[Iter-X] 66/100days

Note: This article was translated for me by AI. I wrote the original in Chinese. I never use AI to write my articles, because that would cost me my own expression; my freedom to express myself is always the most valuable part of my work. So if you can read Chinese, I recommend reading the Chinese version, where you will get the most original and unfiltered version. That said, technological progress exists to give us more convenience, so I will continue using AI to translate my writing into multiple languages, allowing valuable content to reach more people.

Day 6️⃣6️⃣

Not much progress today. I’ve been heavily focused on MCP lately, and also experimenting with travel planning done directly via unwrapped LLMs. It gave me some new ideas for the product. I’m starting to believe that the moat for this type of travel planning product might lie in data:

1️⃣ First, having a reliable and objective factual dataset can significantly suppress hallucinations and maximize the user experience. This is also a key reason why RAG (Retrieval-Augmented Generation) is so popular. I think many LLM-based vertical products can actually be classified as RAG applications.

2️⃣ Second, user data. With ChatGPT’s new Memory feature, I think we’re witnessing a real game-changer. Making users feel “wow, this thing gets me” relies entirely on user data + data generated during usage.

For products in this specific category, different monetization models will highlight different strengths — for example, some might compete based on their supply chain. Just some food for thought.

Current progress summary:

1. Prototype & UI/UX Design: 33%
2. Backend (Go) Development: 60%
3. Client (Flutter) Progress: 56%
4. Data: 14%

If you feel like you fit the following description, let’s talk:

1. You can stay committed
2. You have a dream
3. You’re genuinely interested