Archive position — measured, not model output
0 likes on Devpost
2,264 of the 7,856 archived projects have more likes, and 5,592 share exactly 0 — so this project's #7,157 place in the like-ranked listing is a tie-break inside that group, not a ranking.
Projects (log scale)
Likes on Devpost. ▲ marks this project's group.
Show the figures
| Likes | Projects | Share of archive |
|---|---|---|
| 0 | 5,592 | 71.2% |
| 1 | 1,758 | 22.4% |
| 2 | 285 | 3.6% |
| 3–4 | 132 | 1.7% |
| 5–9 | 75 | 1.0% |
| 10+ | 14 | 0.2% |
Executive Summary
What the company appears to be
TaxProof Solo is a self-reported tax assistant for Canadian contractors, built as a hackathon project. It claims to help British Columbia sole proprietors in 2026 reconcile receipts, transactions, and tax obligations using AI and deterministic financial arithmetic.
What changed
The author states that the product was built as a vertical slice focused on one persona: a British Columbia sole proprietor with employment income, Canadian and US clients, and simple operating expenses. It uses GPT-5.6 for document interpretation and a TypeScript engine for tax calculations.
Single most important open question
Is there any evidence of traction, revenue, or customer adoption beyond the author’s own demonstration?
What The Product Actually Is
The description states that TaxProof Solo is an evidence-first tax assistant designed to help Canadian contractors turn receipts, invoices, and transactions into a defensible tax reserve, deduction ledger, and year-end action plan.
It allows users to explore a synthetic workspace or upload PDF, image, and CSV records. It answers four practical questions:
- How much should I reserve for income tax and CPP?
- Which expenses are supported by evidence?
- Which deductions need more evidence or should be rejected?
- Which actions could improve my position before year-end?
It also tracks cumulative revenue and warns when the GST small-supplier threshold may have been crossed.
The signature experience is “Why this number?”, which shows:
- Facts directly supported by documents
- Facts inferred from context
- Relevant source excerpts
- The tax rule applied
- Deterministic calculation steps
- Confidence and materiality
- Missing evidence
- A history of changes to the conclusion
It uses GPT-5.6 through OpenAI Responses API for document interpretation, and a pure TypeScript engine for financial arithmetic.
Evidence
- The author describes how it works.
- It is built with React, TypeScript, Vite, Tailwind CSS, Cloudflare Pages Function, and OpenAI APIs.
- It uses Zod to validate structured outputs from GPT-5.6.
- It separates document interpretation (GPT) from financial arithmetic (deterministic code).
- It includes a demonstration of receipt-to-transaction reconciliation.
Inference The product is a prototype or vertical slice, not full tax filing software.
Positioning & Claim Evolution
The author states that the idea for TaxProof Solo came from trying to answer “How much of the cash in my account is actually mine?” when considering independent contracting in Canada. The goal was to build something more defensible than a generic chatbot.
It positions itself as:
- An evidence-backed tax assistant
- A tool for contractors to understand their financial position before year-end
- A system that shows how conclusions are reached, not just what they are
Evidence
- The author describes the inspiration and intent.
- It is positioned as a solution to problems that arise before filing time.
Inference The product is framed as a tool for personal use or early-stage contractor planning, not for professional tax preparation or compliance.
Target Customer & ICP
The description states that the initial version is intentionally focused on:
- A British Columbia sole proprietor
- In the 2026 tax year
- With employment income earlier in the year
- Canadian and US clients
- Simple operating expenses
- Available RRSP or FHSA contribution room
Evidence
- The author explicitly defines this persona.
- It is described as a vertical slice, not a full solution for all contractors.
Inference The target customer is a specific type of contractor — likely early-stage, self-employed individuals in BC with relatively simple tax situations.
Business Model & Pricing Evidence
There is no evidence of pricing, business model or monetization strategy in the description.
Evidence
- No mention of fees, subscriptions, or revenue streams.
- The product is described as a hackathon project with no commercial deployment.
Inference The business model is not evident from this self-reporting description.
Technical & Delivery Signals
The author states that:
- GPT-5.6 is used via OpenAI Responses API for document interpretation
- A TypeScript engine handles financial arithmetic
- The frontend is built with React, TypeScript, Vite, and Tailwind CSS
- Cloudflare Pages Function calls the OpenAI API to avoid exposing credentials
- Zod validates structured outputs from GPT-5.6
- The system separates AI interpretation from deterministic calculation
Evidence
- Technology stack is listed.
- The architecture is described as separating AI document parsing from financial logic.
Inference The product uses a hybrid approach of AI and deterministic code, with an emphasis on traceability and reproducibility.
Traction & Maturity Signals
There is no evidence of traction or adoption beyond the author’s own demonstration. The project is described as a hackathon submission.
Evidence
- No mention of users, customers, or revenue.
- It is explicitly stated to be a vertical slice, not full software.
- No data on usage, retention, or growth.
Inference The product has no demonstrated traction or market validation.
Competitive Context
The description does not provide any information about competitors or the broader tax software landscape.
Evidence
- No mention of existing tools or platforms in this space.
- No comparison to other tax software or AI assistants.
Inference No competitive positioning is evident from the self-reporting description.
Key Risks & Red Flags
Key risks and red flags based on the description:
- The product is a hackathon project with no commercial traction.
- It is limited to one specific persona (British Columbia sole proprietor, 2026 tax year).
- It does not support complex scenarios like corporations, partnerships, trusts, or capital gains.
- It uses GPT-5.6 for document interpretation but not for financial arithmetic — a design choice that may limit scalability or accuracy.
- No evidence of user testing beyond manual checks.
Evidence
- The author explicitly states scope limitations.
- It is described as a vertical slice, not a full product.
Inference The product is not yet ready for commercial use and lacks broad market applicability.
Diligence Questions To Ask The Founders
- What is the actual business model or monetization strategy?
- How does the team plan to expand beyond the current vertical slice (British Columbia sole proprietor, 2026)?
- Has there been any user feedback or testing beyond the author’s own manual checks?
- Are there plans for regulatory compliance or legal validation of tax advice?
- What are the technical limitations of GPT-5.6 in handling real-world tax documents?
- How does the product handle edge cases or ambiguous data?
Investment/Partnership Verdict
Not evidenced.
The description is a self-reported account of a hackathon project with no evidence of traction, revenue, customers, or commercial viability.
Confidence Low — based on thin evidence and lack of independent validation.
Inference This appears to be an early-stage prototype or proof-of-concept, not a product ready for investment or partnership.
Source
Submitted to the OpenAI 2026 hackathon on Devpost. Project home on DevPost.
The analysis above was generated by a language model from the project's own one-line description. It is not independent research and contains no verified traction, revenue or customer data.