# building my first AI feature in my app | coding vlog ep. 5

Source: https://www.youtube.com/watch?v=RGINUH_GK0k
Recap page: https://rapidrecap.app/video/RGINUH_GK0k
Generated: 2025-11-24T18:44:11.287+00:00

---
## Quick Overview

The creator successfully built and deployed an AI feature—a custom code or cursor generator for marketers—into their app, Yorby.ai, over five days, utilizing a double-blind testing process involving multiple LLMs (including Gemini 2.5 Pro and Flash) and a custom internal evaluation tool to iterate and select the best-performing model, ultimately demonstrating the power of specialized AI tooling over general-purpose models for specific tasks.

**Key Points:**
- The creator spent five days building and deploying their first AI feature, a code/cursor generator for marketers, into their app, Yorby.ai.
- The core development involved an iterative process comparing multiple LLMs, including Gemini 2.5 Pro and Gemini 2.5 Flash, using an internal evaluation tool.
- The creator used a double-blind testing methodology to grade different models on a 1-10 scale based on their ability to generate high-quality, viral-potential content scripts tailored to a user persona.
- The initial attempt using complex AI workflows and multiple models resulted in poor output, leading the creator to simplify the process to a single, well-crafted prompt.
- The final, simpler approach yielded better results, with the best model scoring 9.8/10, proving that high-quality input is crucial for good AI output.
- The video also briefly mentions two core features of Yorby.ai: a Hiring Feature (pay-for-success model) and a Viral Content Database.

![Screenshot at 15:13: The creator interacts with the YATB \(Yorby AI Tool Database\) interface, selecting the 'AI Remix' option and inputting detailed descriptions of the target application \(Montee, a productivity app\) and audience into the 'Quick Start Template' to initiate the script generation process.](https://ss.rapidrecap.app/screens/RGINUH_GK0k/00-15-13.png)

**Context:** This video is a startup vlog (Episode 5) documenting the creator's intense, 24-hour development sprint to build and test the first AI feature for their social media marketing tool, Yorby.ai. The primary goal was to create a tool that could remix existing viral videos into new content tailored for specific business needs, moving beyond simple prompt engineering to incorporate structured evaluation and iteration loops using various LLMs.

## Detailed Analysis

The creator documents the five-day process of building the first AI feature for their app, Yorby.ai: a tool that generates custom code or cursors for marketers based on existing viral video scripts. The initial approach involved complex workflows and testing multiple LLMs (like Gemini 2.5 Flash and Pro) side-by-side using an internal evaluation tool, which ultimately led to poor results due to the complexity. A key learning was that a simpler approach—using a single, highly specific prompt based on the original video script and a defined user persona—yielded much better results, with one script scoring 9.8/10. The creator details the iterative process of generating multiple scripts, grading them using an internal scoring mechanism (0-10 scale), and refining the prompts based on the results, concluding that the AI tooling ecosystem is powerful but requires careful input design. The video also briefly covers the existing features of Yorby.ai: a Hiring Feature and a Viral Content Database.

### Startup Journey

- Building the First AI Feature
- The creator spent five days developing an AI feature to generate marketing content scripts from viral videos for their tool, Yorby.ai
- The process involved heavy iteration and testing of multiple LLMs (Gemini 2.5 Flash/Pro) using an internal grading system.

### Development Process & Learning | Initial attempts with complex AI workflows failed; success came from simplifying the process to a single, highly detailed prompt informed by user persona and video context | The best model scored 9.8/10, highlighting that input quality dictates output quality.


### Yorby.ai Features Overview

- Hiring Feature
- A service to find and hire creators where payment is only made upon successful placement (pay-for-success).

### Yorby.ai Features Overview

- Viral Content Database
- A repository of proven viral marketing content used as inspiration for remixes, featuring filtering and grading tools.

### Future Plans

- The creator plans to focus on building out an internal AI evaluation tool to objectively score model performance and further refine the AI content remixing workflow.

![Screenshot at 00:08: The title card appears over the creator's opening monologue, reading "Start up Vlog Epis\[ode 5\]".](https://ss.rapidrecap.app/screens/RGINUH_GK0k/00-00-08.png)
![Screenshot at 00:08: The laptop screen displays the title "Start up Vlog Episode 5" over a video call interface, signaling the start of the vlog.](https://ss.rapidrecap.app/screens/RGINUH_GK0k/00-00-08.png)
![Screenshot at 00:50: A graphic slide appears detailing the two main features of Yorby.ai: the Hiring Feature and the Viral Content Database.](https://ss.rapidrecap.app/screens/RGINUH_GK0k/00-00-50.png)
![Screenshot at 03:36: A text overlay highlights the dual focus of the development: creating a script transformer and an AI evaluation system.](https://ss.rapidrecap.app/screens/RGINUH_GK0k/00-03-36.png)
![Screenshot at 04:51: A time jump overlay reads "24 HOURS LATER", indicating significant work has been completed since the morning session.](https://ss.rapidrecap.app/screens/RGINUH_GK0k/00-04-51.png)
