Building KaizenSQL - My Dev Journey

Description and use

KaizenSQL is a Go-based CLI that analyzes SQL code using the Groq LLM, offering Mentor, Performance, and Security modes, and features an animated banner via Bubbletea.

Problem

Create a fast, pleasant-to-use CLI tool that analyzes SQL code and provides AI-powered feedback in multiple modes (Mentor, Performance, Security).

Outcome

KaizenSQL delivers quick, AI-enhanced SQL analysis with a user-friendly CLI interface, supporting mentor guidance, performance insights, and security checks, all while maintaining speed and token limits.

Workflow

• 1. Implemented file/directory reading in Go.
• 2. Integrated Groq API using Go-OpenAI client.
• 3. Defined three modes with distinct system prompts.
• 4. Added command-line flags for mode selection.
• 5. Handled token limits by setting MaxCompletionTokens.
• 6. Added animated banner using Bubbletea and Ascii Motion.
• 7. Tested and iterated on performance and error handling.

Evidence

KaizenSQL is a CLI tool written in Go, it analyzes SQL code and supports three modes Mentor/Performance/Security.

Source

I chose another LLM provider for this project. That is Groq API, it has a generous limit to use it properly as a sandbox for testing your AI interactions.

Source

I added a Mentor mode, its value is that it does not solve the problem, but guides you a clue so that you can find the answer yourself.

Source

The fix? just to set the limit explicitly, that's ok for this little project's scope

Source

After some googling I found bubbletea (a TUI framework), this awesome open-source solution was the speedtrack I was looking for.

Source