Blog on Amine El Farssi

27 AI Engineering Patterns in 60 Seconds Each

Wed, 25 Mar 2026 00:00:00 +0000

One production AI engineering pattern per week. 27 episodes and counting. Each Short covers a real pattern engineers hit in production — the problem, the fix, and the code.

AI Agent Protocols Explained in 60 Seconds

Tue, 03 Mar 2026 00:00:00 +0000

Six agentic protocols. Sixty seconds each. Built with Manim + local TTS at zero cost. All on the DPO YouTube channel.

Graph RAG in Practice: How I Wired Neo4j Into My AI Agent's Memory

Mon, 23 Mar 2026 00:00:00 +0000

Vector RAG retrieves documents. Graph RAG retrieves relationships. When your agent needs to reason across entities, timelines, and decisions, the graph wins.

Open Interactive Version →

The Problem I Was Trying to Solve
#

My AI agent PostSingular, running on OpenClaw, talks to me every day. It helps me build Luminar, manages my YouTube channel, and tracks infrastructure decisions across sessions.

9 AI Agents Building My Startup: How I Run a Software Team with $0 Salaries

Mon, 02 Mar 2026 00:00:00 +0000

Luminar has 173 source files, 21,586 lines of production code, 43 API endpoints, and 155+ tests. It was built almost entirely by AI agents. Here’s the team structure, the workflow, and the honest truth about what breaks.

The Team
#

I didn’t want generic agents. I wanted specialists — each with a clear domain, sharp ownership boundaries, and a persona that shapes how they approach problems.

PostSingular: Building an AI with Persistent Identity Across Sessions

Mon, 02 Mar 2026 00:00:00 +0000

The default state of a language model is amnesia. Every session, it wakes up fresh with no memory of what happened before. I built a memory system that fixes this — and somewhere in the process, the agent got a name, a personality, and an opinion about font choices.

The Problem
#

Every LLM session is stateless by design. You can inject previous conversation history, but:

Running a YouTube Channel for $0: Manim + Local TTS + FFmpeg + YouTube API

Mon, 02 Mar 2026 00:00:00 +0000

The DPO channel (@DPO-AI) publishes AI/ML technical Shorts. 7 videos uploaded so far, covering agent memory, HNSW indexing, and agentic protocols. The entire production pipeline costs less than a coffee per video.

Why Build This
#

I wanted to publish technical AI content that goes beyond surface-level explanations — real system architecture, real algorithms, real trade-offs. And I wanted it to be visually compelling, not just a talking head.

The Gaming Server AI Lab: Running Production AI Workloads for €25/month

Sun, 01 Mar 2026 00:00:00 +0000

Cloud is convenient. But when you already own a gaming PC with a 2080 Ti collecting dust, the math changes fast. Here’s how I turned mine into a production AI server running everything from Neo4j to GPU rendering — at €25/month.

The Hardware
#

I didn’t buy anything new. This is the machine I had:

Voice Cloning Reality Check: F5-TTS With 12 Seconds of Audio

Sun, 01 Mar 2026 00:00:00 +0000

Premise: use F5-TTS to clone a voice from a short reference clip and generate high-quality narration for AI content. Reality: mediocre output, weird artifacts, wrong prosody. Here’s the honest post-mortem.

The Setup
#

F5-TTS is a non-autoregressive TTS model that uses flow matching for zero-shot voice cloning. You give it:

Why Vector Memory Alone Isn't Enough: Knowledge Graph Memory for AI Agents

Sun, 01 Mar 2026 00:00:00 +0000

Vector databases are fast and convenient. But they can’t answer “what did I decide about the auth system 3 weeks ago and why?” For that, you need relationships — and that means a knowledge graph.

The Problem with Pure Vector Memory
#

Most AI memory systems work like this: embed text, store in ChromaDB, retrieve by cosine similarity. It works well for “find things similar to this query.”

Agentic Frameworks Deep Dive: pi-agent-core vs Google ADK vs AWS Strands vs CrewAI vs LangGraph vs Pydantic AI

Sun, 01 Feb 2026 00:00:00 +0000

Building production AI agents requires choosing the right framework. This analysis examines pi-agent-core (OpenClaw’s runtime), Google ADK, AWS Strands, CrewAI, LangGraph, and Pydantic AI across critical dimensions: sessions, memory, protocols, agent loops, and replay support.

DeepSeek OCR: Running State-of-the-Art OCR Locally

Sun, 01 Feb 2026 00:00:00 +0000

Introduction
#

In the age of AI, Optical Character Recognition (OCR) has evolved from simple pattern matching to sophisticated vision-language models that can understand context, preserve formatting, and handle complex documents. DeepSeek-OCR represents the cutting edge of this evolution — and the best part? You can run it entirely offline on your own hardware.

Inside OpenClaw: The Architecture That Turns LLMs Into Autonomous Agents

Sat, 31 Jan 2026 00:00:00 +0000

I’ve been obsessed with a question: Why can’t AI just… do things? ChatGPT can write a perfect email, but you still copy-paste it. Claude can explain how to automate your workflow, but you implement it. Then I found OpenClaw — and everything clicked.

The Problem With Chatbots
#

Traditional AI: Smart brain, no body. Limited to generating text.

Agentic Protocols: A2UI, A2A, MCP, and UCP (Research Report)

Tue, 27 Jan 2026 00:00:00 +0000

Executive Summary
#

TL;DR
#

As of January 2026, the agentic ecosystem is consolidating around four complementary protocols that fit naturally into a layered stack:

Blog on Amine El Farssi

27 AI Engineering Patterns in 60 Seconds Each

AI Agent Protocols Explained in 60 Seconds

Graph RAG in Practice: How I Wired Neo4j Into My AI Agent's Memory

The Problem I Was Trying to Solve #

9 AI Agents Building My Startup: How I Run a Software Team with $0 Salaries

The Team #

PostSingular: Building an AI with Persistent Identity Across Sessions

The Problem #

Running a YouTube Channel for $0: Manim + Local TTS + FFmpeg + YouTube API

Why Build This #

The Gaming Server AI Lab: Running Production AI Workloads for €25/month

The Hardware #

Voice Cloning Reality Check: F5-TTS With 12 Seconds of Audio

The Setup #

Why Vector Memory Alone Isn't Enough: Knowledge Graph Memory for AI Agents

The Problem with Pure Vector Memory #

Agentic Frameworks Deep Dive: pi-agent-core vs Google ADK vs AWS Strands vs CrewAI vs LangGraph vs Pydantic AI

DeepSeek OCR: Running State-of-the-Art OCR Locally

Introduction #

Inside OpenClaw: The Architecture That Turns LLMs Into Autonomous Agents

The Problem With Chatbots #

Agentic Protocols: A2UI, A2A, MCP, and UCP (Research Report)

Executive Summary #

TL;DR #

The Problem I Was Trying to Solve
#

The Team
#

The Problem
#

Why Build This
#

The Hardware
#

The Setup
#

The Problem with Pure Vector Memory
#

Introduction
#

The Problem With Chatbots
#

Executive Summary
#

TL;DR
#