AI Agents6 min read
Graph Engineering Explained: What Actually Changed
Why the loops-versus-graphs debate misses the point, what actually changed in agent orchestration, and which parts of your system should stay deterministic.
Blog
AI engineering essays, explainers, and practical notes.
My blog on practical AI engineering, LLMs, agents, research, and what is actually useful to build.
AI Agents4 min read
How to Build a Memory Your AI Agents Can Actually Reuse
The useful part is not giving agents more context. It is making your research, notes, and sources available again in the next session.
AI News and Analysis9 min read
What Did Microsoft's MAI Model Actually Train On?
Why Microsoft removed AI-generated content from MAI-Thinking-1 pretraining, and what that choice reveals about the model.
Large Language Models8 min read
90% Cheaper GPT APIs
Why a 90% API discount can hide model swaps and expose your credentials, code, and repository.
AI Agents11 min read
Loop Engineering Explained
A practical way to stop babysitting coding agents: design their context, tools, checks, budgets, and stop conditions.
Large Language Models15 min read
How Image Generation Actually Works
Diffusion sculpts noise. Autoregressive models predict visual tokens. Here is how both turn prompts into images.
AI Agents17 min read
Coding Changed Forever
What changed in AI coding, why generated code can feel faster, and where engineering judgment still matters.
Large Language Models18 min read
How Google Went From AI Joke to OpenAI’s Biggest Problem
How Gemini, DeepMind, AI Studio, and Google's distribution turned a mocked chatbot launch into an OpenAI threat.
Computer Vision11 min read
Your AI Can Improve Itself — Or Fool You
How recursive AI improvement loops work, why weak evals reward the wrong behavior, and what builders can use now.
Large Language Models16 min read
AI Distillation Explained: The Truth Behind the Biggest AI Controversy Right Now
How model distillation works, why AI labs accuse rivals of copying, and where the ownership argument gets messy.
AI Agents8 min read
How to Control Bias in AI Agents
The guardrails, audits, and human review loops that actually work
AI Agents9 min read
Harness Engineering: The Missing Layer Behind AI Agents
Prompting tells an agent what to do. The harness controls its tools, permissions, tests, traces, and failures.
Large Language Models11 min read
Why RAG Is Not Training Your AI
RAG changes the context, not the model. Here is when retrieval helps, when it does not, and when to fine-tune.
AI Engineering10 min read
What I Look For When Hiring AI Engineers
After interviewing more than 100 candidates, here’s what actually stands out in AI engineering interviews and take-home assignments
AI Agents6 min read
Stop Building Agent Demos
What separates a polished AI agent demo from a system your team can evaluate, debug, deploy, and trust.
Large Language Models9 min read
I Published 42 Shorts on AI Terms in 42 days
A free 42-video course for understanding model behavior, not collecting more prompt tricks.
AI Agents14 min read
The 12 Questions That Decide Your AI Architecture
A cheatsheet to avoid costly rework in agent systems.
AI Agents9 min read
Multi-agent is becoming the new overengineering
You’re not building agents. You’re building workflows (and that’s fine)
AI Agents23 min read
How to Clean Up AI-Generated Drafts Without Sounding Like ChatGPT
How to Spot and Remove “AI Slop” from Your Writing
Large Language Models13 min read
Why AI Feels Intelligent (and Why That’s Misleading)
A clear explanation of what LLMs actually learn, why humans are different, and why AGI is not around the corner
AI Engineering2 min read
Earn While Helping Others Learn AI
1 referral = our bestselling book. 3 referrals = a course. 10 = full access + affiliate tier
AI Agents10 min read
Deep Research Agents: The Next Big Leap Beyond ChatGPT
OpenAI’s Deep Research Explained
Large Language Models5 min read
What actually changed with GPT-5
Reasoning, tools, costs and when mini beats it
AI Agents10 min read
2025: The Year of AI Agents
Million-Token Context? Cheap Tools? Perfect Time for Agents