Complete learning catalog

One curriculum.Every concept connected.

The interactive sessions create the story. These technical-learning pages slow down each durable concept with a mental model, visual explanation, decision aid, cybersecurity example, FAQ, and primary sources.

6 learning paths 20 presentation concept guides Open presentations

PATH 01

Agentic AI foundations

Build the mental models before adding autonomy.

8 topics

01Governed Agentic AI for CybersecurityA four-session visual learning path from LLMs and reusable skills to agentic security risks, governed orchestration, and a hands-on cybersecurity agent workshop.Interactive series 02LLMs, prompts, and context: the useful mental modelUnderstand what an LLM actually does, how context shapes a response, and why confident language is not the same as verified knowledge.Session 1 · 8 min 03Instructions, user requests, and data need different trust levelsLearn how instruction hierarchy works and why untrusted content must never acquire authority simply because an LLM can read it.Session 1 · 9 min 04From chat to projects: preserving useful working contextChoose between an ad-hoc conversation, a persistent project, and a reusable governed capability without adding autonomy too early.Session 1 · 7 min 05Cybersecurity skill anatomy: package the method, not only the promptStructure repeatable cybersecurity expertise with an operating contract, focused references, schemas, deterministic scripts, and reusable assets.Session 1 · 10 min 06Function tools, MCP, and RAG solve different problemsDistinguish bounded actions, standardized capability connections, and evidence retrieval so the architecture matches the task.Session 1 · 10 min 07The agentic loop: reason, act, observe, and stop safelyUnderstand the runtime loop around a model and the state, limits, validation, escalation, and termination rules that make it governable.Session 1 · 11 min 08Single-agent and multi-agent orchestration: choose who owns the answerSelect manager, handoff, or code-led orchestration only when specialization and typed handoffs justify the coordination cost.Session 1 · 12 min

PATH 02

Secure agentic systems

Treat every new capability as a new trust boundary.

6 topics

01Prompt injection: when untrusted data tries to become an instructionUnderstand direct and indirect prompt injection, why prompt hardening is incomplete, and where system controls can still stop harm.Session 2 · 12 min 02Excessive agency: reduce function, permission, and autonomyControl agentic risk by independently constraining what functions exist, which permissions they receive, and when autonomous execution is allowed.Session 2 · 11 min 03Secure MCP, tools, retrieval, and agent memoryThreat-model capability connections, retrieved evidence, tool outputs, and durable memory as separate trust and data-governance boundaries.Session 2 · 13 min 04Guardrails, human approval, and deterministic control planesPlace input, output, tool, policy, and human controls at the point where they can still prevent harm instead of relying on one filter.Session 2 · 12 min 05The secure agent technology stack: choose each layer by responsibilityMap UI, API, orchestration, models, tools, state, observability, evaluations, and guardrails to the problem each layer owns.Session 2 · 14 min 06Langfuse for cybersecurity: an SOC lensHow Langfuse traces, sessions, users, scores, evaluations and prompt versions help secure agentic systems—and why a SOC still needs a SIEM for correlation, incidents and response.Deep dive

PATH 03

Cybersecurity Orchestrator

Turn specialist expertise into a governed delivery system.

5 topics

01Cybersecurity Orchestrator: the control plane is the productUnderstand how one governed control spine coordinates specialist cybersecurity skills, deterministic gates, artifacts, and human decisions.Session 3 · 12 min 02Specialist capability flows for documents, Sentinel, CSPM, and architecture reviewSee how intake routes to document, architecture, compliance, detection, and cloud-posture specialists without losing ownership or evidence.Session 3 · 13 min 03ArchStudio through MCP: generate quickly, assure deliberatelySeparate fast diagram generation from premium architecture assurance while preserving editable artifacts, findings, and lineage.Session 3 · 10 min 04Artifacts, journals, and lineage: make the run explainableUse typed artifacts for handoffs, a journal for authoritative actions and decisions, and observability traces for execution diagnosis.Session 3 · 11 min 05Current-state and future-state agentic security architectureCommunicate what is implemented now, what evidence supports it, and which controls are planned without presenting a roadmap as production reality.Session 3 · 9 min

PATH 04

Build and secure an agent

Move from bounded task to defensible release evidence.

3 topics

01Build and secure your first cybersecurity agentA practical build sequence from bounded task and non-goals through skill, structured output, narrow tools, controls, attack tests, and ship decision.Session 4 · 15 min 02Threat-model the agent workflow before choosing toolsMap assets, actors, trust boundaries, data flows, abuse paths, side effects, and recovery before granting an agent capabilities.Session 4 · 13 min 03Agent evaluations and release readiness: prove repeatabilityCombine deterministic tests, human review, model-based evaluation, adversarial cases, operational thresholds, and rollback evidence into a ship decision.Session 4 · 14 min

PATH 05

Detection engineering

Turn detection logic into a testable, governed delivery pipeline.

2 topics

01Detection-as-Code: the pipeline & governanceHow analytic rules move from an engineer's idea to a production Sentinel workspace — repo strategy, deploy engines (ARM vs Terraform), CI vs CD, IaC vs API, and the governance case.Deep dive 02Validating Sentinel detections in CI/CDThe three tiers of KQL validation — static lint, syntax/schema check, and functional 'does it fire' testing — mapped to SAST, compile, and DAST, and placed in the pipeline as a shift-left gate.Hands-on guide

PATH 06

Engineering foundations

Build the collaboration habits that make automation safe to change.

2 topics

01Git collaboration: branches, forks & conflictsHow multiple people work on one repo without colliding — the contribution flow, shared-repo vs fork model, why one branch per task, and exactly what happens when two people push to the same branch.Hands-on guide 02Git worktrees: many branches at onceThe working tree explained, then git worktree — one repository with several branches checked out in parallel folders. When you need it (hotfix mid-feature, PR review, parallel builds) and how it works.Hands-on guide