Plain-language explainers on practical AI architecture and agent patterns, written for IT leaders, architects, engineers, and security teams. Each article is self-contained Markdown free to read, download, and reuse with attribution.
New explainers are added over time - this repo is the canonical home for the full-resolution versions of the visuals shared on LinkedIn.
- Mixture of Experts vs. Mixture of Agents — one improves the model, the other improves the answer. Where each sits in the AI stack, why the distinction matters for architecture and delivery decisions, and five common sub-patterns of Mixture of Agents. Includes three high-res diagrams and a print-ready PDF.
- The Real Bottleneck for AI Agents Isn't the Model. It's the Context. — why context, not the model, is usually the limiting factor for agents. Prompt engineering vs. context engineering, the "context rot" problem, the Goldilocks system prompt, and what good context engineering looks like in practice.
- Read on GitHub - open any article folder and its
README.mdrenders in your browser. - Download individual files — open an image or PDF, then use the Download button (for PNGs/PDFs, the "..." / download icon on the file page) to grab the full-resolution original.
- Grab the whole repo as a ZIP — click the green Code button on the repo home page → Download ZIP.
- Clone it —
git clone https://github.com/mrobinson2/ai-explainers.git
This repository is dual-licensed:
- Articles and images (Markdown, PNG, PDF, and other diagrams) are licensed under Creative Commons Attribution 4.0 International (CC BY 4.0) — see LICENSE-CONTENT.md. You may share and adapt them for any purpose, including commercially, with attribution.
- Any code or scripts are licensed under the MIT License.
By Michael Robinson. Connect on LinkedIn: https://www.linkedin.com/in/mrobinson2
© 2026 Michael Robinson.