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 #4,104 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
FindMyScent 2.0 is a self-reported AI-powered fragrance recommendation tool designed for Indonesian users seeking perfume guidance based on natural language preferences. The product uses GPT-5.6 and a curated fragrance catalog to interpret user requests, filter candidates, and produce explainable recommendations.
What changed
The author describes rebuilding the original FindMyScent app as a standalone product with enhanced AI integration, specifically targeting personal decision-making around fragrance choices using conversational input rather than traditional quizzes or filters.
Single most important open question
Is there evidence of any actual user base, revenue, or customer traction beyond the author's own description?
What The Product Actually Is
The description states that FindMyScent 2.0 is an AI perfume consultation and decision assistant. It allows users to describe what they are looking for in their own words without needing fragrance terminology.
It uses:
- GPT-5.6 for natural language understanding, preference extraction, and decision-making
- A backend system that handles catalog retrieval, filtering, scoring, and validation
- A curated Indonesia-first fragrance catalog
The system produces a decision report including:
- Best Match
- Alternative
- Why it fits
- What to consider
- Trade-off
- Confidence
- A Buy Link
Users can refine their preferences during the consultation process without restarting.
Evidence Self-reported by author. No independent verification or demonstration provided.
Positioning & Claim Evolution
The description states that FindMyScent 2.0 was built as a new standalone product for ordinary fragrance shoppers, beginner influencers, and anyone who loves smelling good.
It positions itself as:
- An AI-powered decision assistant
- Not pretending to smell perfumes or guarantee user satisfaction
- A tool to provide clearer, more honest starting points for personal decisions involving taste, budget, occasion, comfort, and trade-offs
The author claims it evolved from a simpler fragrance discovery app (the first version) to this new product focused on conversational input and contextual reasoning.
Evidence Self-reported. No external validation or market positioning data provided.
Target Customer & ICP
The description states that FindMyScent 2.0 is designed for:
- Ordinary fragrance shoppers
- Beginner perfume influencers
- Anyone who loves smelling good
It targets people who want to make personal decisions involving how they want to feel, be perceived, where they will wear it, and how much they are willing to spend.
The author notes that the original inspiration came from observing common questions in social media and their own experience as a multi-brand perfume decant seller.
Evidence Self-reported. No specific customer segments or personas defined beyond general categories.
Business Model & Pricing Evidence
Not evidenced.
The description does not mention any pricing structure, monetization strategy, or business model details.
Technical & Delivery Signals
The system architecture is described as:
- Layered recommendation architecture
- Backend layer handles catalog retrieval, filtering, scoring, validation
- GPT-5.6 acts as language reasoning and final decision layer
- Separation between deterministic logic and model reasoning
- Human-in-the-loop development process using Codex
The author states that the backend enforces hard constraints such as budget, catalog availability, and usage context.
Evidence Self-reported. No technical documentation or delivery evidence provided beyond developer claims.
Traction & Maturity Signals
Not evidenced.
There is no mention of:
- Revenue
- Customers
- User engagement metrics
- Product adoption
- Market traction
- Any form of user feedback or testing results
The project is described as a hackathon submission with no indication of ongoing development or market presence.
Competitive Context
Not evidenced.
The description does not provide information about:
- Competitors in the fragrance recommendation space
- Market size or competitive landscape
- Differentiation from existing tools
- Industry positioning or benchmarks
Key Risks & Red Flags
Risk 1
The product is described as a hackathon submission with no evidence of real-world usage or customer validation.
Risk 2
The system relies heavily on GPT-5.6 for decision-making, but the author notes that LLMs can produce convincing outputs even when facts are inaccurate, which could lead to misleading recommendations if not properly grounded.
Risk 3
The curated catalog is described as Indonesia-first, suggesting limited geographic scope and potential scalability issues.
Risk 4
The author states they are not primarily a hands-on programmer, raising questions about technical depth and product quality control.
Red Flag
No evidence of any revenue, customers, or traction beyond the author's own account.
Diligence Questions To Ask The Founders
- What is your actual user base? Have you tested this with real people?
- How do you validate that GPT-5.6 outputs are accurate and aligned with the curated catalog?
- Can you demonstrate how the system handles ambiguous or contradictory user inputs?
- What is your plan for expanding beyond Indonesia?
- How do you ensure the fragrance data in your catalog remains current and accurate?
- Have you considered how to handle skin chemistry differences that affect perfume perception?
Investment/Partnership Verdict
Not evidenced.
There is no information provided about:
- Valuation
- Funding rounds
- Financial performance
- Strategic partnerships
- Market opportunity size
- Go-to-market strategy
The project is described as a hackathon submission with no indication of commercial viability or traction beyond the author's own claims. The lack of any measurable outcomes, revenue data, or customer evidence makes it impossible to assess its investment potential or partnership value.
Confidence Level Low — based entirely on self-reported information without corroboration or demonstration of product-market fit or commercial traction.
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.