Decoding AI Magazine

Decoding AI Magazine

Home
Notes
Chat
LLM Engineer's Handbook
Agentic AI Engineering Course
Roadmaps
Perks
Contact Me
Archive
About

Advanced

How Evaluation-Driven Development (EDD) Works
Turn every AI agent change into a measured experiment you compare before and after to detect regressions and measure performance.
 • Paul Iusztin and Alejandro Aboy
How to Keep Your AI Agent's Knowledge Graph Clean
The resolution, deduplication, and review pipeline that keeps agent memory usable as it grows.
 • Paul Iusztin
Stop Chasing the Perfect Ontology
Start with a fixed, generic base and extend only when your data demands it.
 • Paul Iusztin
What Held Up at 3 AM: One Engineer's RAG Case Study
You iterate. You evaluate. Weave CLI unifies 11 vector databases into one workflow.
 • Paul Iusztin and dr.max
Scaling to 120+ AI Agents Without Losing Control
How two-tier orchestration keeps multi-agent systems debuggable
 • Lucian Lature
From 0 to Pro AI Engineering Roadmap
From Raw Data to LLM Fine-Tuning, RAG and LLMOps
 • Paul Iusztin
LLMOps for production agentic RAG
Evaluating and monitoring LLM agents with SmolAgents and Opik
 • Paul Iusztin and Anca Ioana Muscalagiu
Build RAG pipelines that actually work
Advanced RAG powering AI assistants
 • Anca Ioana Muscalagiu and Paul Iusztin
Playbook to fine-tune and deploy LLMs
Specialized open-source LLMs for production
 • Paul Iusztin
From noisy docs to fine-tuning datasets
Generate instruct datasets for fine-tuning LLMs using distillation techniques
 • Paul Iusztin
Data pipelines for AI assistants
The backbone of successful AI systems
 • Paul Iusztin
Build your Second Brain AI assistant
Using agents, RAG, LLMOps and LLM systems
 • Paul Iusztin
© 2026 Paul Iusztin · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture