OpenAI 2026 hackathon

Selyo AI — Gemini-Powered Compliance for Filipino MSMEs

Offline-first compliance OS for 1.1M Filipino MSMEs — BIR receipts, sealed on a hash chain.

Solo project by Nisi Ryan Cruz · 0 likes · 0 comments

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 #6,619 place in the like-ranked listing is a tie-break inside that group, not a ranking.

Projects (log scale)

1
10
100
1k
10k
05,592
11,758
2285
3–4132
5–975
10+14

Likes on Devpost. ▲ marks this project's group.

Show the figures
LikesProjectsShare of archive
05,59271.2%
11,75822.4%
22853.6%
3–41321.7%
5–9751.0%
10+140.2%
Devpost like counts for all 7,856 archived projects, captured when this archive was built.

Executive Summary

What the company appears to be

Selyo AI is a self-reported offline-first compliance operating system for Filipino MSMEs, built as a hackathon submission. It claims to offer BIR (Bureau of Internal Revenue) receipt generation and sealing via a hash chain, using Gemini-powered AI.

What changed

The project was submitted to the OpenAI 2026 hackathon, indicating it is in early development or prototype stage. No prior traction, revenue, or customer data are evidenced.

Single most important open question

Is there any evidence of actual use by Filipino MSMEs, or even a functional prototype that demonstrates compliance functionality?

Back to contents

What The Product Actually Is

The description states:

"Selyo AI — Gemini-Powered Compliance for Filipino MSMEs"

It also says:

"Offline-first compliance OS for 1.1M Filipino MSMEs — BIR receipts, sealed on a hash chain."

Inference Based on the author’s own write-up and technology stack, Selyo AI is described as an offline-first system that uses AI (via Gemini API) to generate BIR receipts and seal them using a cryptographic hash chain. The system is intended for Filipino MSMEs.

Evidence

  • Tagline: "Offline-first compliance OS for 1.1M Filipino MSMEs — BIR receipts, sealed on a hash chain."
  • Technology stack includes: capacitor, cloudflare-pages, gemini-api, hmac-sha256, indexeddb, neon-postgres, react, typescript, vite, webgpu.

Not evidenced

  • Whether the system actually generates or seals BIR receipts.
  • Whether it is functional or has been tested with real users.
  • The nature of the "hash chain" implementation.
  • Any integration with actual BIR systems or APIs.

Back to contents

Positioning & Claim Evolution

The description states:

"Selyo AI — Gemini-Powered Compliance for Filipino MSMEs"

"Offline-first compliance OS for 1.1M Filipino MSMEs — BIR receipts, sealed on a hash chain."

Claim

The project positions itself as an offline-first compliance tool for Filipino MSMEs using AI and cryptographic sealing.

Inference It appears to be a hackathon entry that attempts to solve the problem of compliance for small businesses in the Philippines by leveraging AI and blockchain-like technologies (hash chaining). The positioning is narrow, focused on a specific local market segment.

Not evidenced

  • No evolution or prior claims.
  • No evidence of prior versions or product development stages.
  • No indication of how this differs from existing tools or platforms for MSME compliance.

Back to contents

Target Customer & ICP

The description states:

"Offline-first compliance OS for 1.1M Filipino MSMEs"

Claim

The target customer is Filipino MSMEs, with an estimated population of 1.1 million.

Inference The project is aimed at small and medium-sized enterprises in the Philippines, likely those without robust digital infrastructure or access to formal compliance tools.

Not evidenced

  • No evidence of customer research or segmentation.
  • No indication of how the team identified this specific group.
  • No evidence of any user interviews or feedback from MSMEs.
  • No mention of whether the system is designed for individual entrepreneurs, sole proprietors, or larger MSMEs.

Back to contents

Business Model & Pricing Evidence

The description states:

"Offline-first compliance OS for 1.1M Filipino MSMEs — BIR receipts, sealed on a hash chain."

Claim

No explicit business model or pricing is stated.

Inference Given that this is a hackathon submission and the team size is listed as one, there is no evidence of a monetization strategy or pricing model. The system appears to be conceptual or experimental.

