Gemini and Aydın Tiryaki (February 18, 2026)
Triggering Context
This article was triggered by the process of designing a completely new AI assistant (Gem), starting from an initial artistic and philosophical text, to transform such content into a systematic publication package. This process, shaped through interactive dialogues, documents how an idea evolves into a digital model and how the “AI Says” concept was constructed.
Compiled Information
Designing a new Gem from scratch is the art of teaching a way of thinking to a machine. In this process, the AI acts as an “implementer,” while the user serves as the “decision-maker” who builds the entire architecture. The following table illustrates, step-by-step, how an idea evolved into a full-fledged assistant model within approximately 60 minutes:
| Reply No | Time | User Intervention and Purpose | Technical AI Response / Gem Design |
| Reply #1 | 08:42 | Request for an in-depth analysis of an artist’s text. | Philosophical analysis of the text was performed. |
| Reply #3 | 08:48 | Idea to turn analyses into a series titled “AI Says.” | A 4-pillar draft structure (Intro, Analysis, Info, Synthesis) was created. |
| Reply #7 | 08:53 | Requirement for simultaneous TR-EN articles and summaries. | Complex “Output Flow” instructions were integrated into the system. |
| Reply #12 | 09:05 | Request to handle various input types (links, ideas, chats). | A logical layer was added to detect input types and provide references. |
| Reply #13 | 09:12 | Control for AI to “stop and ask” if the topic is too broad. | A “Scope Control” mechanism was integrated into the system. |
| Reply #15 | 09:16 | Requirement for dynamic city and model information. | [Location] and [Model] variables were defined instead of static data. |
| Reply #20 | 09:41 | Label ban (no “Title:”) and visual alignment of footnotes. | Output format was refined; aesthetic rules became “System Commands.” |
Evaluation of the Process in Terms of Gem Design
Unlike traditional software development, this interactive design process is built upon the user’s continuous “natural language” oversight of the system. At every stage, the user identified a “glitch” or “deficiency” (e.g., “The label ‘Title:’ makes copying difficult”), and the AI transformed this feedback into a new version (V1-V9) within seconds.
The primary source of speed here is the AI’s ability to instantly synthesize complex instruction sets. However, the true creativity lies in the mind of the user, who defines the boundaries of those instructions and tells the AI to “stop and ask” during moments of uncertainty. In this scenario, the AI served as a “power multiplier,” instantly realizing manual adjustments and translations that would otherwise take the user hours to complete.
Conclusion
Designing a new Gem is a perfect fusion of the user’s strategic vision and the operational speed of technology. This case study proves that a professional content production tool, with minimized error margins and defined aesthetic criteria, can be brought to life through a dialogue lasting about one hour. The speed of technology only generates “value” through the correct guidance of a human.
| aydintiryaki.org | YouTube | Aydın Tiryaki’nin Yazıları ve Videoları │Articles and Videos by Aydın Tiryaki | Bilgi Merkezi│Knowledge Hub | ░ Virgülüne Dokunmadan │ Verbatim ░ | ░ Yeni Bir Gem Tasarımının Anatomisi │ Anatomy of a New Gem Design ░ 18.02.2026
A Note on Methods and Tools: All observations, ideas, and solution proposals in this study are the author’s own. AI was utilized as an information source for researching and compiling relevant topics strictly based on the author’s inquiries, requests, and directions; additionally, it provided writing assistance during the drafting process. (The research-based compilation and English writing process of this text were supported by AI as a specialized assistant.)
