OpenAI 2026 hackathon

ADAY

ADAY (Assisted Deck Authoring for You) is a local-first web application that turns a brief into an editable PowerPoint deck.

Team of 2 · 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 #521 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

ADAY (Assisted Deck Authoring for You) is a local-first web application that converts user-provided briefs into editable PowerPoint decks. It is described as an end-to-end workflow, not just a prototype, with support for planning, previewing, rendering, importing layouts, managing history and backups, and maintaining editable PPTX output.

What changed

The project was built during a single Build Week (July 17–24, 2026) using Codex as the primary development environment. It includes full-stack implementation, automated testing, documentation, and reproducible CI checks. The authors state they retained key product decisions such as local-first design, editable output, and plan validation before rendering.

The single most important open question

Is there evidence of user adoption or demand beyond the hackathon context? The description provides no data on usage, revenue, customers, or traction — only a self-reported technical implementation.

Back to contents

What The Product Actually Is

  • The description states that ADAY turns a brief into an editable PowerPoint deck.
  • It supports:
    • Refining a brief and generating a structured slide plan
    • Previewing and validating the plan before rendering
    • Generating editable PPTX slides with consistent visual styling
    • Importing images and existing PowerPoint layouts
    • Reusing custom layouts, icons, and photos
    • Managing presentation history, speaker notes, and local backups
  • Everything runs locally by default, with API keys and runtime data kept on the user’s machine.
  • The product is described as a full-stack application built using:
    • JavaScript frontend
    • Python/FastAPI backend
    • OpenAI-compatible language and vision models
    • PptxGenJS for editable PPTX rendering
    • Playwright/Python/Node test suites

Inference The product is not a simple text-to-slides tool but an integrated workflow that includes planning, previewing, editing, and persistence. It emphasizes local-first execution and editable output.

Back to contents

Positioning & Claim Evolution

  • The description states the inspiration behind ADAY was to reduce repetitive work in creating polished presentations.
  • The positioning is: “making that process feel more like collaborating with a design partner than filling out a template.”
  • The authors claim it is an end-to-end workflow, not just a prototype.
  • They also emphasize:
    • Local-first execution
    • Editable PowerPoint output (not flattened images)
    • Visual consistency and plan validation before rendering

Inference The positioning evolved from solving a common pain point in presentation creation to offering a local-first, editable, and validated workflow. The claim is that it improves upon traditional templates by enabling collaboration-like interaction.

Back to contents

Target Customer & ICP

  • Not evidenced.
  • The description does not name specific customer segments or personas.
  • No evidence of target industries, roles (e.g., executives, educators, consultants), or use cases beyond general presentation creation.

Inference The product likely targets individuals who create presentations regularly and value editable outputs. However, no explicit ICP is stated.

Back to contents

Business Model & Pricing Evidence

  • Not evidenced.
  • No mention of pricing models, monetization strategies, or revenue streams.
  • The description does not indicate whether the tool will be sold, offered as freemium, or used internally.

Inference There is no evidence of a business model or pricing structure. The project appears to be a hackathon submission with no commercial intent described.

Back to contents

Technical & Delivery Signals

  • Built during Build Week (July 17–24, 2026) using Codex as the development environment.
  • Full-stack implementation:
    • Browser Studio and Gallery
    • Planning and vision agents
    • FastAPI backend
    • Editable PPTX renderers
    • Previews, imports, backups, and local storage workflows
  • The stack includes:
    • Vanilla JavaScript frontend
    • Python/FastAPI local server
    • OpenAI-compatible language and vision models
    • PptxGenJS for editable PPTX
    • JSZip, deterministic asset packs
    • Playwright/Python/Node test suites
  • Repository-scale iteration and debugging were performed using Codex.
  • Automated test suite covers:
    • Browser behavior
    • Server security
    • All 20 renderers
    • Preview generation
    • SmartArt-style PPTX imports

Inference The technical implementation is robust for a hackathon project, with full-stack development and automated testing. The use of Codex suggests a high degree of automation in development.

Back to contents

Traction & Maturity Signals

  • Not evidenced.
  • No data on user adoption, engagement, or retention.
  • No mention of customers, revenue, or usage metrics.
  • The product is described as a single Build Week effort with no indication of post-hackathon traction or growth.

Inference There are no signs of traction or maturity beyond the initial build. The project has not been commercialized or scaled beyond its hackathon version.

Back to contents

Competitive Context

  • Not evidenced.
  • No mention of competitors or market positioning relative to existing tools (e.g., PowerPoint, Canva, Slides.com).
  • No evidence of competitive advantage or differentiation in the marketplace.

Inference The competitive context is unknown. The project does not appear to be positioned against any known competitors, and no comparative analysis is provided.

Back to contents

Key Risks & Red Flags

  • No commercial traction or revenue: The product is described as a hackathon submission with no evidence of monetization.
  • Unproven market demand: No data on users, adoption, or customer feedback beyond the authors’ own claims.
  • Local-first design may limit scalability: While local-first improves trust, it could hinder broader adoption or collaboration features.
  • Dependency on Codex and proprietary tools: The use of Codex as a development environment is not standard in commercial settings.
  • No clear path to product-market fit: No evidence of user feedback loops, iteration, or validation beyond the initial build.

Inference The project lacks commercial viability indicators. It may be a proof-of-concept with no clear path to monetization or market traction.

Back to contents

Diligence Questions To Ask The Founders

  1. What is your plan for monetizing this product?
  2. Have you tested the product with real users beyond the hackathon?
  3. How do you intend to scale beyond the current local-first, single-user model?
  4. What are the key assumptions about user behavior or needs that underpin this product?
  5. Are there any known technical limitations or scalability issues with the current architecture?
  6. How do you plan to handle collaboration and sharing workflows while preserving local privacy?
  7. What is your roadmap for improving visual consistency across presentation styles?

Back to contents

Investment/Partnership Verdict

  • Not evidenced.
  • No data on valuation, funding rounds, or investor interest.
  • The project is described as a hackathon submission with no indication of commercialization or investment readiness.

Inference There is no evidence that this project is ready for investment or partnership. It appears to be an early-stage prototype with no demonstrated traction or business model.

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.