FixKit AI

Home / Use case

Make sense of old or undocumented software

“We depend on an old program and nobody knows how it works.”

AI can read old code (COBOL, assembly, old file formats) and explain it, and with the right tools it can help study programs you own. Stick to software you have the right to inspect.

Fix it yourself in 3 steps

  1. Gather what you have: source, binaries, file samples, and what the program is supposed to do.
  2. Ask the AI to explain the structure first: main parts, inputs, outputs.
  3. Have it write notes and small tests that capture current behavior before anyone changes it.

Copy this prompt

Here is [code/file samples] from an old system we own: [details]. Explain what it does in plain English: main parts, inputs, outputs, and anything risky. Write tests or examples that capture current behavior. Don't modify the original files. Stop after the explanation and tests.

Fill in the [brackets]. Each prompt says when the AI should stop, so it doesn't wander off.

Agents people used for this: Claude Code, Claude, Gemini, Cursor.

Inspired by real examples collected at agentusecases.ai.

📚 9 real stories of people doing this with AI agents

Collected at AgentUseCases.ai.

Tools for this

#1 · Our pick

Claude Code

Best for: Serious work on real repos

Anthropic's agent for your terminal, IDE and desktop. Reads the whole repo, runs commands and tests, and handles large multi-file changes well.

Visit Claude Code ↗
#2

Cursor

Best for: Editor-first developers

A VS Code-style editor built around AI, with background agents. The comfortable choice if you live in an editor.

Visit Cursor ↗
#3

Claude

Best for: Writing, analysis, code

Anthropic's assistant: strong writing, analysis and coding, with projects and artifacts for longer work.

Visit Claude ↗
#4

Gemini

Best for: Google Workspace users

Google's assistant, woven into Gmail, Docs and Android. Strongest if you live in Google's apps.

Visit Gemini ↗