Instructor Showcase

A pattern-level tour of AI tools for your cybersecurity classroom — presented live on Day 5 (late afternoon). Architecture patterns and demos only; no production infrastructure is exposed. Each card describes the pattern, the tooling, and how you can adapt it.

Day 5 — Jul 24, late afternoon (if time permits after the exam and lab catch-up)These cards are reference material for the live showcase. Code, prompts, and configuration examples referenced here come from the workshop's own labs — nothing proprietary.

Lab Generators

Use an AI coding agent to draft hands-on lab scenarios from a structured prompt template that encodes your course objectives, constraints (CPU-only, no secrets, isolated network), and expected outputs. The agent drafts; you review and refine.

Objective mappingPrompt templateAI draftInstructor reviewPublished bundle
Ollama (local)Python mcp SDKDocker Compose

All four workshop labs (Days 1–4) were scaffolded using this exact pattern — the lab code, README, and expected outputs are fair game to adapt for your own curriculum.

AI Tutoring

A local LLM (Ollama) configured as a Socratic tutor: grounded on your course materials via RAG, rate-limited so it doesn't just give answers, no internet access. Runs on the same hardware as the labs — no API keys, no student data leaves the room.

Course materialVector DB (RAG)Ollama LLMSocratic promptStudent chat
OllamaChromaDBLiteLLM gateway

The Day 1 RAG lab is the direct foundation. Swap in your own course notes and adjust the system prompt to get a domain-specific tutor in <30 min.

MCP Exercise Environments

Model Context Protocol servers that let AI agents interact with simulated SOC tooling — log sources, CVE databases, rule editors — without live network access or real credentials. Students interact with a safe, bounded environment that behaves like the real thing.

MCP serverBundled dataAI agentTool callsValidated output
Python mcp SDKFastMCPBundled CVE data

The Day 4 lab ships a complete MCP server template. Key design constraint: no live NVD queries — all data is bundled to prevent hallucinated CVSS scores.

Coding-Agent Workflows

AI agents that generate security artifacts (detection rules, IaC snippets, lab scripts), then statically validate and repair them — closing the loop without a human in every iteration. Safe for classrooms: no secrets, isolated Docker network, bundled validators.

SpecificationAI generatesStatic validateRepair loopReviewed artifact
sigma-cliSnort 3 (-T)Ollama 3B model

Day 4's Sigma/Snort generation lab uses exactly this pattern. The static validators (sigma-cli, Snort self-test) are the safety net that makes the generate-loop feasible without a security expert reviewing every output.

Hosted API vs. Local LLM — Trade-off Talk

The Day 5 PM session includes a structured discussion of when to use hosted APIs vs. local models for classroom deployments. Here's the comparison framework:

DimensionHosted API (OpenAI / Anthropic / Azure)Local LLM (Ollama, CPU)
CostPer-token; scales with class size and usageHardware cost only; zero marginal cost per query
Privacy / data residencyData leaves campus; check ToS + FERPAAll data stays on the box; FERPA-safe by design
LatencyLow (GPU datacenter), network-dependentHigher on CPU (8–16 GB RAM); use cloud VM for parity
Capability ceilingFrontier models (GPT-4o, Claude 3.7, etc.)Limited to models that fit in RAM (1.5–7B typical)
Offline / demo resilienceRequires network; single point of failureFully offline; no network dependency during demo
Compliance constraintsCheck institution acceptable-use policy; EU AI Act GPAI obligationsSelf-hosted; consult open-model license (Llama 3.2, Qwen 2.5)
Setup complexityAPI key; managed infraOllama install + model pull; Docker recommended

Workshop recommendation: local Ollama for all labs (guaranteed parity, no per-student API cost, offline-safe). Use hosted APIs for instructor demos of frontier capabilities (screenshare only — students stay on local path).

Adoption Roundtable

Discussion prompts for the Day 5 closing roundtable:

  1. Which of these four patterns maps most directly to a course you teach or want to teach?
  2. What's your institution's biggest blocker — budget, IT policy, hardware, or faculty capacity?
  3. How would you handle a student who uses the AI tutor to get direct answers instead of thinking through the problem?
  4. What safeguards would you put in place before deploying an AI coding-agent workflow in a student lab?
  5. Would you use local LLM, hosted API, or institutional AI (e.g., Azure OpenAI via campus contract) for your first deployment?