For security practitioners who use ChatGPT, Claude, Gemini, Copilot or in-product security assistants day to day and need clear rules for what to paste, what to trust and what to record.
The curriculum is being prepared and reviewed. Enrollment is not open yet.
About this course
Security people handle the most sensitive data in an organization: credentials in logs, customer records in incident evidence, unreleased vulnerabilities, and malware. Pasting any of that into the wrong AI tool can create a breach of its own, and acting on a confident but wrong answer can take down production. This course teaches the everyday discipline of using AI assistants in security work without creating those problems.
You will learn how consumer, business and enterprise tiers differ in data retention and training use, and how to read a provider's data terms; how to classify security data and redact or tokenize it before use; and how to verify AI output such as commands, queries, regex, CVE details and indicators before you rely on it. Because security work involves reading attacker-controlled content, the course covers why phishing emails, web pages and malware strings can carry instructions aimed at your assistant, and how to work with them safely. It closes with record-keeping for investigations and a ready-to-adapt team policy. Provider terms are reviewed as of October 2026; it ends with an automated exam and a Wirewalk Institute certificate of completion and assessment.
What you will be able to do
Classify security data (logs, evidence, credentials, vulnerabilities, samples) by what may be shared with which class of AI service
Compare consumer, business and enterprise AI tiers on retention, training use and administrative controls using the provider's own terms
Redact, tokenize or summarize security data before using it with an AI assistant while keeping it useful
Verify AI-generated commands, queries, regular expressions and threat facts before acting on them
Handle attacker-controlled content safely when asking an assistant to analyze it, recognizing prompt injection attempts
Keep an auditable record of AI assistance in investigations and reports
Draft a one-page AI acceptable-use policy for a security team
Syllabus
5 modules · 13 lessons · about 6 hours
1
Module 1: Know Your Tools and Their Data Terms
What happens to what you type, and how assistant tiers and deployment models differ.3 lessons
Consumer, Business and Enterprise Tiers: Retention and Training Use
In-Product Security Assistants Versus General Chat Assistants
Reading a Provider's Data Processing Terms in 15 Minutes
2
Module 2: What You May Share
Classify security data and prepare it so it is safe and still useful.3 lessons
Classifying Security Data: Logs, Evidence, Secrets and Vulnerabilities
Redaction and Tokenization Techniques for Logs and Tickets
Malware Samples, Exploits and Customer Data: Hard Lines
3
Module 3: Trust but Verify
Check every AI output before it touches a system, a report or a block list.3 lessons
Verifying Commands, Queries and Regular Expressions Before Running Them
Checking CVEs, Indicators and Threat Claims Against Primary Sources
Recognizing Confident Errors and Outdated Knowledge
4
Module 4: Working with Attacker-Controlled Content
Analyze phishing, web pages and suspicious files without letting the content steer your assistant.2 lessons
Prompt Injection Hidden in Emails, Pages and Strings
Safe Patterns for Analyzing Suspicious Content with AI
5
Module 5: Records, Policy and Team Practice
Document AI use defensibly and turn the course into team rules.2 lessons
Recording AI Assistance in Investigations and Reports
Writing a One-Page AI Acceptable-Use Policy for Your Security Team
Exam and certificate
The exam unlocks once you have completed every lesson. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 30 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.
Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.
The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by OpenAI, Anthropic, Google, or Microsoft. Product and company names are trademarks of their respective owners.
Learn what generative AI has changed about scams, from cloned voices and deepfake video calls to fluent phishing, and build a short set of verification habits that work no matter how convincing the fake is. Free, about one hour, with a 10-question check at the end.
A plain-language introduction to AI in cyber defense: the difference between classic machine learning detection and LLM assistants, where each shows up across the security stack, how attackers are using AI, and how to judge a security AI claim. No coding or security background beyond IT basics is required.
A practitioner course on using AI in the security operations center: LLM-assisted triage and enrichment, incident summaries and timelines, natural-language hunting with KQL, SPL and ES|QL, AI-assisted Sigma detection engineering, SOAR playbooks with approval gates, and honest measurement. Every technique comes with prompts, queries or playbook snippets, and the course closes with a hands-on lab on synthetic logs.