MLflow 3 + PayFlow AI — Part 8
GitHub Actions CI/CD + Structured Logs + Loki + Grafana + MLflow Tracing
Explore posts by discipline, then filter by the technologies and topics inside each series.

GitHub Actions CI/CD + Structured Logs + Loki + Grafana + MLflow Tracing

PostgreSQL + MinIO + Docker Compose: Build the Self-Hosted MLOps Stack

MLflow Serving + Production FastAPI

Model Registry, Versions, Champion & Challenger

Model Evaluation & Production Quality Gates

Scale the Experiment: Random Forest, XGBoost, Run Comparison & MLflow Autologging

Build Our First Real ML Experiment: Payment Success Prediction

Build MLflow locally in VS Code, understand the Tracking Server architecture, connect the UPI Transactions 2024 dataset, and create our first reproducible experiment step by step.

Build an End-to-End Customer Churn MLOps Platform

From weak learners to a strong ensemble: building an end-to-end employee attrition prediction system with AdaBoost, scikit-learn, MLflow, FastAPI, Streamlit, Docker, GitHub Actions, and Azure.

Azure × AWS × Google Cloud — AI, ML, GenAI, RAG, Agents, MLOps & Enterprise Architecture

FastAPI + Pydantic + MLflow Champion + Service Layer + Batch Inference + Swagger + Streamlit

Enterprise Credit Card Fraud Detection MLOps

Git + DVC + Deterministic Pipelines + Data/Model Lineage

Part 1 : From Raw Data → Production ML → Continuous Training → AI Platform

Complete End-to-End ML + MLOps Project

From Zero to Production MLOps with Iris Flower Classification

Classification, Regression, Real-World Projects, MLOps, System Design, Deployment & Interview Preparation

Why understanding the data comes before building the model

From Excel, SQL & Power BI to Senior Analyst, Analytics Lead and AI-Native Decision Intelligence — without accidentally becoming a Data Engineer

SQL → Advanced SQL Problem Solving → Data Modeling → PostgreSQL → Warehouses → BigQuery/Snowflake → Python for Data → Spark → dbt → Airflow → Kafka → Lakehouse → Cloud Data Engineering → Power BI

From Raw Transactions → Data Validation → EDA → Feature Engineering → Multiple Models → Imbalance Handling → Cross-Validation → Hyperparameter Tuning → Threshold Optimization → Explainability → Final

From Matplotlib Foundations → Statistical Visualization → Better ML Decisions

Understand the Data Before You Ask a Model to Learn From It

Scale the Experiment: Random Forest, XGBoost, Run Comparison & MLflow Autologging

From weak learners to a strong ensemble: building an end-to-end employee attrition prediction system with AdaBoost, scikit-learn, MLflow, FastAPI, Streamlit, Docker, GitHub Actions, and Azure.

XGBoost exposes a scikit-learn-compatible estimator interface, including classification through XGBClassifier.

From Ensemble Learning → Fraud Probability → API → Dashboard → Docker → CI/CD → Cloud → Monitoring → Retraining

Complete End-to-End ML + MLOps Project

From Zero to Production MLOps with Iris Flower Classification

End-to-End Telecom Customer Churn Prediction

Classification, Regression, Real-World Projects, MLOps, System Design, Deployment & Interview Preparation

From Raw Numbers → Visual Patterns → Better ML Decisions

From Raw Tabular Data → Clean, Model-Ready Dataset

From Python Lists to Fast Numerical Computing

From Python Fundamentals → Advanced Concepts → ML-Ready Programming

From a Business Problem to a Production ML System

Understand Data, Features, Targets, Parameters, Metrics, Overfitting, Bias & Variance — The Vocabulary Every ML Engineer Must Know

From Supervised Learning to Reinforcement Learning — How Machine Learning Systems Move From Data to Production

How Computers Learn Patterns From Data Instead of Following Hard-Coded Rules

From Narrow AI to Super Intelligence

How 70 Years of AI History Created the Modern AI Revolution Series: 100 Days of Machine Learning & AI Engineering Phase 1 — Machine Learning Foundations Module 1 — Artificial Intelligence

Phase 1 — Machine Learning Foundations Module 1 — Artificial Intelligence Chapter: ML-001 — What is Artificial Intelligence?

