Adding a CI pass fail threshold - day 30
I brought my eval journey to the finish line today by integrating our small test dataset directly into our CI/CD pipeline with a pass/fail threshold.
All Post on 1 page
2026
I turned a defect into an eval - day 15
I found one AI bug today—and turned it into a permanent test in 10 minutes.
I put a price tag on quality - day 10
I tested two models today. One answer was only slightly better and much more expensive.
I tested the ‘boring’ requirement - day 05
Putting predictable constraints and standard expectations to the test, evaluating how the LLM judge grades standard formatting and basic rules.
My first AI eval was boring - day 02
Setting up a basic LLM evaluation only to find the initial results predictable, but discovering why simple tests are the best place to start.
The same prompt, 10 different answers - day 01
Running the exact same prompt multiple times reveals the inherent variability in LLM responses, a core challenge in AI testing.
Guide to implement Multi-tab Code Snippets in Jekyll 🧪
Written by - Millan Kaul
Saving 216 Minutes in 2.5 Years with Simple Docker Enhancements
How three minor Docker configuration changes shaved 33% off my Jekyll build times, saving hours of developer wait time.
How to Build Your First Local RAG Pipeline with Ollama, Qdrant, and Python
Learn how to run your first RAG pipeline locally with Ollama, Qdrant, Python, LangChain, guardrails, and RAGAS evals.
Machine Learning Pipelines: The Backbone of Reliable AI Systems
An ML pipeline turns raw data into deployable models through repeatable, automated steps that improve consistency, scale, and reliability.
Why AI Agents Need a Test Harness
AI agents do not become reliable because the model is bigger. They become reliable because the harness around the model is testable, observable, and continuo...
constitution.md in Spec-Driven Development
Here is what constitution.md is, and how developers, architects, and QA teams should use it in spec-driven development.
Spec-Driven Development: QA’s North Star in AI-Native Teams
QA is not disappearing in the AI era. It is becoming the layer that makes AI outputs reliable, testable, and safe.
QA Toolbox: Powering Reliable AI Outputs
QA is not disappearing in the AI era. It is becoming the layer that makes AI outputs reliable, testable, and safe.
Open Banking MCP: Compare Bank Rates in Your AI Assistant
Ask your AI to compare home loan rates, savings accounts, and credit cards instantly. Open Banking MCP brings Australian CDR data into Claude, Cursor, and VS...
LLM Hallucinations: Why Models Invent Facts Confidently
Written by - Millan Kaul
Zero-Shot vs Few-Shot Prompting: How LLMs Learn From Almost Nothing
Written by - Millan Kaul
LLM Fine-tuning: Customize Powerful Models for Your Needs
Written by - Millan Kaul
LLM Pre-training: Learning From Trillions of Words
Written by - Millan Kaul
Transformer Architecture: The Engine Behind Every LLM
Written by - Millan Kaul
Attention Mechanism: How LLMs Decide ‘What Matters Most’
Written by - Millan Kaul
Word Embeddings: How AI Understands ‘Similar Meaning’
Written by - Millan Kaul
What is Tokenization? How LLMs See Your Text
Written by - Millan Kaul
What is an LLM - Large Language Model ?
Written by - Millan Kaul
Where MCP Shines
“Single LLMs hallucinate. Multi‑agent systems multiply the problem.”
MCP: 5 Leadership Lessons
From hype to control. Here are the 5 truths every CTO must know.
How MCP Works?
“MCP handshake → tool call → your code runs. 3 minutes to understand.”
Why MCP?
“Last week my LLM swore the 2024 World Cup winner was ‘Moon United FC’. It was confident, detailed, and 100% hallucinated.”
When to Use MCP?
MCP = LLM lifeline when models hallucinate most.
What is MCP?
Model Context Protocol (MCP) = Standardized way for LLMs to discover and call your external tools/data.
