Leanpub Header

Skip to main content
Leanpub Clips — big ideas, small videos

Leanpub Clips

Short clips from Leanpub's videos.

About

These are short clips from our Leanpub videos — our Launch videos, Podcast videos, and more from our YouTube channel.

Subscribe on YouTube
Podcast

Would You Go to University to Become a Software Architect?

Systems Thinking for Agentic AI by Ediz Najim

An LLM is not an AI system.Systems Thinking for Agentic AI shows software engineers and architects how to design reliable AI applications with prompts, RAG, tools, memory, orchestration, guardrails, evaluation, observability, and runtime control.Move beyond chatbot demos and learn how to build production-ready agentic AI systems you can reason about, measure, debug, operate, and improve

Podcast

Why Your LLM Is NOT an AI System (Most Teams Get This Wrong)

Systems Thinking for Agentic AI by Ediz Najim

An LLM is not an AI system.Systems Thinking for Agentic AI shows software engineers and architects how to design reliable AI applications with prompts, RAG, tools, memory, orchestration, guardrails, evaluation, observability, and runtime control.Move beyond chatbot demos and learn how to build production-ready agentic AI systems you can reason about, measure, debug, operate, and improve

Podcast

Why Your LLM Can't Be the Final Authorization Layer

Systems Thinking for Agentic AI by Ediz Najim

An LLM is not an AI system.Systems Thinking for Agentic AI shows software engineers and architects how to design reliable AI applications with prompts, RAG, tools, memory, orchestration, guardrails, evaluation, observability, and runtime control.Move beyond chatbot demos and learn how to build production-ready agentic AI systems you can reason about, measure, debug, operate, and improve

Podcast

The Clearest Definition of an AI Agent You'll Ever Hear

Systems Thinking for Agentic AI by Ediz Najim

An LLM is not an AI system.Systems Thinking for Agentic AI shows software engineers and architects how to design reliable AI applications with prompts, RAG, tools, memory, orchestration, guardrails, evaluation, observability, and runtime control.Move beyond chatbot demos and learn how to build production-ready agentic AI systems you can reason about, measure, debug, operate, and improve

Launch

Build Your Own Thing: Why Passion + Understanding Beats Just Following Steps

Your Own 24/7 Internet Radio by Ivaylo Demidov

Build your own 24/7 internet radio in a single weekend — on a €5 server, understood down to the last line. Ten chapters from bare server to on-air: the tower (Icecast), the robot (Liquidsoap), the door (nginx). Every step tested live, every trap marked. Friday it's a napkin sketch; Sunday night a stranger presses play, and it plays.

Launch

How AI Enabled Solo Author to Do Robust Testing on a Cloud Book

Apache CloudStack — A Production Deployment Guide by Michael Hinsley

When a license renewal lands at 567% of last year's bill, renting your infrastructure stops being a strategy. This is the escape tunnel: a complete production build of Apache CloudStack 4.22 LTS — KVM, Ceph, OS10 leaf-spine — across a three-city UK estate, written by an engineer with 32 years of building the real thing. Own your cloud down to the last packet.

Launch

He Built MatrixClaw: AI That Builds, Breaks & Governs Infrastructure

Apache CloudStack — A Production Deployment Guide by Michael Hinsley

When a license renewal lands at 567% of last year's bill, renting your infrastructure stops being a strategy. This is the escape tunnel: a complete production build of Apache CloudStack 4.22 LTS — KVM, Ceph, OS10 leaf-spine — across a three-city UK estate, written by an engineer with 32 years of building the real thing. Own your cloud down to the last packet.

Launch

Python Scripts Make Complex Harness Setup Easy — MatrixCore Nano on GitHub

Apache CloudStack — A Production Deployment Guide by Michael Hinsley

When a license renewal lands at 567% of last year's bill, renting your infrastructure stops being a strategy. This is the escape tunnel: a complete production build of Apache CloudStack 4.22 LTS — KVM, Ceph, OS10 leaf-spine — across a three-city UK estate, written by an engineer with 32 years of building the real thing. Own your cloud down to the last packet.

Launch

Why Sysadmins Fled to Apache CloudStack After Their Hypervisor Got Acquired

Apache CloudStack — A Production Deployment Guide by Michael Hinsley

When a license renewal lands at 567% of last year's bill, renting your infrastructure stops being a strategy. This is the escape tunnel: a complete production build of Apache CloudStack 4.22 LTS — KVM, Ceph, OS10 leaf-spine — across a three-city UK estate, written by an engineer with 32 years of building the real thing. Own your cloud down to the last packet.

Launch

When a Cloud Product Gets Acquired and Everything Changes

Apache CloudStack — A Production Deployment Guide by Michael Hinsley

When a license renewal lands at 567% of last year's bill, renting your infrastructure stops being a strategy. This is the escape tunnel: a complete production build of Apache CloudStack 4.22 LTS — KVM, Ceph, OS10 leaf-spine — across a three-city UK estate, written by an engineer with 32 years of building the real thing. Own your cloud down to the last packet.

Launch

Kill One Agent Before It Takes Down Everything

Rethinking Performance Engineering for Agentic AI by Kandasamy Selvaraj

Your agent passed every load test and timed out in production anyway. This free practitioner's guide shows why the traditional performance playbook breaks for agentic AI, and what replaces it: latency budgets, bounded autonomy, token SLOs, and production-grade observability, from a performance engineering and observability architect with two decades in production.

Launch

Old Engineering Primitives Still Apply to AI — Just Differently

Rethinking Performance Engineering for Agentic AI by Kandasamy Selvaraj

Your agent passed every load test and timed out in production anyway. This free practitioner's guide shows why the traditional performance playbook breaks for agentic AI, and what replaces it: latency budgets, bounded autonomy, token SLOs, and production-grade observability, from a performance engineering and observability architect with two decades in production.