Reelish: Turn Reels Into Dinner

The description states:

• Reelish is a native Android app that turns shared Instagram food reels into source-supported recipe cards.
• It allows users to select recipes and combine ingredients into one grocery list.
• The app uses Kotlin, Jetpack Compose, Room, WorkManager, Firebase Authentication, Firestore, and Cloud Functions for backend support.
• A V2 parser was added during OpenAI Build Week 2026, using OpenAI Responses API, transcription, frame sampling, OCR, caching, and explicit review handling.

Inference The app appears to be a mobile tool focused on transforming social media content into structured cooking workflows.

The description states:

• The inspiration was that food reels are inspiring but have fragmented recipe information.
• The goal is to turn “inspiration” into a practical cooking workflow without silently inventing anything.
• It distinguishes review states and provenance, preserves a safe V1 fallback, and reduces the chance of invented recipes.

Inference The positioning appears to be about trustworthiness in recipe extraction from unstructured social media content, with an emphasis on preserving source integrity.

The description states:

• The app targets users who watch Instagram food reels and want to cook from them.
• It is built for a “practical cooking workflow.”

Not evidenced No explicit customer persona or ICP defined beyond the general use case of watching food reels.

The description states:

• No pricing model, monetization strategy, or business model is described.
• The app is presented as a tool for personal use and workflow improvement.

Inference No evidence of a commercial model; the project appears to be a prototype or hackathon submission.

The description states:

• Built with Kotlin and Jetpack Compose on Android.
• Uses Room and WorkManager for local-first experience.
• Firebase Authentication, Firestore, Cloud Functions support backend.
• V2 parser uses OpenAI Responses API, transcription, frame sampling, OCR, caching, and explicit review handling.

Inference The technical stack is standard for modern Android development with cloud integration and multimodal AI parsing components.

The description states:

• The project was submitted to the OpenAI Build Week 2026 hackathon.
• It includes a V2 parser added during the hackathon.
• No mention of users, customers, or adoption beyond the author’s own account.

Not evidenced No evidence of revenue, user base, or product traction.

The description states:

• No competitive analysis or market positioning is provided.
• The app is described as solving a problem in food reel consumption and recipe creation.

Not evidenced No information on existing solutions or competitive landscape.

The description states:

• The app is built for a hackathon, not production use.
• It uses OpenAI APIs and OCR, which may introduce dependency risks.
• The author acknowledges the challenge of balancing retrieval cost, reliability, and user trust.

Inference Key risks include lack of commercial traction, reliance on external AI services, and limited evidence of product-market fit or scalability.

1. What is the current user base or adoption rate for Reelish?
2. Has the app been tested in real-world cooking workflows?
3. Are there plans to monetize or scale beyond the hackathon prototype?
4. How does the app handle edge cases where source content is ambiguous or incomplete?
5. What are the technical limitations of the current parser, and how do they impact usability?