Archive

28 posts published so far

Using Simulators to Evaluate Multi-Turn AI Agents

Mundher Al-Shabi, PhD

Jun 9, 2026

Why Grep Won't Save Your RAG Pipeline

Mundher Al-Shabi, PhD

May 24, 2026

Harnessing Conversational AI

Mundher Al-Shabi, PhD

May 17, 2026

Vectorless RAG

Mundher Al-Shabi, PhD

May 4, 2026

Thoughts on Advanced Chunking Strategies for RAG

Mundher Al-Shabi, PhD

May 3, 2026

All You Need is a Good Chunking

Mundher Al-Shabi, PhD

Jul 14, 2025

AI Agent Experience (AX)

Mundher Al-Shabi, PhD

Jun 29, 2025

The Messy Reality of Evaluating GenAI Systems

Mundher Al-Shabi, PhD

Feb 9, 2025

The Decline of the "Prompt Expert": Why AI Is Making Prompt Engineering Obsolete

Mundher Al-Shabi, PhD

Feb 5, 2025

What Can Machine Learning Engineers Learn from Site Reliability Engineering?

Mundher Al-Shabi, PhD

Feb 5, 2025

The EU AI Act: First Compliance Deadline is Here

Mundher Al-Shabi, PhD

Feb 5, 2025

Why Optimizing for Long-Term Value (LTV) Beats Just Chasing Clicks in AdTech

Mundher Al-Shabi, PhD

Dec 28, 2023

Instead of using retrieval to enhance ChatGPT, why not use ChatGPT to improve the retrieval?

Mundher Al-Shabi, PhD

Dec 22, 2023

In-Context Few-Shots Prompting Approach

Mundher Al-Shabi, PhD

Dec 19, 2023

Is Gemini Really Better than ChatGPT?

Mundher Al-Shabi, PhD

Oct 29, 2023

Managing AI Risks in an Era of Rapid Progress

Mundher Al-Shabi, PhD

Oct 22, 2023

Can LLMs Self-critiquing Their Own Answers?

Mundher Al-Shabi, PhD

Oct 8, 2023

5 factors should be considered when selecting the Vector Search

Mundher Al-Shabi, PhD

Oct 7, 2023

Document Order and Retrieval Strategies for Enhanced LLM Performance

Mundher Al-Shabi, PhD

Oct 7, 2023

Vector Search vs. Vector Database

Mundher Al-Shabi, PhD

Oct 7, 2023

AI emits 130 to 2900 times less CO2e than a human when doing the same task!

Mundher Al-Shabi, PhD

Oct 7, 2023

No, you don’t need vector search to build your RAG

Mundher Al-Shabi, PhD

Archive

How to Build Privacy into LLM Agents Without Breaking Their Brains

Stacking Agent Memory: Checkpoints, Status Boards, and Active Context

Smart LLM Routing

Using Simulators to Evaluate Multi-Turn AI Agents

Why Grep Won't Save Your RAG Pipeline

Harnessing Conversational AI

Vectorless RAG

Thoughts on Advanced Chunking Strategies for RAG

All You Need is a Good Chunking

AI Agent Experience (AX)

The Messy Reality of Evaluating GenAI Systems

The Decline of the "Prompt Expert": Why AI Is Making Prompt Engineering Obsolete

What Can Machine Learning Engineers Learn from Site Reliability Engineering?

The EU AI Act: First Compliance Deadline is Here

Why Optimizing for Long-Term Value (LTV) Beats Just Chasing Clicks in AdTech

Instead of using retrieval to enhance ChatGPT, why not use ChatGPT to improve the retrieval?

In-Context Few-Shots Prompting Approach

Is Gemini Really Better than ChatGPT?

Managing AI Risks in an Era of Rapid Progress

Can LLMs Self-critiquing Their Own Answers?

5 factors should be considered when selecting the Vector Search

Document Order and Retrieval Strategies for Enhanced LLM Performance

Vector Search vs. Vector Database

AI emits 130 to 2900 times less CO2e than a human when doing the same task!

No, you don’t need vector search to build your RAG

Command Palette

How to Build Privacy into LLM Agents Without Breaking Their Brains

Stacking Agent Memory: Checkpoints, Status Boards, and Active Context

Smart LLM Routing

Using Simulators to Evaluate Multi-Turn AI Agents

Why Grep Won't Save Your RAG Pipeline

Harnessing Conversational AI

Vectorless RAG

Thoughts on Advanced Chunking Strategies for RAG

All You Need is a Good Chunking

AI Agent Experience (AX)

The Messy Reality of Evaluating GenAI Systems

The Decline of the "Prompt Expert": Why AI Is Making Prompt Engineering Obsolete

What Can Machine Learning Engineers Learn from Site Reliability Engineering?

The EU AI Act: First Compliance Deadline is Here

Why Optimizing for Long-Term Value (LTV) Beats Just Chasing Clicks in AdTech

Instead of using retrieval to enhance ChatGPT, why not use ChatGPT to improve the retrieval?

In-Context Few-Shots Prompting Approach

Is Gemini Really Better than ChatGPT?

Managing AI Risks in an Era of Rapid Progress

Can LLMs Self-critiquing Their Own Answers?

5 factors should be considered when selecting the Vector Search

Document Order and Retrieval Strategies for Enhanced LLM Performance

Vector Search vs. Vector Database

AI emits 130 to 2900 times less CO2e than a human when doing the same task!

No, you don’t need vector search to build your RAG