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 #3,197 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: Chalkbox is a self-service tool for teachers to generate interactive math and physics manipulatives using AI. The author states it allows educators to type a misconception and receive a live, draggable component that students can interact with on their phones.
What changed: The project description shows an early-stage prototype built for a hackathon. It includes a working generation engine with verification loops, automated tests, and CI/CD infrastructure — but no evidence of revenue, customers or adoption beyond the author's own claims.
The single most important open question: Is there any evidence that teachers actually use this tool in classrooms, or that it has been tested with real students?
Note: This analysis is based entirely on the self-reported project description provided by the caller. No external verification or historical data exists for this project. All claims are treated as stated by the author and not independently confirmed.
What The Product Actually Is
The description states that Chalkbox allows teachers to type a misconception they want to address, and in about a minute receives a live, draggable manipulative that students can open on any phone. It is described as:
- A single-file interactive React component
- Built with Codex (GPT-5.6) and verified via headless testing
- Published under a strict no-network CSP
- Limited to math and physics manipulatives only
It uses a verification loop involving:
- GPT-5.6 Luna triage
- AST-level static validation
- Headless rendering + invariant probe execution
- Output-safety scan before publishing
The author claims this is not just a demo, but a real product with live generation and testing.
Inference: The system appears to be an AI-powered tool that generates interactive educational components for teachers, using a multi-stage verification pipeline.
Positioning & Claim Evolution
The author positions Chalkbox as solving a specific gap in education: teachers cannot create manipulatives themselves, but research shows they are effective at breaking misconceptions. The core claim is:
"Chalkbox exists to close exactly that gap, and nothing else."
It emphasizes:
- No-code experience for teachers
- Live, interactive components on student phones
- Verification loop that ensures correctness
- Narrow scope (math/physics only) to enable strong verification
There is no indication of broader positioning beyond this niche use case.
Claim: Chalkbox is a tool for educators to generate interactive learning materials without coding skills.
Inference: The positioning evolved from solving a specific pedagogical problem to building a productized workflow around AI-assisted authoring.
Target Customer & ICP
The description states that the primary user is a teacher — specifically:
- Ms. Alvarez, a 6th-grade math teacher
- Teaching 32 kids at three ability levels
- Facing a specific misconception: "dividing by a fraction makes the answer smaller"
The author also notes:
- The tool is built for someone who can't code
- It targets classroom-level educators
No evidence of other personas or segments (e.g., curriculum developers, schools, EdTech vendors) is provided.
Claim: Teachers in K–12 settings are the primary users.
Inference: The ICP appears to be teachers working with math and physics misconceptions who lack technical skills.
Business Model & Pricing Evidence
There is no mention of pricing, monetization or business model in the description. The author does not state whether Chalkbox will charge for access, offer freemium tiers, or sell subscriptions.
Not evidenced
Technical & Delivery Signals
The project was built using:
- Codex (GPT-5.6)
- GitHub Actions
- Next.js 15 / React 19 / TypeScript / Tailwind v4
- Supabase, Vercel
- Playwright E2E tests
- Vitest unit tests
- CodeQL CI gate
It includes:
- Four verification gates (triage, static checks, self-test, output safety)
- SSE server route to keep keys off client
- Probe cross-check mechanism to prevent generator from cheating
- Bench honesty guard to detect stub fallbacks
- Demo mode labeled and guarded by opt-in
Claim: The system is built with a robust verification pipeline, automated tests, and CI/CD.
Inference: The technical stack suggests a modern SaaS-like architecture, though it's not yet production-ready.
Traction & Maturity Signals
The description does not provide any evidence of:
- Revenue
- Customers or users
- Adoption metrics
- Product usage data
- Market traction beyond the hackathon submission
It mentions:
- 54 automated tests
- 28 unit + 26 Playwright E2E tests
- CI with CodeQL
- A bench that tracks success rates (but not actual usage)
Not evidenced
Competitive Context
No mention of competitors or market context is provided in the description. The author does not reference existing tools for creating educational manipulatives, nor does it compare Chalkbox to similar offerings.
Not evidenced
Key Risks & Red Flags
- Unproven adoption: No evidence that teachers actually use the tool or find value in it.
- Limited scope: Narrow focus on math/physics may limit scalability.
- Dependency on AI quality: Reliance on Codex (GPT-5.6) for generation and verification introduces risk if performance degrades.
- Lack of commercial viability: No pricing, monetization or business model discussed.
- Demo vs. real-world use: The system is described as working in demos but not tested with real classrooms.
Inference: The project is an early prototype with strong engineering but unclear path to market traction or revenue.
Diligence Questions To Ask The Founders
- Have you conducted any pilot testing with actual teachers?
- What is the current status of the product beyond the hackathon demo?
- How do you plan to monetize this tool?
- Are there any real-world users or feedback from educators yet?
- What are the long-term plans for expanding beyond math and physics?
- How do you ensure consistent performance across different AI generations?
Investment/Partnership Verdict
The project is an early-stage prototype built by one person (Edy Cu) for a hackathon. It demonstrates:
- Strong technical execution
- A clear understanding of the problem space
- A working verification pipeline
However, there is no evidence of traction, revenue, or customer adoption.
Verdict: Not ready for investment or partnership at this stage. The product shows promise in solving a real educational need but lacks commercial validation and market readiness.
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.
