
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.
Blog
My blog on practical AI engineering, LLMs, agents, research, and what is actually useful to build.

The useful part is not giving agents more context. It is making your research, notes, and sources available again in the next session.

Model choice is not only about benchmark scores. It is also about what behavior the model inherited.



The real process behind Midjourney, Gemini, FLUX, and ChatGPT


Everyone Laughed at Gemini. Now It’s Everywhere.

Self-Improving AI Is No Longer Theory

US AI Labs Accused China of Stealing

The guardrails, audits, and human review loops that actually work

The clearest way to understand the difference between prompt engineering, context engineering, and harnesses

Are You Actually Changing the Model, or Just Giving It Context?

After interviewing more than 100 candidates, here’s what actually stands out in AI engineering interviews and take-home assignments

Agentic AI Engineering teaches you how to design, evaluate, and deploy autonomous systems that don’t collapse under real constraints

Because Prompting Was Never the Real Problem

A cheatsheet to avoid costly rework in agent systems.

You’re not building agents. You’re building workflows (and that’s fine)

How to Spot and Remove “AI Slop” from Your Writing

A clear explanation of what LLMs actually learn, why humans are different, and why AGI is not around the corner

1 referral = our bestselling book. 3 referrals = a course. 10 = full access + affiliate tier

OpenAI’s Deep Research Explained
Reasoning, tools, costs and when mini beats it

Million-Token Context? Cheap Tools? Perfect Time for Agents

Allow optional usage analytics to help improve the site. Privacy details