JevMade

Sign in
← Back to guides

JevMade field notes / Architecture and workflow guide

A guide to checking code for hidden mistakes using AI

You will learn how this project uses an AI tool to check computer code and documents for confusing mistakes. It explains how to set rules, test them, and review the results before making changes.

Original by mizchiEvaluation

Listen to this guide

JevMade’s plain-English explanation

0:00 /

Our summary

This project is a tool that helps writers and programmers find confusing mistakes in their work. People use it to spot problems that standard checkers miss, like when a description says one thing but the actual instructions do something completely different.

The software searches for specific parts of a file and sends them to Jev, an AI tool that chooses from options rather than writing an answer. The AI scores how likely it is that a rule was broken, and flags the issue if the score is high enough.

This tool is useful for teams wanting to double-check their work, but it is not perfect. In the author's tests, about one in five alerts was wrong. Because the AI's scores can change slightly between runs, a person must always review the flagged issues before acting on them.

Key takeaways

  1. Write specific rules that look for one clear mistake instead of general bad quality.
  2. Record the AI's decisions so you can review them later when adjusting your alert settings.
  3. Only ask the AI to double-check its answers if the results change too much between tests.

The author reported the measurements and how the software behaves.

Repository README and documentation

Read the original guide Opens the author’s site in a new tab.

Your note

Only you can see this. Clear the text and save to remove it.

Keep what you save

Sign in to keep bookmarks and private notes on every device. We email you a link; there is no password, and the same link creates your account.