DEV Community

Cover image for Build an AI Incident Copilot CLI in Python
AutoShiftOps profile image Sajja Sudhakararao
Sajja Sudhakararao for AutoShiftOps

Posted on • Edited on

Build an AI Incident Copilot CLI in Python

#devops #python #docker #sre

When an incident fires, you don't need more dashboards.
You need answers, fast.

This post is a build-a-tool weekend project: a Python CLI that collects logs from systemd and Docker, highlights repeating patterns, maps them to the Golden Signals, and generates a ready-to-use incident report.

Project files 

incopilot/
  cli.py         collectors.py
  analyzer.py    reporter.py    config.py
scripts/
  demo_generate_sample_logs.py
requirements.txt    pyproject.toml    README.md
Enter fullscreen mode Exit fullscreen mode

Setup 

python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
Enter fullscreen mode Exit fullscreen mode

Quick demo (no real services) 

python scripts/demo_generate_sample_logs.py
python -m incopilot file --path sample.log
Enter fullscreen mode Exit fullscreen mode

Systemd triage 

python -m incopilot journal --unit nginx --since "30 min ago"
Enter fullscreen mode Exit fullscreen mode

Docker triage 

python -m incopilot docker --container my-api --since 1h
Enter fullscreen mode Exit fullscreen mode

Both (bundle) 

python -m incopilot bundle --unit nginx --container my-api --since-journal "30 min ago" --since-docker 1h
Enter fullscreen mode Exit fullscreen mode

Outputs

  • out/report.md — human-friendly
  • out/report.json — machine-friendly

Originally published on [LINK]

💬 What's your go-to first command when an incident fires?
Drop it in the comments — I'll add the best ones to the safe-commands list.

Top comments (0)