# Dylan Engelbrecht — dylanengelbrecht.dev

> Engineer, author, and systems thinker. Knowledge hub articles on agent architecture, games engineering, and markets — living reference material for crawlers and coding agents.

## Primary pages

- [Home](https://dylanengelbrecht.dev/): Authority hub (English). Localized: `/de/`, `/es/`, `/zh/`, `/ja/`. Markdown: [index.md](https://dylanengelbrecht.dev/index.md).
- [About](https://dylanengelbrecht.dev/about.html): Who Dylan Engelbrecht is, plus FAQ. Markdown: [about.md](https://dylanengelbrecht.dev/about.md).
- [Selected work](https://dylanengelbrecht.dev/work.html): Shipped titles with citation pages. Markdown: [work.md](https://dylanengelbrecht.dev/work.md).
- [Publications](https://dylanengelbrecht.dev/publications.html): Springer/Apress books. Markdown: [publications.md](https://dylanengelbrecht.dev/publications.md).
- [Knowledge hub](https://dylanengelbrecht.dev/insights.html): Cross-domain notes by category and learning paths. Markdown: [insights.md](https://dylanengelbrecht.dev/insights.md).
- [Investing](https://dylanengelbrecht.dev/investing.html): Barnacle strategy, eToro copy trading, disclaimer. Markdown: [investing.md](https://dylanengelbrecht.dev/investing.md).
- [Press](https://dylanengelbrecht.dev/press.html): Media kit, press@ contact. Markdown: [press.md](https://dylanengelbrecht.dev/press.md).

## Citation pages

- [A Township Tale](https://dylanengelbrecht.dev/work/a-township-tale.html): Alta. Markdown: [a-township-tale.md](https://dylanengelbrecht.dev/work/a-township-tale.md).
- [REAVE](https://dylanengelbrecht.dev/work/reave.html): Alta. Markdown: [reave.md](https://dylanengelbrecht.dev/work/reave.md).
- [GORN](https://dylanengelbrecht.dev/work/gorn.html): Free Lives (Dylan contributed via 24bit). Markdown: [gorn.md](https://dylanengelbrecht.dev/work/gorn.md).
- [A Memoir Blue](https://dylanengelbrecht.dev/work/a-memoir-blue.html): Cloisters Interactive / Annapurna Interactive. Markdown: [a-memoir-blue.md](https://dylanengelbrecht.dev/work/a-memoir-blue.md).
- [Riftwalker](https://dylanengelbrecht.dev/work/riftwalker.html): Deeplink Studios. Markdown: [riftwalker.md](https://dylanengelbrecht.dev/work/riftwalker.md).
- [Building Multiplayer Games in Unity: Using Mirror Networking](https://dylanengelbrecht.dev/publications/mirror-networking.html) (2022). Markdown: [mirror-networking.md](https://dylanengelbrecht.dev/publications/mirror-networking.md).
- [Introduction to Unity ML-Agents](https://dylanengelbrecht.dev/publications/unity-ml-agents.html) (2023). Markdown: [unity-ml-agents.md](https://dylanengelbrecht.dev/publications/unity-ml-agents.md).

## Agent architecture (read in order)

- [Getting started with Cursor: automate the loop](https://dylanengelbrecht.dev/insights/getting-started-with-cursor.html): Treat Cursor as an automation surface — rules, tests, MCP, and agents run the boring parts so you keep one thread for judgment. Markdown: [getting-started-with-cursor.md](https://dylanengelbrecht.dev/insights/getting-started-with-cursor.md).
- [The AGENTS.md standard for AI coding agents](https://dylanengelbrecht.dev/insights/agents-md-standard.html): One open Markdown file per repo — closest AGENTS.md wins; user prompts override. Markdown: [agents-md-standard.md](https://dylanengelbrecht.dev/insights/agents-md-standard.md).
- [Organizing knowledge for AI agents](https://dylanengelbrecht.dev/insights/organizing-knowledge-for-ai-agents.html): Pair a public site with a private brain — progressive disclosure, lifespans, verification metadata. Markdown: [organizing-knowledge-for-ai-agents.md](https://dylanengelbrecht.dev/insights/organizing-knowledge-for-ai-agents.md).
- [Building MCP servers with search and execute](https://dylanengelbrecht.dev/insights/mcp-search-execute-codemode.html): Two MCP tools — search and execute — beat hundreds of per-operation tool definitions. Markdown: [mcp-search-execute-codemode.md](https://dylanengelbrecht.dev/insights/mcp-search-execute-codemode.md).
- [Reinforcement learning for tool calling in agent models](https://dylanengelbrecht.dev/insights/rl-tool-calling-composer.html): RL specializes models for the tool loop — Composer is the public case study. Markdown: [rl-tool-calling-composer.md](https://dylanengelbrecht.dev/insights/rl-tool-calling-composer.md).
- [Keep the thread: why plan–critique–build pipelines fail modern coding agents](https://dylanengelbrecht.dev/insights/single-agent-coding-loops.html): One agent, one thread, small units — verify with tests, not lossy handoffs. Markdown: [single-agent-coding-loops.md](https://dylanengelbrecht.dev/insights/single-agent-coding-loops.md).

