Security AI Platforms: Security Copilot, Google Security AI and Others
For security architects, SOC managers and buyers who must choose, deploy and govern a security AI platform and prove it is worth its cost.
The curriculum is being prepared and reviewed. Enrollment is not open yet.
About this course
Choosing a security AI platform is mostly a decision about where your security data already lives, how the vendor's AI reaches it, and what it costs to run. This course gives you the architecture view and the evaluation method to make that decision well, rather than a feature checklist that will be outdated next quarter.
Each platform module explains how the AI is grounded in the vendor's data (for example, Microsoft Security Copilot across Defender XDR, Sentinel and its data lake and Entra; Gemini and its triage and investigation agent in Google Security Operations; Charlotte AI across CrowdStrike Falcon and Next-Gen SIEM; Purple AI in SentinelOne Singularity; AI assistants in Splunk Enterprise Security and Elastic Security including Attack Discovery), what it can do on its own, what it can take action on, how it is licensed or metered, and where data is processed. You will also look at bring-your-own-model options using MCP servers and open-source stacks. The course closes with a proof-of-value method: success criteria, test datasets, scoring rubrics, cost modeling and governance (roles, approvals and audit logs). All product details are reviewed as of October 2026 and taught alongside durable evaluation principles.
What you will be able to do
Describe a reference architecture for security AI platforms: data plane, grounding, tools, agents and action surface
Explain how Microsoft Security Copilot, Google Security Operations with Gemini, CrowdStrike Charlotte AI and SentinelOne Purple AI each reach and act on security data
Compare AI capabilities in Splunk and Elastic and open-source or bring-your-own-model alternatives
Assess data residency, retention, model training use and tenant isolation for a security AI service
Model licensing and consumption costs for a realistic SOC workload
Run a structured proof-of-value with defined success criteria, test data and scoring
Define governance for a deployed platform: roles, approvals for automated actions, and audit logging
Syllabus
6 modules · 18 lessons · about 12 hours
1
Module 1: Architecture of a Security AI Platform
A vendor-neutral model to compare every product against.3 lessons
Data Plane, Grounding, Tools and Action Surface
Assistants, Embedded Experiences and Agents: Three Delivery Models
Native Integration Versus Bring-Your-Own-Model with MCP
2
Module 2: Microsoft Security Copilot
Copilot across Defender XDR, Sentinel, Entra, Intune and Purview, and its agents.3 lessons
Security Copilot Architecture: Standalone, Embedded and Plugins
Copilot Agents in Defender and Sentinel: Triage, Investigation and the Sentinel Data Lake
Capacity, Licensing and Administration
3
Module 3: Google Security AI
Gemini in Google Security Operations and Google Threat Intelligence.3 lessons
Gemini in Google Security Operations: Search, Summaries and Detection Authoring
The Triage and Investigation Agent and Agentic SOC Features
Google Threat Intelligence and Mandiant Context
4
Module 4: EDR-Native and SIEM-Native AI
CrowdStrike, SentinelOne, Splunk and Elastic approaches compared.4 lessons
CrowdStrike Charlotte AI Across Falcon and Next-Gen SIEM
SentinelOne Purple AI in the Singularity Platform
Splunk Enterprise Security and Elastic Security AI Features
Open-Source and Self-Hosted Alternatives
5
Module 5: Data Protection and Risk
The questions your privacy, legal and vendor-risk teams will ask.2 lessons
Data Residency, Retention and Training Use
Tenant Isolation, Permissions and Prompt Injection Exposure
6
Module 6: Proof-of-Value and Governance
Decide on evidence and run the platform safely after purchase.3 lessons
Designing a Proof-of-Value: Success Criteria and Test Datasets
Cost Modeling for Metered Security AI
Governance After Go-Live: Roles, Approvals and Audit Logs
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 45 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 Microsoft, Google, CrowdStrike, SentinelOne, Splunk, Cisco, Elastic, or Palo Alto Networks. 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.
Practical rules for using general-purpose and security-specific AI assistants in security work: classifying what can be shared, sanitizing logs and malware samples, verifying output before acting, handling untrusted content that may carry prompt injection, and keeping an auditable record. Ends with a one-page team policy you can adopt.