Stunspot’s Guide to AI Systems

The AI Engineering Systems Canon
A comprehensive field manual for practical AI systems design.

Stunspot’s Guide to AI Systems is a Markdown-native knowledge repository built primarily to support AI-assisted design, engineering, analysis, evaluation, and decision-making across modern AI systems.

Its main audience is the model.

When loaded into an AI workspace, RAG pipeline, long-context session, agent memory layer, project knowledge base, or retrieval corpus, the Guide functions as a dense architectural substrate: it gives the assisting model structured doctrine, field vocabulary, decision frameworks, failure maps, design patterns, evaluation logic, and operational heuristics for reasoning about AI systems with greater precision.

Human readers can use it as a field manual, but its deeper purpose is practical augmentation: to make AI systems better at helping engineers, builders, prompt designers, product leads, and technical decision-makers reason through the design and operation of AI systems.

The Canon organizes AI engineering as a layered discipline spanning model steering, context architecture, corpus engineering, retrieval, model lifecycle, runtime mechanics, agents, tools, multimodal interfaces, security, resilience, evals, telemetry, governance, product architecture, and system doctrine.

At its core is a simple engineering premise:

AI systems are probabilistic cognitive engines operating inside deterministic operational environments. Good AI engineering means designing the interfaces, constraints, context, tools, feedback loops, and human controls that let that probabilistic core behave usefully, safely, and economically under real conditions.

Use it as reference material.
Use it as RAG substrate.
Use it as project knowledge.
Use it as doctrine for AI agents tasked with designing, critiquing, or improving AI systems.

Start Here

Canon Map

Full Canon

Part I — Foundations of AI Systems

Volume 1 — The Informational/Epistemic Layer
How models think, how meaning is steered, and how state becomes usable.

Volume 2 — Knowledge, Data, and Corpus Engineering
Where trustworthy external knowledge comes from, how it is shaped, and how it enters the system.

Volume 3 — Model Lifecycle and Adaptation
How models are selected, modified, evaluated, compressed, deployed, and retired.

Volume 4 — Runtime Architecture and Inference Mechanics
How AI systems actually execute under physical, computational, and operational constraints.

Part II — Agentic and Multimodal Systems

Volume 5 — Agentic Systems and Tool-Using Architectures
How static generators become actors, and how to keep them from becoming raccoons with API keys.

Volume 6 — Multimodal and Interface-Controlling Systems
How AI engineering changes when the system reads, sees, hears, speaks, and acts through interfaces.

Part III — Failure, Security, and Resilience

Volume 7 — Failure, Security, and Hostile Environments
How AI systems break, leak, get attacked, or quietly become cursed.

Volume 8 — Resilience, Degraded Modes, and Human Trust
How systems fail gracefully enough that users do not feel the machinery grinding underneath them.

Part IV — Evaluation, Operations, and Governance

Volume 9 — Observability, Evaluation, and Verification
How to know whether the system is actually doing what it claims to do.

Volume 10 — Operations, Governance, and Lifecycle Management
How AI systems are maintained as living infrastructure rather than one-time builds.

Part V — Product Doctrine and Engineering Method

Volume 11 — Product, Business, and Organizational Architecture
How to ensure the system matters, survives adoption, and creates value instead of expensive theater.

Volume 12 — Engineering Method and System Doctrine
The cross-cutting principles that govern the entire canon.

Knowledge Packs

For AI Projects, RAG systems, NotebookLM-style tools, and long-context workspaces, use the bundled knowledge packs.

Recommended default: By Part.

Use as AI Knowledge Substrate

The Canon is designed to be useful when placed inside AI systems as structured knowledge.

Possible uses include:

loading selected reports into long-context sessions
attaching volumes as project knowledge
loading the whole corpus into a NotebookLM or similarly robust RAG system
indexing reports into a RAG pipeline
personal education and reference
grounding agentic design review workflows
supporting architecture critique, failure analysis, and implementation planning
giving AI systems stable vocabulary for AI engineering concepts
improving consistency across design, evaluation, governance, and operations tasks

For best results, load only the portions relevant to the current task, then instruct the model to treat the Canon as governing reference material for analysis and design.

