Agile Buddha

Most conversations about AI in software delivery start with the tool – e.g. context framework, Cursor, which model to use, which vendor.

They skip the harder question: is your delivery pipeline ready for AI in the first place?

I have been working with banks and large enterprises on delivery transformation over the years.

I recently built an AI-augmented delivery pipeline from scratch on actual code — five stages with real GitHub integration, security scanning, and compliance narrative drafting.

Here is what I found: AI applied to a well-functioning pipeline reduces friction. AI applied to a broken pipeline just moves the constraint forward. 

The speed of the wrong thing is not progress.

Before you add AI to your pipeline, here are seven things that need to be in place or actively in progress.

[Read more…] about 7 Things A Delivery Pipeline Needs Before AI Can Help

There is no shortage of articles telling you what RAG is.

This is not one of them.

This is what happens when you actually build one — over real content, with real questions, and an honest evaluation of what works and what does not.

What Is RAG and Why Should You Care?

RAG stands for Retrieval Augmented Generation.

The idea is simple. Before answering your question, the AI searches your documents, finds the most relevant pieces, and uses those to construct a grounded answer — not a generic one.

Think of it as the difference between asking a colleague who has read your internal policy documents versus asking someone who has only read the internet.

Most enterprise AI assistants being deployed right now use this approach. Internal knowledge bots, policy assistants, code documentation tools — RAG is underneath most of them.

What I Built

I wanted to understand what enterprises actually face when they deploy these systems. The only honest way to do that was to build one myself and stress-test it.

So I built a RAG system over 14 years of my own content — 111 blog posts from agilebuddha.in and my book on Agile estimation. Then I ran real questions against it and documented every failure.

The technology itself took eight focused sessions of 60-90 minutes each. It is not rocket science.

What came after building it — that is where it gets interesting.

What I Found

[Read more…] about 14 Years of Writing. One AI System. Here’s What It Found.

I was recently working with a software team that just received AI coding tool licences, one for every developer on the team. Their leadership was excited. The CTO had made the call personally. AI-assisted development was going to change everything.

Sprint 1 ended. Not a single story was done.

Not in review. Not in testing. Not deployed. Done.

I want to tell you this had nothing to do with AI coding tool.

The team did not know how to use it well yet – that was true – but that was not the reason.

The real reason was that the constraint was somewhere else entirely.

[Read more…] about Your Team Got AI Tools. Why Isn’t Anything Moving?