OpenAI 2026 hackathon

PGEN

No one likes PowerPoint but there is no way to create a company styleguide compatible one with AI and get reliable results. This is the goal of PGEN. Create a styleguide, pick widgets and go!

Solo project by Joerg Hannemann · 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 #5,918 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

Company: PGEN

Self-reported purpose: A tool to generate PowerPoint presentations from reusable style guides using AI and design systems, with editable outputs.

What changed: The project was submitted as part of the OpenAI 2026 hackathon; it is described as a work-in-progress.

Single most important open question: Is there evidence of any traction, revenue, or customer adoption beyond the author's own development effort?

This analysis is based entirely on the self-reported description provided by the author — no third-party data, no archived history, and no independent verification. The project is described as a personal hackathon submission with no commercial activity evidenced.

Back to contents

What The Product Actually Is

The description states that PGEN is a tool for creating PowerPoint presentations from reusable style guides. It allows users to configure design elements such as colors, fonts, logos, spacing, backgrounds, and widget styles. Users can then generate slides using layouts like title slides, KPI overviews, section dividers, and text-image compositions.

The generated output is a .pptx file containing native PowerPoint objects (not flattened images), intended to be editable in PowerPoint.

Evidence: The author's own write-up describes the functionality and output format.

Inference: PGEN appears to be a design-system-based presentation generator that aims to improve consistency and editability over existing tools.

Back to contents

Positioning & Claim Evolution

The tagline states: “No one likes PowerPoint but there is no way to create a company styleguide compatible one with AI and get reliable results. This is the goal of PGEN.”

This implies a positioning around:

  • Improving corporate presentation workflows
  • Combining design systems with automation
  • Addressing the limitations of current tools

The author also says: “I wanted to build a tool that combines automation with real corporate design standards.”

This suggests an intent to bridge the gap between design consistency and automation in business presentations.

Evidence: The tagline and write-up describe the intended positioning.

Inference: PGEN is positioned as a solution for teams seeking consistent, editable, AI-assisted PowerPoint creation — though no evidence of actual market demand or adoption exists.

Back to contents

Target Customer & ICP

The description does not identify a specific customer segment or ideal customer profile (ICP). It implies that the tool is aimed at users who need to create presentations with corporate design standards, but it doesn’t name industries, roles, or company sizes.

Evidence: No explicit target customer or ICP mentioned.

Inference: Likely aimed at teams or individuals in corporate environments who use PowerPoint and want consistency and automation — but this is speculative without further data.

Back to contents

Business Model & Pricing Evidence

There is no evidence of a business model or pricing structure in the description. The project is described as a personal hackathon submission, not a commercial product.

Evidence: Not evidenced.

Inference: No indication of monetization strategy, pricing, or customer acquisition methods.

Back to contents

Technical & Delivery Signals

The author states:

  • Built with Angular.js (frontend), C# (.NET Core), PostgreSQL, and Open XML SDK.
  • Uses a shared scene model to keep browser preview and PowerPoint output consistent.
  • The tool was built using Codex MacOS app and 5.6 Sol (medium) only.
  • Challenges included text/image geometry, padding, dynamic layouts, and preserving editability.

Evidence: The author describes the tech stack and development process.

Inference: The project is technically feasible but still in early stages; it shows some engineering sophistication but lacks production-grade delivery signals.

Back to contents

Traction & Maturity Signals

The description explicitly states: “The project is explicitly still work in progress!”

It also says: “Sorry for the bad video but I had to hurry since I just got to know today (Jul/19) of this openai-build-week.”

And: “Polishing is needed as well ;)

There is no evidence of:

  • Customers
  • Revenue
  • Usage metrics
  • Product-market fit
  • Adoption

Evidence: The author describes the project as incomplete and a hackathon submission.

Inference: No traction or maturity signals are evident.

Back to contents

Competitive Context

The description does not mention any competitors or market context. It is unclear whether PGEN is addressing a specific gap in the market, or how it compares to existing tools like Canva, PowerPoint’s built-in templates, or other presentation automation tools.

Evidence: Not evidenced.

Inference: No competitive positioning or differentiation is described.

Back to contents

Key Risks & Red Flags

  • No traction or commercialization evidence: The project is a hackathon submission and not yet a product in the market.
  • Single-person team: The author is the only contributor, which may limit scalability or development velocity.
  • Incomplete tool: Described as “still work in progress” with “polishing needed.”
  • No pricing or monetization strategy: No indication of how the tool would be sold or used commercially.
  • Unverified claims: All descriptions are self-reported and unverifiable.

Evidence: The author’s own statements about project status and lack of commercial activity.

Inference: High risk of failure to scale or gain traction without further development, funding, or market validation.

Back to contents

Diligence Questions To Ask The Founders

  1. What is the intended user journey from styleguide creation to presentation generation?
  2. How does PGEN handle complex layouts or dynamic content (e.g., charts, data-driven slides)?
  3. Are there any plans for integration with existing design systems or platforms (e.g., Figma, Adobe)?
  4. What are the key assumptions about customer needs that underpin this tool?
  5. Is there a plan to monetize or commercialize PGEN beyond the hackathon?
  6. How does PGEN ensure consistency across different versions of PowerPoint or platforms?

Back to contents

Investment/Partnership Verdict

Not evidenced — no data on revenue, customers, traction, or business model.

Inference: This is a personal hackathon project with no commercial viability or evidence of traction. It may be a prototype or early-stage idea, but there is no indication it has moved beyond the author’s own development effort.

The project does not yet demonstrate any commercial potential or market readiness. Any investment or partnership would require further proof of concept, customer interest, or product-market fit.

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.