some transactions and - I kid you not - their SAP implementation wasn't able to address this. They also said that all solutions on the market were either cumbersome (think: manually typing in all fields) or required deep system integration. I thought it cannot be that hard to use AI for this and built a little invoice converter that takes your PDF invoice in whatever form it is, and outputs exactly the XML structure that is required in the…
What it does
In the maker’s words, at launch
I got approached by the finance department of a large company. There is a new regulation in Europe that mandates a defined XML-format for e-invoices for some transactions and - I kid you not - their SAP implementation wasn't able to address this. They also said that all solutions on the market were either cumbersome (think: manually typing in all fields) or required deep system integration. I thought it cannot be that hard to use AI for this and built a little invoice converter that takes your PDF invoice in whatever form it is, and outputs exactly the XML structure that is required in the regulation. Given that AI is not perfect (but surprisingly close to it!), you can manually edit all fields. Target users are companies where their current solution does not yet support the standard and that do not want to change their existing invoicing flow (incl. foreign businesses). Trying it out is free. Given this is my first real B2B tool, would love some feedback!
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
