OpenAI 2026 hackathon

CANADIAN RETIREMENT INTELLIGENCE

TwinTigers is an AI retirement planner built 95% with Codex in last 3 months. It tests thousands of tax, spending, CPP/OAS and withdrawal strategies to show how much you can safely spend.

Solo project by George XU · 1 likes · 0 comments

Archive position — measured, not model output

1 like on Devpost

506 of the 7,856 archived projects have more likes, and 1,758 share exactly 1 — so this project's #755 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: Canadian Retirement Intelligence (CRI) is a self-described AI retirement planning platform for Canadians, built by a single developer using OpenAI Codex over ~3 months. The product claims to evaluate thousands of retirement strategies across tax, spending, CPP/OAS, and withdrawal rules, offering recommendations in plain language.

What changed: The project was submitted as part of the OpenAI 2026 hackathon. It represents a one-person team's attempt to build an enterprise-grade financial planning tool using AI-assisted development methods.

Single most important open question: Is there any evidence that CRI has been used by actual users or tested in real-world scenarios beyond the author’s own development experience?

This analysis is based entirely on the self-reported, unverified description provided by the project author. No third-party data, revenue figures, customer names, or traction metrics are available.

Back to contents

What The Product Actually Is

  • The description states that CRI evaluates thousands of retirement strategies across:
    • Spending
    • RRSP and RRIF withdrawals
    • CPP and OAS timing
    • Taxes
    • Investment growth
    • Government-benefit clawbacks
    • Estate goals
  • It compares alternatives, identifies stronger strategies, and explains results in plain language.
  • The platform includes a tax test-case generator that converts scenarios into structured tax cases for external validation.
  • It supports three user roles:
    • Administrators (manage users and templates)
    • Financial advisers (manage client workspaces and plans)
    • Clients (read-only access to results)

Inference: Based on the author’s claims, CRI appears to be a multi-user financial planning platform with backend logic for retirement strategy modeling and tax validation. However, no evidence of actual deployment or usage exists.

Back to contents

Positioning & Claim Evolution

  • The description states that CRI aims to answer key questions retirees care about most:
    • Can I retire?
    • How much can I safely spend?
    • Will my money last?
    • What will my family inherit?
    • What should I do now?

Claim: The platform is positioned as an intelligent, transparent, explainable, and independently verifiable decision-support tool for Canadian retirement planning.

Inference: CRI positions itself as a solution to the problem of static projections in retirement tools, aiming for optimization and clarity. It also implies it can be used by both individuals and financial advisers.

Back to contents

Target Customer & ICP

  • The description mentions that CRI supports three user roles:
    • Administrators
    • Financial advisers
    • Clients

Claim: The platform targets individuals planning retirement, as well as financial professionals managing client plans.

Inference: While the author describes a multi-user system, there is no evidence of actual customers or user adoption beyond the developer’s own use case.

Back to contents

Business Model & Pricing Evidence

  • No pricing information, subscription model, or monetization strategy is described.
  • The description does not mention any revenue streams or business model.

Not evidenced

Back to contents

Technical & Delivery Signals

  • Built with:
    • HTML, JavaScript, Java
    • Railway, scripts, Tomcat
  • Developed by a one-person team in ~3 months using Codex (GPT-5.6)
  • The author claims Codex helped implement:
    • Calculation engine
    • Strategy optimizer
    • Scenario generation/management
    • Dashboards, reports, tax-validation tools
    • User management, testing, configuration, deployment

Claim: A single developer with extensive enterprise experience used AI to rapidly prototype and build a complex financial platform.

Inference: The use of Codex is presented as a key enabler for rapid development. However, no evidence exists that this approach has been validated in production or at scale.

Back to contents

Traction & Maturity Signals

  • No evidence of:
    • Revenue
    • Customers
    • Usage metrics
    • Product-market fit
    • Deployment history
    • User feedback or testing

Not evidenced

Back to contents

Competitive Context

  • No mention of competitors, market size, or competitive positioning.
  • The description does not reference existing retirement planning tools or platforms in the Canadian market.

Not evidenced

Back to contents

Key Risks & Red Flags

  • Unverified claims: All features and capabilities are self-reported without independent verification.
  • No traction: No evidence of real-world usage, customers, or revenue.
  • AI dependency risk: Heavy reliance on Codex raises concerns about reproducibility, scalability, and quality control if the tool becomes unavailable or changes.
  • Single-person team: While experienced, a single developer may not be sufficient to handle full product lifecycle, especially in complex domains like financial planning.
  • Lack of transparency: The platform’s internal logic is described but not demonstrated through external validation.

Inference: The project appears experimental and lacks commercial maturity or proof-of-concept beyond the author's own development process.

Back to contents

Diligence Questions To Ask The Founders

  1. What specific financial rules or models were implemented, and how were they validated?
  2. Has the platform been tested with real-world data or scenarios?
  3. Are there any external validations of the tax calculations or retirement strategies?
  4. How does the team plan to scale beyond a single developer?
  5. What is the roadmap for monetization or commercialization?

Back to contents

Investment/Partnership Verdict

  • The description presents an ambitious idea with strong technical execution claims, but lacks evidence of traction, revenue, or user adoption.
  • The project appears to be an experimental prototype built under tight time constraints using AI tools.
  • There is no indication that CRI has moved beyond the development phase or achieved any level of market validation.

Verdict: Not ready for investment or partnership. Requires further demonstration of real-world usage, validation, and commercial viability before any serious consideration.

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.