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 #6,011 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
Poker IA is a self-reported offline poker training simulator for No-Limit Texas Hold'em, built by one developer (Ryan CHARLES) during OpenAI Build Week. It records player decisions in simulated sessions and generates coaching feedback including decision-quality scores, EV loss estimates, replay links, and personalized training plans.
What changed
The project evolved from a basic poker simulation tool into a “Session Coach” feature that adds post-session analysis and learning plan generation. This was built using AI tools like Codex and GPT-5.6 during the hackathon extension.
Single most important open question
Is there any evidence of user adoption, usage frequency, or feedback from real players beyond the author’s own account?
What The Product Actually Is
The description states that Poker IA is an offline No-Limit Texas Hold'em training simulator for two to eight players using fictional chips. It records player decisions and keeps a complete history on the device.
It includes:
- A local strategy engine estimating available actions;
- A new “Session Coach” feature that turns completed sessions into:
- Decision-quality score out of 100;
- Cumulative estimated EV loss in big blinds;
- Three costliest decisions with direct replay links;
- Personalized training plan;
- Measurable strengths;
- Downloadable Markdown coaching report.
The system is described as local-only, not connecting to external poker platforms or real money games. It is a learning tool, not a profit-generating platform.
Evidence
- The author describes the product as an offline simulator.
- Session Coach features are detailed in the write-up.
- No mention of live play, betting, or integration with real poker sites.
Not evidenced
- Whether any of these features have been tested by users beyond the developer.
- If the system supports multiplayer online or cloud-based sessions.
- Any actual implementation details beyond what is described.
Positioning & Claim Evolution
The project positions itself as a private, local poker training coach, aiming to turn decision quality into an actionable learning plan. The tagline emphasizes privacy and personalization.
Evolution of claims
- Initially, Poker IA was a basic simulation tool.
- During Build Week, it added the “Session Coach” functionality.
- The author highlights that this new component focuses on understandable feedback, not raw statistics.
Inference The shift from a generic simulator to a structured coaching system suggests an evolution in user value proposition — moving from gameplay to learning outcomes.
Evidence
- The write-up explicitly mentions the transition from baseline to Session Coach.
- The author emphasizes the importance of outcome-independent scoring and simplicity of output.
Not evidenced
- No evidence of how users perceive or respond to the coaching features.
- No indication of whether this is a standalone tool or part of a larger ecosystem.
Target Customer & ICP
The description states that Poker IA is designed for poker players who want to improve their decision-making skills in No-Limit Texas Hold'em. It targets individuals interested in private, local training, not those seeking real-money play or platform integration.
Inference
Given the offline nature and focus on personal improvement, the ICP likely includes:
- Casual or semi-professional players;
- Self-taught learners;
- People from regions like Martinique where access to structured poker education may be limited.
Evidence
- The author identifies as an independent, non-technical creator from Martinique.
- The product is framed as a tool for personal development, not competitive play or monetization.
Not evidenced
- No data on actual users or their demographics.
- No indication of whether the tool appeals to professionals or hobbyists.
- No mention of marketing channels or user acquisition strategies.
Business Model & Pricing Evidence
The description does not provide any information about a business model or pricing. It is clear that the project is not monetized — it does not involve real money, betting, or commercial transactions.
Evidence
- The product explicitly states it does not connect to poker platforms, observe external tables, place bets, or use real money.
- No mention of subscriptions, purchases, or revenue streams.
Inference
If the tool were to scale, potential monetization could come through:
- Premium features;
- Coaching services;
- Integration with other learning platforms.
But none of these are suggested in the current description.
Not evidenced
- Any pricing structure.
- Revenue model.
- Commercial partnerships or plans.
Technical & Delivery Signals
The project is built using:
- Backend: FastAPI, Python
- Frontend: React, TypeScript
- Database: SQLite
- AI tools used: Codex, GPT-5.6
- Testing: 117 backend tests, 38 frontend tests, 26 Chromium scenarios
The author also notes that the repository separates pre-hackathon and post-hackathon work for review.
Evidence
- The technical stack is listed in the project description.
- Test coverage numbers are provided.
- AI tools were used to assist with development.
Inference The use of AI tools suggests a rapid prototyping approach, possibly aimed at accelerating feature delivery during the hackathon.
Not evidenced
- No indication of scalability or performance metrics beyond test counts.
- No mention of deployment infrastructure or cloud usage.
- No evidence of production readiness or long-term architecture planning.
Traction & Maturity Signals
There is no evidence of traction, such as:
- User base
- Active usage
- Customer feedback
- Revenue
- Market validation
The project appears to be a personal prototype built during a hackathon, with no external validation or adoption reported.
Evidence
- The author describes being an independent creator.
- No mention of users beyond the developer.
- No data on how often the tool is used or how it’s received by others.
Inference The lack of traction suggests that the project has not yet entered a phase of real-world use or product-market fit.
Not evidenced
- Any user engagement metrics.
- Customer testimonials or reviews.
- Growth indicators like downloads, active sessions, or retention.
Competitive Context
There is no evidence of competitors mentioned in the description. The author does not reference existing poker training tools or platforms.
Evidence
- No competitive analysis or comparison to other simulators or coaching apps.
Inference It’s possible that this tool operates in a niche market, or that the author has not researched the broader landscape.
Not evidenced
- Any awareness of similar products.
- Market size or competitive positioning.
- Whether there are established players in poker education or simulation.
Key Risks & Red Flags
Key risks and red flags based on the self-reported information:
- No traction or adoption: The project is described as a prototype, with no evidence of real-world usage.
- Single-person development: With only one team member (the author), scalability and long-term maintenance are concerns.
- Limited validation: No user feedback, reviews, or performance data to validate the effectiveness of the coaching features.
- Unproven business model: The tool is not monetized, and there’s no indication of how it might evolve into a sustainable product.
- AI dependency: Heavy reliance on AI tools for development raises questions about reproducibility and future maintainability.
Evidence
- All of the above points are drawn from the lack of evidence in the description.
Not evidenced
- No mention of risks or challenges faced during development.
- No indication of how the tool might be integrated into a larger ecosystem.
Diligence Questions To Ask The Founders
- What is your definition of “decision quality” and how was it implemented?
- Have you tested the Session Coach with other players, or is it based solely on your own experience?
- How do you plan to validate that the training plans are actionable and effective for users?
- Are there any plans to expand beyond offline use or add multiplayer features?
- What would be the next steps if you wanted to scale this into a product with broader adoption?
Investment/Partnership Verdict
Not evidenced
There is no evidence of:
- Revenue
- Customers
- Traction
- Market validation
- Product-market fit
The project is described as a personal prototype, built during a hackathon, without any indication of commercial viability or user adoption.
Inference At this stage, the project is more of an experiment than a scalable business. It may have potential for further development but lacks the signals needed to assess investment or partnership value.
Confidence level Low — due to lack of evidence beyond self-reporting and absence of any commercial data or user feedback.
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.