Will McMillan
William is an experienced cybersecurity professional and Microsoft-certified engineer with deep, practical knowledge of AI integration within security operations, threat detection, and automation workflows.
Courses
Intro to AI for Incident Response
This course examines how artificial intelligence supports incident response activities by assisting responders with investigation, correlation, and analysis of security events. Explore how AI can identify attack patterns, reconstruct incident timelines, and surface relevant evidence during active security incidents.
AI Guardrails: Implementing Security Controls for LLM Applications
AI Guardrails are security controls that intercept and validate inputs to and outputs from Large Language Models (LLMs), addressing unique attack vectors that traditional security controls cannot prevent. Learn to build a complete guardrails stack, test it against prompt injection attacks and PII disclosure, and monitor and tune these controls.
Developing Custom AI Tools
Custom AI tools introduce non-determinism, external dependencies, and the risk of excessive agency. Traditional IT controls are necessary but not sufficient. You will learn to set trust boundaries, constrain tool scopes, and enforce latency budgets that match business SLAs.
Getting Started in AI
In this practical course, you'll learn how to treat AI prompts and outputs like governed assets. Mitigate risks like prompt injection, protect sensitive data, and apply enterprise-grade controls to your workflow. Master the art of validating outputs and measuring cost/accuracy to scale AI safely. Secure your output. Protect your data.
Vetting AI tools
Master the AI Tool Vetting Lifecycle. Learn to define enterprise workflows, map threats (MITRE ATLAS/OWASP LLM), and evaluate vendor evidence consistently. Develop skills to measure model quality/cost and negotiate contracts for strong data protection. Finally, plan deployment, monitoring, and lifecycle controls for sustained safety and compliance.
Secure AI Research
Learn to align AI research with secure principles to ensure due care and faster approvals. You will prioritize adversarial risks using MITRE and OWASP LLM Top 10, design data protection controls for privacy and integrity, build an evaluation process, select safe integration patterns, and communicate risk to review boards with audit-ready artifacts.
AI for GRC analysts
Learn how to link GRC frameworks to SOC and engineering realities. You will build a practical playbook for translating AI risk frameworks into controls, evidence, monitoring expectations, and audit-ready reporting, and a short implementation plan you can execute with product, platform, security, and compliance partners.
AI for red teams
The course links offense to operations. AI risk is not just another web app risk. Models can generalize and hallucinate, retrieval chains blend internal and external data, and tool use lets models perform actions, multiplying impact. Red teams must model this system boundary, then pressure test across prompts, retrieval, tools, and supply chains.
William is an experienced cybersecurity professional and Microsoft-certified engineer with deep, practical knowledge of AI integration within security operations, threat detection, and automation workflows.
He's designed and delivered technical training for enterprise environments covering topics such as AI-driven incident response, secure AI adoption, and data model governance.He has applied AI extensively within cybersecurity operations, particularly in threat detection, SOC automation, and incident response enrichment. His experience includes integrating GPT-based models and Azure OpenAI into Microsoft Sentinel workflows to summarize incident data, flag anomalies, and assist analysts with triage. He's also developed AI-assisted scripts for phishing analysis, log correlation, and vulnerability prioritization using Python and REST APIs. He has also contributed to AI risk assessments and data handling controls aligned with secure AI principles (prompt safety, model governance, and auditability).