Software Engineering

Root cause analysis with 5 Whys

AI helps apply the 5 Whys technique to recurring bugs so teams can move beyond symptoms and identify systemic fixes plus process or tooling improvements.

Why the human is still essential here

Humans are needed to determine the true organizational or technical root cause, agree on preventive changes, and put those process improvements into practice.

How people use this

Bug retrospective facilitator

AI guides a team through repeated why questions after a recurring defect and turns the discussion into a structured root-cause chain.

Claude / ChatGPT

Postmortem draft from issue data

AI synthesizes tickets, incident notes, and chat transcripts into a first-pass postmortem that highlights contributing factors and systemic failures.

Atlassian Intelligence / ChatGPT

Preventive action planning

AI converts the identified root cause into concrete follow-up actions such as tests, lint rules, runbooks, or release-process checks for named owners.

Atlassian Intelligence / Claude

Need Help Implementing AI in Your Organization?

I help companies navigate AI adoption -- from strategy to production. Whether you are building your first LLM-powered feature or scaling an agentic system, I can help you get it right.

LLM Orchestration

Design and build LLM-powered products and agentic systems

AI Strategy

Go from idea to production with a clear implementation roadmap

Compliance & Safety

Build AI with human-in-the-loop in regulated environments

Related Prompts (4)

Latest community stories (1)

Personal Story
Blog

How I Use AI as a Senior Engineer

I've been using AI for code reviews for over a year. In that time I've learned one uncomfortable truth:

Most developers are using AI wrong for code reviews.


They paste code and ask "is this good?" They get back a wall of generic feedback that could apply to literally any codebase. It feels useful for about 10 seconds, then you realize nothing actionable came out of it.


The problem isn't the AI. It's the prompt.


After hundreds of iterations, I've identified the patterns that separate a mediocre AI code review from one that actually finds bugs, catches security holes, and suggests fixes a senior engineer would be proud of.


Here's what I learned — and the exact prompts I now use daily.

K
KengineeringSenior Engineer
May 25, 2026