It's a self-hosted personal finance tool. You upload a bank statement CSV and a local LLM (Ollama, qwen3.5:9b) categorizes every transaction into 13 spending categories. A rule engine learns your preferences so repeat categorizations are instant. A dashboard gives you spending breakdowns, budget tracking, and cash flow trends across all your uploads.

Stack: FastAPI + React + Ollama + SQLite. Works on macOS, Linux, Windows.

Features:

  - Auto-detects CSV column mapping (handles EU/US date and number formats, exotic delimiters)
  - Rule engine applies saved patterns before hitting the LLM
  - Manual review queue for low-confidence categorizations
  - Dashboard with budget tracking, category breakdowns, cash flow trends
  - Rule Advisor that analyzes your patterns and suggests reusable rules

Happy to answer questions about the architecture or LLM categorization pipeline.

Comments URL: https://news.ycombinator.com/item?id=47377333

Points: 1

# Comments: 0

I'd push back slightly on the production grade point. The models aren't the ceiling, the user's mental model of software is, depending on his experience/knowledge.

Someone just starting out will get working prototypes and solid MVPs, which is genuinely impressive. But as they develop real engineering intuition — how Git works, how databases behave under load, how hosting and infra fit together — that's when they start shipping production-grade things with Claude Code.

Based on what I'm seeing, the tool can handle it. The question is whether the person behind it understands what they're asking for. Anthropic, for example, mostly uses claude code to develop claude code.

I was pointing out that practice helps with the speed and the scope of capabilities. Building a personal prototype is a different ballgame than building a production solution that others will use.

For example, I needed a local model to review some transactions and output structured output in .json format. Not all local models are necesserily good at structured outputs, so I asked grok (becuase it has solid web search and is up to date), what are the best recommended models given this use case and my laptop's specs. It suggested a few models, I chose one and went for it and now it's working.

To summarise, - find model given use case and specs. - trial and error - test other models (if needed) - rinse repeat - because models are always coming out and getting better

Fast forward to 2024 when I saw Cursor (the IDE coding agent tool). I immediately felt like this was going to be the way for someone like me.

Back then, it was brutal. I'd fight with the models for 15 prompts just to get a website working without errors on localhost, let alone QA it. None of the plan modes or orchestration features existed. I had to hack around context engineering, memories, all that stuff. Things broke constantly. 10 failures for 1 success. But it was fun. To top it all off, most of the terminology sounded like science fiction, but it got better in time. I basically used AI itself to hack my way into understanding how things worked.

Fast forward again (only ~2 years later). The AI not only builds the app, it builds the website, the marketing, full documentation, GIFs, videos, content, screen recordings. It even hosts it online (literally controls the browser and configures everything). Letting the agent control the browser and the tooling around that is really, genuinely, just mad science fiction type magic stuff. It's unbelievable how often these models get something mostly right.

The reality though is that it still takes time. Time to understand what works well and what works better. Which agent is good for building apps, which one is good for frontend design, which one is good for research. Which tools are free, paid, credit-based, API-based. It all matters if you want to control costs and just get better outputs.

Do you use Gemini for a website skeleton? Claude for code? Grok for research? Gemini Deep Search? ChatGPT Search? Both? When do you use plan mode vs just prompting? Is GPT-5.x better here or Claude Opus? Or maybe Gemini actually is.

My point is: while anyone can start prompting an agent, it still takes a lot of trial and error to develop intuition about how to use them well. And even then everything you learn is probably outdated today because the space changes constantly.

I'm sure there are people using AI 100× better than I am. But it's still insane that someone with no coding background can build production-grade things that actually work.

The one-person company feels inevitable.

I'm curious how software engineers think about this today. Are you still writing most of your code manually?

Wait 5-10 minutes, and should be done.

It genuinely is that simple.

You can even use local models using claude code or codex infrastrucutre (MASSIVE UNLOCK), but you need solid GPU(s) to run decent models. So that's the downside.