Ledger: A Small-Business Finance Tracker with Groq-Hosted Open-Weight AI
Description and use
Ledger is a lightweight finance tracker for solo business owners that leverages Groq’s open‑weight model for AI‑assisted transaction drafting and price calculation.
Problem
Solo business owners and freelancers need a simple way to record income and expenses, review totals, and estimate product or service prices without a full accounting suite.
Outcome
Ledger delivers a lightweight finance tracker with AI‑assisted drafting and pricing, reducing manual effort for small‑business owners. It demonstrates how an open‑weight model can be integrated via an OpenAI‑compatible API, keeping business logic separate from AI suggestions.
Workflow
- 1. User enters transaction details or selects AI draft mode.
- 2. Server sends text to Groq via OpenAI SDK and receives JSON‑formatted draft.
- 3. Server validates amounts, dates, and evidence before presenting draft to user.
- 4. User reviews and confirms draft, then it is saved as a transaction.
- 5. For pricing, user inputs cost and markup; AI provides qualitative advice.
- 6. Application calculates price using formula (unit cost + additional costs per unit) × (1 + markup percentage / 100).
- 7. User can save the price as a pricing record, search, filter, edit, or delete it.
- 8. All records are scoped by a business ID but no authentication is yet implemented.
Evidence
Ledger is a small‑business finance tracker and AI pricing assistant for solo business owners and freelancers.
Both AI flows use the same Groq client and configured model. The server uses the OpenAI SDK with Groq's OpenAI‑compatible endpoint:
The default model ID is openai/gpt-oss-120b.
For transaction entry, Ledger asks the model for JSON‑formatted drafts, then validates the response on the server and checks whether amounts and dates are supported by evidence in the user's original text.
One limitation: Ledger does not yet authenticate users or establish business ownership.
- Record date: 2026-10-19T01:41:32.672Z