2025
My global speaking journey at Tech Conferences & Meetups in 2025
Written by - Millan Kaul
The Hidden Cost of Quality Debt: What Leadership Doesn’t See
Written by - Gavin Cheung
How AI Agents Actually Collaborate: Real-World Workflows, Protocols, and Pitfalls
Written by - Millan Kaul
5 Well-Known and 5 Less-Known MCP Concepts with Examples
Written by - Millan Kaul
15 AI terms related or similar to MCP (Model Context Protocol) and Agent
Written by - Millan Kaul
20 AI acronyms and keywords with definitions and use cases
Written by - Millan Kaul
10 Foundational AI Building Block Concepts for Testers and Developers
Written by - Millan Kaul
A live implementation of a chatbot
Written by - Millan Kaul
The API Automation framework I wish I had known sooner
Written by - Millan Kaul
QE Leadership at 3 stage of org, your blueprint for QE Success
The most successful QE leaders don’t just enforce quality—they cultivate that environment…
How to Successfully collaborate with multiple Test Leads in a Large-Scale Projects
Master the art of collaborating with multiple QA leads in enterprise projects. Learn effective strategies for test coordination, risk management and successf...
2024
2024 in Review: QA, AI and Quality Engineering in Reflection at #QWM
Written by - Millan Kaul
Choosing between : Speed, Quality, Cost - in Test Automation
Written by - Millan Kaul
The Ultimate guide to complex JSON parsing using JavaScript, Python, Go, and Java
Written by - Millan Kaul
Importance of Test Data - with code example
Written by - Millan Kaul
WebDriver Saga
Written by - Neelam Pal
Say hello to Multiple : New Performance testing tool
Written by - Millan Kaul
Exponential backoff strategy - explained with {code}
Written by - Millan Kaul
Navigating the Tempest: QA in the Age of Hyper-Driven Development
Written by - Dennis Nyawira
How I turned my blog into a Docker based development paradise 🐳 - Try It Yourself!
Written by - Millan Kaul
k6 - web dashboards + HTML report 📊
Written by - Millan Kaul
Easiest way to understand How Appium works
Written by - Millan Kaul
2023
A/B Tetsing - in 5 steps
Written by - Millan Kaul
A tasty analogy: Quality and testing explained like a piece of cake 🍰
Written by - Millan Kaul
Starting My Corporate Journey: working as an intern/graduate
Written by - Jing Deng
API testing with nightwatch in 15 mins
Written by - Millan Kaul
Run your first RESTful API service using docker
Written by - Millan Kaul
How to Shift-Left without writing Code 👩💻
Written by - Millan Kaul
The paradigm of Quality - Optimised
Written by - Alejandro Sanchez Giraldo , ChatGPT , Gith...
7 most used util and helper methods in test automation project
Written by - Millan Kaul
The paradigm of Quality - Built-In
Written by - Alejandro Sanchez Giraldo , ChatGPT and Gi...
The paradigm of Quality - Embedded
Written by - Alejandro Sanchez Giraldo , ChatGPT and Gi...
Evolution of Reliability Tester and AI testing
Written by - Karthik Hariharan
Base64 decoding using Postman
Written by - Millan Kaul
Two Timeless Concepts
Written by - Alejandro Sanchez Giraldo and ChatGPT
The paradigm of Quality
Written by - Alejandro Sanchez Giraldo and ChatGPT
Leading by Example: The Power of a Strong Software Testing Leader
Written by - Millan Kaul
Exploratory Testing 🔎 + Automation ⚙️
Written by - Millan Kaul
As a Dev 👨💻, why you should be better friends with QA ❤️
Written by - Millan Kaul
Plus Ca Change in Test Automation
Written by - Paul Maxwell-Walters
Installing and running Postman app on linux (REHL 8.x)
Written by - Millan Kaul
What is 𝗻𝘃𝗺 ❓️ - ⓝⓥⓜ 𝟭𝟬𝟭 in 5 minutes !
Written by - Millan Kaul
How to win dev friends as a QA 🤝
Written by - Millan Kaul
Love-Hate Relationship with Selenium Automation
Written by - Millan Kaul
How to handle 404, 500 and more - using fetch()API in JavaScript
Written by - Millan Kaul
How to decode JSON Web Token (JWT) offline
Written by - Millan Kaul
Is Open Banking just another API❓
Written by - Millan Kaul
2022
Why test automation will be key focus in 2023 ?
Written by - Millan Kaul
2021
Welcome to #QualityWithMillan
Welcome to #QualityWithMillan !
Running a local server and API testing in less than 10 minutes
Written by - Millan Kaul
5 misconceptions regarding Test Automation
Written by - Millan Kaul