Building KaizenSQL - My Dev Journey
TL;DR KaizenSQL is a CLI tool written in Go, it analyzes SQL code and supports three modes Mentor/Performance/Security. To give it AI-powered capabilities I used Groq api for free LLM tokens. Overall, the main concern and goal with this project was to make the tool fast and pleasant to use. Every decision to be implemented had to take that into account. In this post I'll share the faced…
Juan Huanaco, a Systems Engineering student from Peru, shares his journey in creating KaizenSQL, a Go-based CLI tool that analyzes SQL code. The main objective was to make the tool fast and pleasant to use, while finding reliable ways to implement features.
Initially, Huanaco considered using the Gemini chat LLM for assistance, but opted for Groq API due to its generous free tier limits and compatibility with OpenAI's client library. This decision allowed for faster development and flexibility to switch to other providers later.
The project defined three modes - Mentor, Performance, and Security - each with their own system prompts to guide the AI agent. However, the selected LLM model had a limit of 8k tokens per minute, requiring careful consideration of input and output token usage.
To improve the user experience, Huanaco added an animated banner using Bubbletea, a TUI (Text User Interface) framework, as well as an ASCII animation generator called Ascii Motion. These enhancements made the CLI tool more engaging and visually appealing.
Although there were some challenges along the way, such as exceeding token limits with the chosen LLM model, Huanaco persevered and ultimately created KaizenSQL. The project can be found on GitHub, along with setup instructions and a ready-to-use binary.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.