[Iter-X] 32/100days

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.

Day3️⃣2️⃣

</source>
AI for Trip Planing

The AI architecture and overall framework are complete, and an intelligent itinerary creation process is now running successfully. However, there are still some tasks to tackle:

  1. Consider integrating MCP for further standardization.
  2. Enhance observability—LLM calls need monitoring, including cost tracking, input-output sampling, etc., to support future Agent version iterations with data.
  3. Strengthen boundary handling to ensure fallback mechanisms in certain scenarios.
  4. Standardize prompt version management.
  5. Optimize full-text search—consider replacing Elasticsearch with Postgres, which should be sufficient for a long time.
  6. Improve Agents and Tools.

These tasks can be addressed progressively. Now that the framework is in place, AI engineers can focus on optimization, backend developers can implement logic, and data engineers can integrate data.

Current Progress:

  • Prototype Design & UI/UX: 28%
  • Backend (Go) Development: 30%
  • Client (Flutter) Progress: 8%
  • Data: 8%

🚀 We’re looking for a UI designer! If you meet the following criteria, let’s talk:

  1. Committed
  2. Ambitious
  3. Passionate

Let’s build something amazing together! 👾




Enjoy Reading This Article?

Here are some more articles you might like to read next:

  • LLM Infra 101 v0.0: Model Inference
  • Daily Harness
  • Browser Use Deep Dive
  • The Primitive Urge to Solve Problems
  • How We Are Speedrunning the AI Era