Dr Ahmad H. Estabrag
AI Engineering Laboratory

Dr Ahmad H. Estabrag

Investigating and Engineering Production-Ready AI Systems

I’m a software architect, researcher and educator with more than 30 years of experience designing, studying and teaching complex software systems.

This is my AI Engineering Laboratory—a place where I investigate how modern AI systems work, why they fail, and how they can be engineered to become reliable, maintainable and fit for production.

The work spans LLM systems, RAG, agentic systems and computer vision, explored through engineering case studies, practical projects, architecture, experimentation and evaluation.

Ask about my work Explore the Laboratory View Case Studies
Guiding principle Production AI is Systems Engineering.
Free Technical Seminar

RAG Beyond the Demo

An Engineering Perspective for Software Developers

Building a RAG demo is relatively straightforward. Building a RAG system that is reliable, maintainable and ready for real-world use is a very different engineering problem.

This free 90-minute seminar looks beyond the basic retrieve-and-generate pipeline: where simple implementations break down, which architectural decisions matter, and how to think about RAG as a production software system.

Thursday, 26 November 2026 · 6:30–8:00 pm BST · Online
Register Free Seminar Details
The Laboratory

Investigating AI Systems Through Engineering

The laboratory brings together research, software architecture and practical development to investigate the engineering challenges behind production AI systems.

My work is driven by a longstanding interest in complex systems: understanding how they work, analysing why they succeed or fail, evaluating alternative approaches, and identifying the principles that make them dependable.

Rather than treating AI as a collection of tools, the laboratory studies complete systems—including models, software, data, infrastructure, hardware, operations and people.

01Observe
02Investigate
03Experiment
04Evaluate
05Engineer
06Share
Build

Practical Projects

Reference implementations, prototypes, repositories and working systems.

Investigate

Engineering Case Studies

Structured experiments, findings, trade-offs and recommendations.

Explain

Engineering Articles

Architecture, principles and clear explanations for software professionals.

Teach

Technical Education

Seminars, workshops, courses and professional learning programmes.

Engineering Case Studies

Structured Investigations into Production AI

Each case study starts with an engineering question, defines an experiment, evaluates evidence and extracts reusable lessons.

AECS-001Planned

Choosing the Right Chunk Size

How chunk size affects retrieval quality, context construction, latency and cost.

RAG · Retrieval · Evaluation
AECS-002Planned

Can Metadata Improve Retrieval?

A comparison of useful, noisy and missing metadata under controlled retrieval tests.

Metadata · Search · Experiments
AECS-003Planned

Does Hybrid Search Really Improve Results?

A measured comparison of semantic, keyword and hybrid retrieval strategies.

Semantic Search · BM25 · Hybrid
Explore Engineering Case Studies →
Projects & Open Engineering Work

Building Systems, Not Just Demonstrations

Practical repositories and development projects that turn engineering questions into working systems.

RAG Engineering

Software Engineering RAG

A multi-project repository exploring RAG as a software engineering discipline, beginning with codebase intelligence and evolving through real implementations.

Explore on GitHub →
Computer Vision

Table Tennis Intelligence

A product-oriented computer vision project investigating ball tracking, player detection, event analysis and real-time sports intelligence.

In development
Production AI

Production-Ready AI Systems

Architecture, evaluation, observability, failure handling, security, scalability, maintainability and operations across modern AI systems.

Research programme
Engineering Articles

Explaining the Principles Behind the Systems

Articles explain concepts and architectural ideas. Case studies remain separate: they investigate specific questions through evidence and experimentation.

01
RAG Engineering

What Software Engineers Get Wrong About RAG

Why production RAG is as much an architecture and systems problem as an AI problem.

Read →
02
Embeddings

Embeddings: A Software Engineer’s Perspective

Understanding embeddings as an architectural capability rather than only mathematical vectors.

Read →
03
Computer Vision

From Model to System: Engineering a Computer Vision Pipeline

How preprocessing, inference, evaluation, integration and deployment turn a model into a usable system.

Read →
View all Engineering Articles →
Technical Education

Teaching Engineers How to Move from Models to Systems

Engineering-first education for software professionals who want to design, evaluate and operate dependable AI systems.

01

Technical Seminars

Focused sessions on architecture, RAG, evaluation and production AI.

02

Practical Workshops

Hands-on engineering exercises, experiments and guided implementation.

03

Professional Programmes

Structured courses and bootcamps for developers and engineering teams.

04

Corporate Training

Tailored learning aligned with organisational systems and engineering goals.

Explore Technical Education
About the Investigator

Research Thinking Meets Software Architecture

I am a software engineer, architect and educator with a PhD in Software Engineering and more than 30 years of experience spanning software development, enterprise architecture, university teaching, research and consulting.

Throughout my career, I have been fascinated by complex systems. I enjoy studying how they work, analysing why they succeed or fail, evaluating competing approaches, and identifying the engineering principles that make them reliable and maintainable.

My academic research experience and practical architecture work now come together in this laboratory, where I investigate the transition from AI models and prototypes to complete production systems.

1990s

Software Development

C/C++ · Object-Oriented Systems · Software Quality

2000s

Enterprise Software

Middleware · Distributed Systems · Integration

2000s–2010s

Research & Education

Software Design · Patterns · Neural Networks · MSc Supervision

2010s

Enterprise Architecture

SOA · BPM · Analytics · Integration · Blockchain

Today

AI Engineering Laboratory

LLM Systems · RAG · Agentic Systems · Computer Vision · Production AI

Engineering Philosophy

Production AI is Systems Engineering

Models matter, but production systems also depend on data, software, infrastructure, hardware, architecture, evaluation, operations and people.

Introduction

Welcome to the AI Engineering Laboratory

In the introductory video, I explain why I investigate complex systems, how research and engineering shape my work, and what you will find across the laboratory’s projects, case studies, articles and educational resources.

Introduction video · Coming soon
Introduction Video Coming soon
Contact

Let’s Investigate, Engineer and Learn

Interested in AI engineering, technical education, research collaboration or the practical challenges of moving AI systems into production?

Contact Me Connect on LinkedIn