Three Weeks, One App: What AI Can Build For You and What It Absolutely Cannot
Blog post from Rasepi
In just three weeks, the author transformed a partially completed .NET backend and Vue frontend into a comprehensive application, Rasepi, featuring a block-level translation engine, AI-powered semantic search, a plugin SDK, collaborative real-time editing, and more. This rapid development was significantly accelerated by AI tools such as Claude, ChatGPT, and Codex, which assisted in coding tasks like writing service interfaces and building HTML pages. However, the author emphasizes that AI's capabilities are limited to code generation and lack the ability to interact with the configuration and deployment processes, such as setting up infrastructure, managing DNS records, and integrating third-party services. Despite the productivity boost provided by AI, the author highlights the necessity of possessing foundational software engineering knowledge and the ability to manually handle configurations to bring an application to market. The narrative underscores the gap between building an app and creating a sellable product, with AI tools accelerating the former but not replacing the essential human role in the latter.
| Trend | Post Mentions | Total Month Mentions | Posts | Companies | MoM |
|---|---|---|---|---|---|
| MCP | 2 | 6,108 | 613 | 170 | +36% |
| RAG | 2 | 941 | 216 | 85 | -48% |
| Real-time | 2 | 6,296 | 1,346 | 246 | -2% |
| Secrets Management | 2 | 1,821 | 338 | 111 | +22% |
| AI Coding Assistant | 1 | 1,480 | 382 | 153 | +18% |
| AI Model Fine-tuning | 1 | 420 | 130 | 55 | -54% |
| Vector Search | 1 | 1,739 | 413 | 146 | -27% |
Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.