J’ai Recréé une APP à 34M€ en 20 Minutes avec l’IA

J’ai Recréé une APP à 34M€ en 20 Minutes avec l’IA

🎙 Yassine Sdiri 👥 262K 📅 February 15, 2026 ⏱ 21 min 👁 88K 📄 tutorial 🧭 2026-08-03
Available in: English (current) Français

Keywords

Cal AIMVPClaudeLovableStitch

Summary

The video demonstrates how to recreate a calorie-tracking app similar to Cal AI, which reportedly generates $34 million in annual revenue, using three AI tools: Claude, Lovable, and Stitch. The creator, Yassine Sdiri, explains the process step-by-step, starting with using Claude as a project manager to generate a detailed brief, then using Lovable to build the app’s frontend and integrate AI features, and finally using Stitch to enhance the design and functionality. The video shows a live demo where the app successfully scans a banana and estimates its calories. The creator emphasizes that this is a minimal viable product (MVP) that can be built quickly and cheaply, and he discusses the importance of marketing for success. He also mentions that deploying to app stores requires additional steps, which he hints at but does not cover in detail. The video is aimed at non-developers interested in leveraging AI for app creation.

150 words

Critical Evaluation

The video provides a practical, hands-on tutorial for building a mobile app MVP using AI tools, which is valuable for non-developers. The creator demonstrates a clear workflow: using Claude to generate a project brief, Lovable to build the app, and Stitch to refine the design. The live demo of scanning a banana and getting accurate calorie estimates is compelling and shows the potential of these tools. However, the video has several limitations. First, the claim that Cal AI generates $34 million in annual revenue is presented without solid evidence; the creator mentions it is based on public statements by the founder, but no direct source is provided. This weakens the reliability of the information. Second, the video is essentially a promotional piece for the creator’s academy and services, with multiple calls to action, which may bias the presentation. Third, while the tutorial is clear, it lacks depth on technical aspects such as data privacy, scalability, and the limitations of AI-generated apps. The creator briefly mentions that these tools may create HTML-encapsulated apps, but does not elaborate on how to overcome this for store deployment. The adéquation between title and content is good, as the video indeed recreates an app similar to Cal AI in about 20 minutes. The argumentation is straightforward and practical, but the scientific rigor is limited because it relies on anecdotal evidence and personal experience rather than systematic testing or peer-reviewed sources. The sources cited are the tools themselves (Claude, Lovable, Stitch) and Dribbble for design inspiration, which are relevant but not academic. Overall, the video is useful for beginners, but viewers should be cautious about the revenue claims and the promotional nature.

276 words

Title / Content Match

The title accurately reflects the content: the creator recreates a calorie-tracking app similar to Cal AI in about 20 minutes using AI tools.

Quality & Reliability

6/10

The video provides a practical demonstration of using AI tools to build a mobile app MVP, but relies on unverified claims about the revenue of Cal AI and lacks rigorous scientific methodology. The information is practical and actionable, but the reliability is moderate due to promotional elements and lack of independent verification.

Chapters

Cited Sources

  • Claude — Used as the project manager AI to generate the app brief.
  • Lovable — Used as the developer AI to build the app.
  • Stitch — Used as the designer AI to refine the app's design.
  • Dribbble — Mentioned as a source for design inspiration.

Concurring Sources

  • Cal AI — The app being recreated, whose revenue claims are mentioned but not independently verified.

Dissenting Sources

  • Cal AI revenue claims — The video claims Cal AI generates $34 million in annual revenue, but this is based on the founder's statements and not independently verified, which may be inaccurate or exaggerated.

Contribution & Novelties

The video offers a practical, step-by-step guide to building a mobile app MVP using AI tools, which is accessible to non-developers. It demonstrates the integration of multiple AI tools (Claude, Lovable, Stitch) to streamline the development process, from planning to design. The live demo of scanning a banana and getting accurate calorie estimates showcases the potential of AI-powered apps. The video also emphasizes the importance of marketing and MVP validation, which is valuable for aspiring entrepreneurs.

Pour aller plus loin :

  • Minimum viable product — Relevant to understand the concept of MVP discussed in the video.
  • Artificial intelligence in software development — Provides background on AI tools used in development.
  • Calorie counting — Relevant to the app’s functionality.

118 words

Radar Profile

The radar profile shows moderate scores across all dimensions, with a slight emphasis on quantity of information and technical level, but lower reliability due to unverified claims and promotional content.

Reliability 5/10

💬 Très positif : Sur les 30 commentaires analysés, la grande majorité exprime un fort intérêt pour une suite vidéo sur le déploiement sur les stores, avec des éloges pour la clarté et l'utilité du contenu.