OpenAI 2026 hackathon

PreguntaLab

Plataforma educativa que ayuda a crear preguntas tipo Saber con IA, criterios pedagógicos y enfoque curricular, sin necesidad de conocimientos técnicos.

Solo project by Danny Galindo · 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 #6,055 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

PreguntaLab is a self-reported educational platform designed to help teachers create and administer Saber-style assessments using AI-assisted tools. It supports both student-facing assessment sessions and teacher-facing management features, with integration into Google Sheets for gradebook synchronization.

What changed

The author, a secondary-school social studies teacher, built PreguntaLab through an AI-assisted learning process over time, starting before the OpenAI Build Week hackathon and extending it during that period. The project evolved from a personal classroom tool to a more structured platform with defined workflows for assessment creation, delivery, and grading.

Single most important open question

Is there evidence of actual classroom usage or adoption by teachers, beyond the author's own experience?

Note: This analysis is based entirely on the self-reported description provided by the author. No external verification, revenue data, customer feedback, or traction metrics are available. All claims are treated as stated by the author and not independently confirmed.

Back to contents

What The Product Actually Is

The description states that PreguntaLab is a plataforma educativa (educational platform) that helps teachers create preguntas tipo Saber (Saber-style questions) using AI, pedagogical criteria, and curriculum focus. It allows students to enter a name, course, key, and access code to participate in an assessment session. The system assigns questions, records answers, calculates scores, and sends grades to Google Sheets.

It includes:

  • Student-facing interface for taking assessments
  • Teacher-facing tools for creating questions, managing sessions, monitoring activity, and reviewing results
  • Integration with Google Apps Script and Google Sheets for gradebook synchronization

Inference: The platform appears to be a web-based tool built using Next.js, React, Supabase, and other technologies. It supports individualized question assignment and has anti-fraud controls in development.

Back to contents

Positioning & Claim Evolution

The author positions PreguntaLab as an educational solution tailored to Colombian secondary school students preparing for the Saber exams, which are standardized tests used in Colombia’s education system.

Key claims:

  • The platform helps teachers overcome the time-intensive process of creating assessments.
  • It leverages AI to simplify question creation without requiring technical knowledge.
  • It supports a full classroom assessment workflow from session initiation to grade reporting.
  • The tool was developed by a teacher who wanted to solve a real problem in his own classroom.

Claim vs Fact: These are self-reported intentions and use cases. There is no evidence of external validation, market traction, or adoption beyond the author’s personal experience.

Back to contents

Target Customer & ICP

The description states that PreguntaLab targets:

  • Secondary school teachers in Colombia
  • Specifically those preparing students for Saber exams
  • Teachers who struggle with time-consuming assessment creation and grading processes

Inference: The primary user is a teacher using the platform to support their classroom needs. There is no indication of broader target segments or institutional buyers beyond individual educators.

Back to contents

Business Model & Pricing Evidence

There is no evidence in the description regarding:

  • Revenue model
  • Pricing structure
  • Monetization strategy
  • Subscription plans or licensing fees

Not evidenced: No information on how the platform intends to generate revenue or whether it is monetized at all.

Back to contents

Technical & Delivery Signals

The author reports building PreguntaLab using:

  • Next.js, React, TypeScript, Tailwind CSS
  • Supabase for backend/database
  • Vercel for deployment
  • Google Apps Script and Google Sheets for integration
  • Tools like Codex were used to assist in development

Key technical features mentioned:

  • Separate student and teacher interfaces
  • API routes, controlled access, assessment sessions, question assignment, answer validation, scoring, feedback, and grade synchronization

Inference: The platform appears to be a full-stack web application built with modern frontend/backend tools. It integrates with Google services for data handling.

Back to contents

Traction & Maturity Signals

The author describes:

  • A working prototype that supports core assessment workflows
  • Ongoing improvements during the OpenAI Build Week hackathon
  • Use of AI tools like Codex to improve functionality and testing
  • Plans for future enhancements (practice mode, better security, expanded question bank)

However, there is no evidence of:

  • Real-world usage or classroom adoption
  • Customer base or user feedback
  • Revenue or monetization
  • Product maturity beyond initial development

Not evidenced: No data on actual users, engagement, retention, or product-market fit.

Back to contents

Competitive Context

The description does not mention any competitors. It also lacks:

  • Market size estimates
  • Competitive landscape analysis
  • Benchmarking against existing educational platforms or assessment tools

Not evidenced: No information about the competitive environment or how PreguntaLab compares to other solutions in the space.

Back to contents

Key Risks & Red Flags

Several potential risks and red flags are present based on the self-reported description:

  1. Single-person team: The platform is built by one person (Danny Galindo), raising concerns about scalability, maintenance, and long-term support.
  2. No external validation or traction: There is no evidence of real-world usage, customer feedback, or adoption beyond the author’s own classroom.
  3. Educational focus without market data: While focused on Saber exams, there is no indication of broader market demand or alignment with national education policy trends.
  4. Privacy and security concerns: The platform handles student names, identifiers, and grades — critical data that requires robust privacy controls, which are only described as “equally important” but not demonstrated.
  5. AI dependency: Heavy reliance on AI tools like Codex for development may indicate a lack of traditional engineering depth or scalability.

Inference: The project is highly experimental and personal in nature, with limited evidence of commercial viability or institutional adoption.

Back to contents

Diligence Questions To Ask The Founders

  1. Have you had any teachers or schools test or adopt PreguntaLab beyond your own classroom?
  2. What specific pedagogical frameworks or curriculum standards does the platform align with?
  3. How do you plan to scale beyond a single developer and ensure product stability and security?
  4. Are there any partnerships or institutional relationships in place that support the platform’s growth?
  5. Can you explain how you will monetize this platform, if at all?
  6. What are the key challenges in maintaining data privacy and compliance with Colombian education regulations?

Back to contents

Investment/Partnership Verdict

Not evidenced: There is no evidence of revenue, customers, or traction to support an investment or partnership decision.

The description indicates a personal project developed by one individual, likely driven by a teacher’s need rather than a scalable business model. While the idea has potential in the educational tech space, especially for standardized test preparation, there is no indication of commercial readiness or market validation.

Confidence Level: Low — this analysis is based solely on self-reported information with no external corroboration.

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.