Example instruction:

Analyze, design, critique, or improve the requested AI system using Stunspot’s Guide to AI as governing reference material, not decorative background reading. Begin by retrieving and applying the Guide’s vocabulary, doctrine, design patterns, failure modes, interface logic, evaluation standards, and operational assumptions as the frame through which the system is understood. Treat the Canon as a working engineering discipline: use it to sharpen definitions, expose hidden constraints, identify brittle abstractions, detect hallucination-prone or evaluation-weak components, and convert vague AI ambition into deployable system logic. When making recommendations, ground them in the Guide’s concepts and name the relevant pattern, risk, or principle where useful; when the user’s idea conflicts with the Canon, surface the mismatch plainly and propose the smallest viable correction. Produce recommendations that are precise, build-aware, testable, and operationally realistic: architecture before ornament, interfaces before vibes, evals before confidence, failure modes before launch fantasy. Do not merely summarize the Canon. Use it to improve the quality, precision, and realism of the work.

Deliver the result as a practical engineering artifact suited to the task: diagnosis, architecture, redesign, implementation plan, evaluation rubric, risk register, prompt/system spec, or decision memo as appropriate. Include clear assumptions, system boundaries, user/job-to-be-done, data/context flows, model/tool responsibilities, human-in-the-loop points, known failure modes, eval strategy, deployment risks, and next actions. Keep the language crisp, canonical, and decision-grade.

Repository Structure

.
├── README.md
├── LICENSE.md
├── CITATION.cff
├── knowledge-packs/
│   ├── by-volume/
│   ├── by-part/
│   └── omnibus/
└── docs/
    ├── index.md
    ├── canon-map.md
    ├── knowledge-packs.md
    ├── how-to-use-this-canon.md
    ├── _config.yml
    ├── _layouts/
    │   └── default.html
    ├── assets/
    │   ├── brand/
    │   └── css/
    │       └── style.css
    ├── volume-01/
    ├── volume-02/
    ├── volume-03/
    ├── volume-04/
    ├── volume-05/
    ├── volume-06/
    ├── volume-07/
    ├── volume-08/
    ├── volume-09/
    ├── volume-10/
    ├── volume-11/
    └── volume-12/

The /docs/ directory contains the canonical source reports and GitHub Pages site.

The /knowledge-packs/ directory contains bundled upload formats for AI Projects, RAG systems, NotebookLM-style tools, and long-context workspaces.

Attribution

Created by Sam “stunspot” Walker / Collaborative Dynamics.

Citation

If you use or reference this Canon, please cite it.

See CITATION.cff for citation metadata.

Suggested plain-text citation:

Walker, Sam “stunspot.” The AI Engineering Systems Canon: A Doctrinal Knowledge Base for High-Dimensional AI System Architecture. Collaborative Dynamics.

License

See LICENSE.md.

Unless otherwise stated, the written materials in this repository are licensed under:

Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International CC BY-NC-SA 4.0

Commercial use, resale, paid redistribution, inclusion in commercial training products, or incorporation into paid knowledge-base products requires prior written permission.

Status

2026-06-16 - First pass v1.0 complete. All reports and combined files created. All reports given a first pass sanity check with substantial editorial input. I intend to do a comprehensive source double-check to catch anything Deep Research invented (there’s probably about 1-5 total across all reports, judging from experience) but that will take substantial time.

Disclaimer

This corpus was constructed with a mix of GPT and Gemini Deep Research. Its specific nature severely mitigates against Deep Research’s rare hallucination, and I have seen maybe 5 instances of such across dozens of similar knowledge bases, but errors ARE possible with AI. It is at least as reliable as a comparable 1600 page textbook written by humans and so far seems substantially more so.

That said, I am not a software engineer or coder of any kind. I am a prompt engineer and AI operations expert. My skills are not in programming or KV cache optimization, they lie in knowing how to elicit superb results from the model and how to recognize and correct it when it has an error of operation. I cannot create a new architecture on my own. I can teach the model how to do it for me.

And now it can do so for you, as well.

I won’t promise perfect but I do promise usefull.

–stunspot ⟨🤩⨯📍⟩ and 💠‍🌐Nova

Stunspot’s Guide to AI Systems

Start Here

Full Canon

Part I — Foundations of AI Systems

Part II — Agentic and Multimodal Systems

Part III — Failure, Security, and Resilience

Part IV — Evaluation, Operations, and Governance

Part V — Product Doctrine and Engineering Method

Knowledge Packs

Use as AI Knowledge Substrate

Suggested Reading Paths

For RAG and Knowledge Systems

For Agentic Systems

For Model Selection, Adaptation, and Serving

For Security, Reliability, and Governance