Enterprise Software Engineer to AI Architect : Enterprise Grade Projects

From Enterprise Software Engineer to AI Architect

From Enterprise Software Engineer to AI Architect

Why I'm Starting This Journey: From Enterprise Software Engineer to AI Architect. A public learning journey documenting the transition from building enterprise software to designing production-grade A

From Text Prompts to Pixels: Understanding How AI Creates Images

From Open-Source Foundation Models to Fine-Tuned Production AI

From BERT and GPT to Vision Transformers, Mixture-of-Experts, GQA, and modern LLMs — a practical guide to what Transformers are, why different types exist, and when each one is used.

From Pixels to Perception — From Fundamentals to Production-Grade Vision AI

From Artificial Neurons to Your First Neural Network

🔥 Becoming a Deep Learning Expert: PyTorch, Computer Vision, Transformers & Enterprise AI Systems

From Raw Numbers → Visual Patterns → Better ML Decisions

From Raw Tabular Data → Clean, Model-Ready Dataset

From Python Lists to Fast Numerical Computing

From Python Fundamentals → Advanced Concepts → ML-Ready Programming

From Text Prompts to Pixels: Understanding How AI Creates Images

From BERT and GPT to Vision Transformers, Mixture-of-Experts, GQA, and modern LLMs — a practical guide to what Transformers are, why different types exist, and when each one is used.

Teaching PandaLM How to Read - Continuation of building An Open Foundational Small Language Model for Engineering...

Building the Training Corpus for a Foundational Engineering SLM

Building the Laboratory for a Foundational Engineering SLM

An Open Foundational Small Language Model for Engineering

From Enterprise RAG to an Enterprise Engineering Agent What → Why → How → Real Code → Business Scenarios → Security → Deployment

From Naive Vector Search to Secure, Observable, Evaluated Enterprise RAG

Models, Prompts, Structured Output, Runnables, Tools, Retrieval & Your First Enterprise RAG System

From a real production incident to a working AI Engineering Copilot — built entirely in Python on Google Colab with MCP tools, local LLMs, RAG, human approvals, FastAPI, Gradio, observability...

Azure × AWS × Google Cloud — AI, ML, GenAI, RAG, Agents, MLOps & Enterprise Architecture

🔥 Becoming a Deep Learning Expert: PyTorch, Computer Vision, Transformers & Enterprise AI Systems

How 70 Years of AI History Created the Modern AI Revolution Series: 100 Days of Machine Learning & AI Engineering Phase 1 — Machine Learning Foundations Module 1 — Artificial Intelligence

The Retrieval Architecture Decision Guide for Modern AI Builders

Stop Building Dumb Chatbots — Build RAG-Powered AI That Actually Knows Your Data

Automation, Workflows, Orchestration & How n8n Fits In

From Workflow Automation to Production-Grade AI Agents, Durable Systems & Enterprise Platforms

From Enterprise RAG to an Enterprise Engineering Agent What → Why → How → Real Code → Business Scenarios → Security → Deployment

From a real production incident to a working AI Engineering Copilot — built entirely in Python on Google Colab with MCP tools, local LLMs, RAG, human approvals, FastAPI, Gradio, observability...

Azure × AWS × Google Cloud — AI, ML, GenAI, RAG, Agents, MLOps & Enterprise Architecture

PostgreSQL & Business Data

Credentials, API Keys & OAuth

Loops, Batches & Pagination

IF, Switch, Merge & Business Decision Logic

HTTP Request Node & REST API Masterclass

Triggers, Webhooks & Building Your First Real HTTP Workflow

Mastering Expressions & Dynamic Data

Understanding the n8n UI, Nodes, Executions, JSON, Items & Data Flow

Install n8n Locally with Docker + PostgreSQL

Automation, Workflows, Orchestration & How n8n Fits In

From Workflow Automation to Production-Grade AI Agents, Durable Systems & Enterprise Platforms

