Noctua — Reading List and Resources

This reading list is organized into Core (required) and Expanded (recommended deep-dives) for each topic area. Core readings are assigned weekly; Expanded readings support capstone research and personal exploration.


Critical Thinking and CCT

Core

Expanded


AI Ethics and Responsible AI

Core

Expanded


Agentic Engineering

Core

Expanded


Agent Knowledge Bases & Memory

How agents store, retrieve, and use knowledge across sessions. Covers both institutional context (what you write down for the agent) and dynamic memory (what the agent accumulates through work). Directly supports the three-tier context architecture in Unit 5 and the harness engineering patterns in Unit 4.

Core

Expanded


Agentic AI Security — Research Papers

Core

Expanded


Red Teaming and Adversarial ML

Core

Expanded


AI Supply Chain Security

Core

Expanded


Governance, Policy, and Compliance Frameworks

Core

Expanded


Compliance & Data Governance

Core

Expanded


Non-Human Identity (NHI) Security

Core

Expanded


AI in Cybersecurity Operations

Core

Expanded


Cybersecurity Foundations

Core

Expanded


Rapid Prototyping and Innovation

Core

Expanded


Agent Protocols — Technical Documentation


Framework and Platform Documentation


Mechanistic Interpretability (Emerging)


Academic Journals and Conferences


Supplementary Video — AI Engineer YouTube Channel

Conference talks from the AI Engineer YouTube channel (260k+ subscribers), curated by topic relevance to course units. All talks are free. The AI Engineer World's Fair and Summit events feature speakers from Anthropic, OpenAI, Google DeepMind, Meta, and leading AI startups.

Unit 1–2: Foundations & Agent Tool Architecture

Unit 4: Rapid Prototyping & Agentic Engineering

Unit 5: Multi-Agent Orchestration

Unit 6: AI Attacker vs. AI Defender

Unit 7: Production Security Engineering

General / Cross-Cutting


Online Courses (Supplementary)


Weekly Reading Schedule

Semester 1: Foundations

Week Topic Core Reading
1 Threat Landscape Anthropic — "Disrupting AI-orchestrated cyber espionage" (2025); Course Assessment
2 Critical Thinking Kahneman — "Thinking, Fast and Slow" (Ch. 1-7); Sagan — Baloney Detection Kit
3 AI Fundamentals Anthropic — Claude Model Card; "Attention Is All You Need" summary
4 Context Engineering Anthropic — "Effective Context Engineering for AI Agents"
5 Agent Protocols MCP Specification; "A Survey of AI Agent Protocols" (arXiv:2504.16736)
6 Tool Design & GTG-1002 Anthropic — "Disrupting the First Reported AI-Orchestrated Cyber Espionage Campaign" Full Report (Nov 2025); West — "Agentic Engineering Book" (tool design)
7 Cyber Threat Framework MITRE ATT&CK overview; Buchanan — "The Hacker and the State" (selected)
8 Risk Management NIST AI RMF 1.0 overview
9 Responsible AI AIUC-1 Standard (full review of all six domains); NIST AI RMF (full); AIUC-1/NIST crosswalk
10 Agentic Security OWASP Top 10 for Agentic Apps; "Agentic AI Security" (arXiv:2510.23883)
11 Bias and Fairness O'Neil — "Weapons of Math Destruction" (selected); IBM AI Fairness 360 docs
12 Compliance EU AI Act summary; NIST Cyber AI Profile (December 2025); AIUC-1 standard (https://www.aiuc-1.com/)
13 Implementation Claude Agent SDK (full); West — orchestration patterns chapter
14 Rapid Prototyping & Shipping Discipline Knapp et al. — "Sprint" (prototyping chapters); gstack by Garry Tan — /ship pipeline, pre-landing AI checklist, Boil the Lake principle (https://github.com/garrytan/gstack)
15 Integration OWASP Agentic Top 10 deep review; synthesis
16 Review No new reading

Semester 2: Advanced

Week Topic Core Reading
1 Multi-Agent Architecture "Survey of Agentic AI and Cybersecurity" (arXiv:2601.05293); Agent SDK (subagents)
2 Orchestration Frameworks Anthropic — Claude Managed Agents documentation (full); OpenAI Agents SDK README and quickstart
3 Workflow & State Anthropic — Claude Managed Agents: subagent patterns and orchestration; NIST Incident Response Lifecycle
4 Evaluation & Agent Memory West — evaluation chapter; Promptfoo Documentation; "Survey on Memory Mechanism of LLM-based Agents" (arXiv:2404.13501); LinkedIn knowledge base case study (The New Stack)
5 Threat Landscape MITRE ATLAS (full); "Prompt Injection on Agentic Coding Assistants" (arXiv:2601.17548)
6 Red Teaming "Red Teaming the Mind of the Machine" (arXiv:2505.04806); OWASP Agentic Top 10 (deep)
7 Defense & Guardrails NeMo Guardrails docs; LlamaFirewall docs; Guardrails AI docs
8 Wargame Prep Buchanan — "The Hacker and the State" (full); PeaRL security research docs
9 Supply Chain "State of MCP Server Security 2025"; "Poisoning Attacks on LLMs" (arXiv:2510.07192)
10 NHI Governance "2025 State of NHI Report"; Zero Trust for AI (CISA); PeaRL governance docs; AIUC-1 + AIVSS crosswalk
11 Observability OpenTelemetry docs (AI observability); NIST IR 8596 monitoring sections
12 Production Security Christian — "The Alignment Problem" (deployment chapters); CISA AI guidance
13-16 Capstone Directed research aligned with project scope

Document Information

Course: Noctua Graduate Course Academic Year: 2026 Last Updated: March 2026 Reading List Version: 3.0 — Restructured into Core/Expanded with September 2025 – March 2026 research