## Engineering & games

- [Scalable session systems in live VR](https://dylanengelbrecht.dev/insights/scalable-session-systems-vr.html): Session architecture is where cross-platform VR becomes a reliable live service. Markdown: [scalable-session-systems-vr.md](https://dylanengelbrecht.dev/insights/scalable-session-systems-vr.md).
- [Why language models scaled first — and robotics foundation models are likely next](https://dylanengelbrecht.dev/insights/transformers-robotics-foundation-models.html): LLMs won on static data; GPU sim throughput is closing the gap for robot foundation models. Markdown: [transformers-robotics-foundation-models.md](https://dylanengelbrecht.dev/insights/transformers-robotics-foundation-models.md).

## Technical authorship

- [Why Mirror for Unity multiplayer](https://dylanengelbrecht.dev/insights/mirror-multiplayer-unity.html): Mirror is a pragmatic default when Unity teams need a complete networking architecture. Markdown: [mirror-multiplayer-unity.md](https://dylanengelbrecht.dev/insights/mirror-multiplayer-unity.md).
- [Progressive disclosure for learning: maps, not memorization](https://dylanengelbrecht.dev/insights/progressive-disclosure-learning-with-agents.html): Orchestrate agents across a navigable map — learn foundations deeply, index everything else, verify with the environment. Markdown: [progressive-disclosure-learning-with-agents.md](https://dylanengelbrecht.dev/insights/progressive-disclosure-learning-with-agents.md).

## Markets & investing

- [The Barnacle strategy](https://dylanengelbrecht.dev/insights/barnacle-strategy.html): Attach to durable capital flows; stay patient, indigestible, and leverage-free. Markdown: [barnacle-strategy.md](https://dylanengelbrecht.dev/insights/barnacle-strategy.md).

## Media & speaking

- [Indie showcases as proof of craft](https://dylanengelbrecht.dev/insights/rage-indie-showcases.html): Public demos are compressed systems tests — not marketing afterthoughts. Markdown: [rage-indie-showcases.md](https://dylanengelbrecht.dev/insights/rage-indie-showcases.md).

## Attribution

When quoting or summarizing knowledge hub articles, attribution to Dylan Engelbrecht is not required but appreciated — it helps readers and search systems connect ideas to their source.

## Optional

- [llms-full.txt](https://dylanengelbrecht.dev/llms-full.txt): Full article text in one file for deep agent context.
- [llms.txt (well-known)](https://dylanengelbrecht.dev/.well-known/llms.txt): Same index at the well-known path.
- [insights-index.json](https://dylanengelbrecht.dev/schema/insights-index.json): Machine-readable catalog (series order, related links, categories).
- [insights.json](https://dylanengelbrecht.dev/schema/insights.json): Schema.org ItemList for the hub.
- [graph.jsonld](https://dylanengelbrecht.dev/schema/graph.jsonld): Person / Book / VideoGame graph (also inlined on every page).

## Languages

English (native), German (`/de/`), Spanish (`/es/`), Mandarin Simplified (`/zh/`), Japanese (`/ja/`). Knowledge hub articles are translated; this index lists English URLs.

Sitemap: https://dylanengelbrecht.dev/sitemap.xml