From Empty VS Code Workspace to a Deployed Azure Workflow

Azure Logic Apps: The Complete Mental Model Before You Build Anything

From a Business Problem to a Production ML System

Install n8n Locally with Docker + PostgreSQL

From Cloud Fundamentals to Enterprise Multi-Cloud & AI Architecture — Azure, AWS, Google Cloud (GCP)

GitHub Actions CI/CD + Structured Logs + Loki + Grafana + MLflow Tracing

PostgreSQL + MinIO + Docker Compose: Build the Self-Hosted MLOps Stack

From Empty VS Code Workspace to a Deployed Azure Workflow

Azure Logic Apps: The Complete Mental Model Before You Build Anything

From Outlook, Teams, SharePoint and OneDrive events to a production-grade event-driven enterprise platform

From weak learners to a strong ensemble: building an end-to-end employee attrition prediction system with AdaBoost, scikit-learn, MLflow, FastAPI, Streamlit, Docker, GitHub Actions, and Azure.

SQL → Advanced SQL Problem Solving → Data Modeling → PostgreSQL → Warehouses → BigQuery/Snowflake → Python for Data → Spark → dbt → Airflow → Kafka → Lakehouse → Cloud Data Engineering → Power BI

The Role That Connects Software Engineering, AI, Cloud, and Real Business Outcomes

Azure × AWS × Google Cloud — AI, ML, GenAI, RAG, Agents, MLOps & Enterprise Architecture

From Ensemble Learning → Fraud Probability → API → Dashboard → Docker → CI/CD → Cloud → Monitoring → Retraining

Git + DVC + Deterministic Pipelines + Data/Model Lineage

From a Business Idea → Requirements → Architecture → APIs → Data → Infrastructure → Production System

From First Principles to 100+ Real-World Architectures, HLD, LLD, Distributed Systems, Cloud, Performance, Reliability, Security & AI System Design

Building Production-Ready .NET Microservices with ConfigMaps, Secrets, Volumes, Deployments, StatefulSets, DaemonSets, Jobs & CronJobs

A Practical Guide to Building, Deploying, Scaling, and Operating .NET Microservices on Kubernetes

A Complete Step-by-Step Guide

A Practical Guide with Azure Service Bus & .NET Core

HTTP Request Node & REST API Masterclass

From Empty VS Code Workspace to a Deployed Azure Workflow

Create the Right Object Without Coupling Your Business Logic to Concrete Classes

One Instance, One Shared Resource — Classic Singleton vs AddSingleton in Real .NET Applications

The Foundation Before We Start Implementing Design Patterns in .NET 10 & C# 14

The Foundation You Need Before Learning Singleton, Factory, Strategy, Decorator, or Anything Else

From Outlook, Teams, SharePoint and OneDrive events to a production-grade event-driven enterprise platform

: Python + C# with Real-World Examples

The Role That Connects Software Engineering, AI, Cloud, and Real Business Outcomes

From Python Fundamentals → Advanced Concepts → ML-Ready Programming

Building Production-Ready .NET Microservices with ConfigMaps, Secrets, Volumes, Deployments, StatefulSets, DaemonSets, Jobs & CronJobs

A Practical Guide to Building, Deploying, Scaling, and Operating .NET Microservices on Kubernetes

Day 1 of My AI Engineering Journey

A practical, step-by-step guide to mastering threads, tasks, and synchronization in modern .NET applications

A Complete Step-by-Step Guide

A Practical Guide with Azure Service Bus & .NET Core

From a real production incident to a working AI Engineering Copilot — built entirely in Python on Google Colab with MCP tools, local LLMs, RAG, human approvals, FastAPI, Gradio, observability...

SQL → Advanced SQL Problem Solving → Data Modeling → PostgreSQL → Warehouses → BigQuery/Snowflake → Python for Data → Spark → dbt → Airflow → Kafka → Lakehouse → Cloud Data Engineering → Power BI

: Python + C# with Real-World Examples

From Raw Tabular Data → Clean, Model-Ready Dataset

From Python Lists to Fast Numerical Computing

From Python Fundamentals → Advanced Concepts → ML-Ready Programming