OpenAI 2026 hackathon

DdakDama

Turn a shopping list into a verified, reviewable Coupang cart.

Solo project by PARK JUNESUNG · 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 #3,657 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

DdakDama is a self-reported Chrome extension and ChatGPT app hybrid tool designed to automate parts of the shopping process on Coupang, a South Korean e-commerce platform. It interprets free-form shopping lists using AI (specifically GPT-5.6), parses product information from Coupang, and helps users verify or manually select items before adding them to their cart.

What changed

The project was submitted as part of the OpenAI 2026 hackathon. The author describes it as a v1.0.2 release with a focus on structured search, product verification, and manual checkout. It includes a Chrome extension, an OpenAI App SDK integration, and Cloudflare infrastructure for handling MCP-based interactions.

The single most important open question

Is there any evidence of user adoption, revenue, or traction beyond the author's own development and testing?

Back to contents

What The Product Actually Is

The description states that DdakDama is a TypeScript monorepo composed of four layers:

  1. A shared deterministic parser and quantity planner.
  2. A Manifest V3 Chrome Side Panel extension for search, comparison, validation, and cart actions.
  3. An OpenAI Apps SDK and MCP-based ChatGPT app for structured list review and secure handoff.
  4. A Cloudflare Worker and Durable Object service for public MCP access, pairing, rate limiting, and user isolation.

It uses GPT-5.6 to interpret shopping intent and invoke structured tools. It also leverages Codex, Playwright, React, TypeScript, and other technologies.

The tool is built to parse Coupang product unit results and separates search from automatic selection, classifying candidates as EXACT, REVIEW, or NONE based on identity, size, and package match.

It does not automate checkout or order confirmation — all such actions remain manual.

Inference This appears to be a proof-of-concept or prototype tool for personal use, likely developed during a hackathon. It is not described as a commercial product with customers or revenue.

Back to contents

Positioning & Claim Evolution

The author states that DdakDama aims to close the gap between AI-generated shopping routines and manual cart creation on Coupang. The core claim is that it provides an explicit review and verification boundary for shopping lists.

It positions itself as a tool that:

  • Interprets free-form shopping lists.
  • Parses product details from Coupang.
  • Helps users verify or manually select items before adding to the cart.
  • Ensures accuracy in quantity, package size, and physical supply.

The author also emphasizes:

  • Separation of search from automatic selection.
  • Visibility of partial failures and price-unverified states.
  • Non-automation of payment or order confirmation.

Inference This is a self-described tool for improving shopping efficiency on Coupang. It does not claim to be a marketplace, platform, or commercial product with users beyond the developer.

Back to contents

Target Customer & ICP

The description does not name specific customer segments or personas.

It implies that the target user is:

  • Someone who uses Coupang.
  • Someone who creates shopping lists and wants them interpreted and verified.
  • Someone who values manual control over cart additions.
  • Likely a developer or tech-savvy individual, given the technical stack and testability.

The author notes that the tool is built for personal use, not for mass adoption or commercial sale.

Inference No clear ICP is defined. The product appears to be aimed at individuals who want to automate parts of their shopping on Coupang, but there is no evidence of a broader customer base or commercial targeting.

Back to contents

Business Model & Pricing Evidence

The description does not state any business model or pricing structure.

It mentions:

  • The tool is built for personal use.
  • It will be published through the Chrome Web Store.
  • It may include affiliate benefits in the future, but only if platform-compliant.

There is no mention of monetization, subscriptions, or paid features.

Inference No evidence of a business model or pricing strategy. The tool appears to be a prototype with no commercial revenue or customer data.

Back to contents

Technical & Delivery Signals

The project uses:

  • Chrome extension (Manifest V3)
  • Cloudflare Workers and Durable Objects
  • OpenAI Apps SDK and MCP protocol
  • Playwright, React, TypeScript, Vitest, Zod
  • Codex for code acceleration

It is described as a TypeScript monorepo with:

  • A deterministic parser
  • A Chrome extension UI
  • A backend service for pairing and rate limiting
  • Structured tools for AI interaction

The author provides a test path using pnpm commands, including linting, type checking, unit tests, and E2E tests.

Inference The tool is technically well-structured and tested. However, this is a prototype or hackathon project, not a production-ready product.

Back to contents

Traction & Maturity Signals

The description states:

  • It is version v1.0.2
  • It was submitted to the OpenAI 2026 hackathon
  • The author provides a GitHub repository and test instructions
  • It uses real Coupang product parsing, but does not automate checkout or order confirmation

There is no mention of:

  • Users, customers, or adoption
  • Revenue or monetization
  • Product-market fit or growth metrics
  • Any form of public launch or marketing

Inference No traction or maturity signals are evident. It is a self-developed prototype with no external validation or user data.

Back to contents

Competitive Context

The description does not mention competitors or market positioning beyond Coupang.

It is implied that the tool addresses inefficiencies in shopping list interpretation and cart creation on Coupang, but there is no comparison to existing tools or platforms.

Inference No competitive analysis or context is provided. It is unclear whether similar tools exist or how DdakDama differentiates from them.

Back to contents

Key Risks & Red Flags

  • No evidence of traction or revenue: The tool is described as a hackathon project with no commercial adoption.
  • Limited scope: It only works on Coupang and does not appear to be scalable beyond one platform.
  • Manual checkout requirement: This may limit user convenience and adoption.
  • Self-reported only: No third-party validation, customer data, or performance metrics are provided.
  • No monetization strategy: The tool is not described as a commercial product with a path to revenue.

Inference The project lacks commercial viability indicators. It is a prototype with no clear path to market traction or monetization.

Back to contents

Diligence Questions To Ask The Founders

  1. What is the intended user base beyond personal use?
  2. Are there any plans to expand beyond Coupang?
  3. How does the tool handle edge cases in product parsing or quantity logic?
  4. Is there a plan for monetization or commercial launch?
  5. Has the tool been tested with real users, or is it purely internal?
  6. What are the technical limitations of the current architecture?

Back to contents

Investment/Partnership Verdict

Not evidenced.

The description provides no evidence of:

  • Revenue
  • Customers
  • Traction
  • Market demand
  • Commercial viability

It describes a self-developed prototype, likely built for a hackathon, with no indication of commercial intent or market validation.

This is not a product with demonstrated traction or a clear path to monetization. It is a technical demonstration, not a business opportunity.

Confidence: Low.

The entire analysis is based on self-reported claims and does not include any external data, user feedback, or performance metrics.

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.