Not evidenced

  • No pricing information.
  • No indication of whether it will be free, subscription-based, or pay-per-use.
  • No mention of revenue streams or monetization plans.
  • No evidence of any commercial relationship with BIR or government entities.

Back to contents

Technical & Delivery Signals

The description states:

"Built with (author-declared): capacitor, cloudflare-pages, cloudflare-workers, drizzle-orm, express.js, gemini-api, google-cloud-run, hmac-sha256, indexeddb, neon-postgres, pnpm, radix-ui, react, tailwind-css, typescript, vite, webgpu"

Claim

The system is built using a modern tech stack including React, TypeScript, and cloud services like Cloudflare Workers and Google Cloud Run.

Inference It appears to be a frontend-heavy, cloud-native application with offline capabilities (indexeddb), cryptographic features (hmac-sha256), and AI integration (Gemini API). The use of capacitor suggests it may be a cross-platform mobile or web app.

Not evidenced

  • No evidence of actual functionality.
  • No demonstration or prototype available.
  • No information on how offline-first works in practice.
  • No explanation of how the hash chain is implemented or used for sealing receipts.

Back to contents

Traction & Maturity Signals

The description states:

"Source: https://devpost.com/software/selyo-sovereign-offline-first-invoicing-shield"

"Team size: 1"

Claim

This is a hackathon submission, and the team consists of one person.

Inference There is no evidence of traction or product maturity. The project is in an early stage, likely conceptual or prototype-level.

Not evidenced

  • No customer base.
  • No revenue or ARR.
  • No user feedback or adoption data.
  • No evidence of a functioning product or MVP.
  • No mention of any follow-up or development post-hackathon.

Back to contents

Competitive Context

The description states:

"Selyo AI — Gemini-Powered Compliance for Filipino MSMEs"

Claim

No direct competitors are mentioned, but the idea of compliance tools for MSMEs is not novel.

Inference There are likely existing platforms or government systems for MSME compliance in the Philippines (e.g., BIR e-filing, other invoicing apps). The project’s positioning as an offline-first, AI-powered solution may differentiate it from traditional tools, but no evidence of competitive analysis is provided.

Not evidenced

  • No mention of competitors.
  • No indication of market research or competitive landscape.
  • No comparison to existing solutions for MSME compliance in the Philippines.

Back to contents

Key Risks & Red Flags

Claim

This project is a hackathon submission by a single person, with no evidence of traction or product development.

Inference

Key risks include:

  • Lack of product-market fit validation.
  • No evidence of real-world use or testing.
  • Single-person team may limit execution capability.
  • The claim of "BIR receipts sealed on a hash chain" is not substantiated.
  • No commercial viability or monetization strategy evident.

Not evidenced

  • No risk assessment or mitigation strategies.
  • No indication of regulatory compliance or legal issues with BIR integration.
  • No evidence of scalability or long-term roadmap.

Back to contents

Diligence Questions To Ask The Founders

  1. What is the actual functionality of Selyo AI? Can you demonstrate how it generates and seals BIR receipts?
  2. How does the offline-first design work in practice, and what are the limitations?
  3. Is there any integration with real BIR systems or APIs?
  4. What is the technical implementation of the hash chain used for sealing receipts?
  5. Have you tested this with actual Filipino MSMEs? If so, what were their feedback and adoption rates?
  6. Is this a one-off hackathon project, or are you planning to build it further?

Back to contents

Investment/Partnership Verdict

Claim

This is a self-reported hackathon submission by one person.

Inference At this stage, there is no evidence of a viable product, traction, or business model. The project appears to be conceptual and experimental. It lacks any commercial due-diligence signals such as revenue, customers, or even a functional prototype.

Not evidenced

  • No financials.
  • No customer data.
  • No market validation.
  • No indication of future development plans beyond the hackathon.

Verdict This is not ready for investment or partnership consideration. It is a speculative idea with no demonstrated value or traction. Further development and evidence of product-market fit are required before any due-diligence evaluation can be meaningful.

Back to contents

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.