Security / Code scanning
GitHub Agentic Autofix: review the patch
A review protocol for GitHub Agentic Autofix: what CodeQL validation proves, how to test a proposed fix independently, and when to hold a draft PR.
9 min readRead guide →
English edition Use AI.
Use AI.
Check the result.
DottorLone turns everyday AI and coding-agent workflows into steps you can inspect. Start with a useful prompt, then learn how to check documents, code changes and automated security patches.
Start with a concrete check
Will an agent follow your repository rules?
Write a short AGENTS.md, then compare a real diff and test report with the rules you gave it.
See the check →Does a closed alert prove the fix?
Use CodeQL’s result alongside a focused regression test and an independent review.
Read the review protocol →English guides
All English guides →Read, adapt, verify
Project instructions
How to write an effective AGENTS.md for Codex
A practical AGENTS.md example for Codex: what belongs in it, how to scope rules, and how to check whether an agent actually followed them.
8 min readRead guide →
Getting started
What can you actually ask ChatGPT to do?
Practical ChatGPT requests for email, summaries, comparisons, and explanations, with a five-point check before you use the result.
4 min readRead guide →
Documents
Summarize a document with AI without missing the important parts
Use a coverage map, source references, and a separate register for amounts and dates before trusting an AI document summary.
4 min readRead guide →
Practical decisions
Compare quotes and offers with AI without losing the numbers
A worked comparison of two service quotes: normalize the term, calculate total cost, surface missing conditions, and keep a source record.
4 min readRead guide →
Agent security
Agent data injection: protect the trust boundary
A practical trust map for web and coding agents: external data, verified metadata, least privilege, approval gates and provenance.
4 min readRead guide →