For CTI analysts and SOC teams who want to use LLMs to collect, extract, map and report threat intelligence faster while keeping analytic rigor and source discipline.
The curriculum is being prepared and reviewed. Enrollment is not open yet.
About this course
Threat intelligence teams face more reporting than they can read, in more languages than they speak, and consumers who want answers in hours. LLMs are well suited to reading, extracting and summarizing, and poorly suited to judging source reliability or inventing confidence. This course teaches where that line sits.
You will start from the intelligence cycle and priority intelligence requirements, then use LLMs to triage and cluster reporting, extract indicators and TTPs from unstructured reports into STIX 2.1 objects, and map behaviors to MITRE ATT&CK techniques with measurable accuracy (including the detection strategies and analytics introduced in ATT&CK v18). You will work with multilingual and underground sources, use structured analytic techniques such as Analysis of Competing Hypotheses with an AI assistant as a challenger rather than an oracle, and write finished intelligence using the Admiralty Code and standard estimative language. The final module builds a small enrichment pipeline around open-source MISP or OpenCTI and surveys commercial AI-enabled TI platforms such as Google Threat Intelligence, Microsoft Defender Threat Intelligence and CrowdStrike Falcon intelligence, reviewed as of October 2026.
What you will be able to do
Write priority intelligence requirements and design where an LLM fits in each phase of the intelligence cycle
Extract indicators and TTPs from unstructured reports into valid STIX 2.1 objects and measure extraction accuracy
Map reported adversary behavior to MITRE ATT&CK techniques with an LLM and audit the mappings
Use AI to translate and summarize multilingual and underground sources while preserving provenance
Apply structured analytic techniques with an AI assistant as a challenger, and assign source reliability and confidence correctly
Produce finished intelligence products for technical and executive audiences with clear estimative language
Build a small AI-assisted enrichment pipeline using MISP or OpenCTI
Syllabus
6 modules · 18 lessons · about 12 hours
1
Module 1: The Intelligence Cycle Meets LLMs
Requirements first, then where AI helps and harms in each phase of the cycle.3 lessons
Priority Intelligence Requirements and Consumers
Mapping LLM Strengths and Weaknesses onto the Intelligence Cycle
Source Volume Triage: Clustering and Deduplicating Reporting
2
Module 2: Extraction and Structuring
Turn prose reports into structured, machine-usable intelligence.3 lessons
Extracting IOCs and Defanged Indicators with Structured Output
Building STIX 2.1 Objects and Relationships from Reports
Measuring Extraction Precision and Recall on a Labeled Set
3
Module 3: TTPs and ATT&CK Mapping
Map behavior, not just indicators, and connect it to detection.3 lessons
LLM-Assisted ATT&CK Technique Mapping and Its Common Errors
From Mapped Techniques to Detection Strategies and Analytics in ATT&CK v18
Actor Profiles and Campaign Tracking Without False Attribution
4
Module 4: Hard Sources
Multilingual, underground and noisy sources handled with provenance intact.3 lessons
Translation and Summarization of Foreign-Language Reporting
Underground Forum and Leak Site Monitoring: Legal and Safety Boundaries
Preserving Provenance and Chain of Sourcing
5
Module 5: Analysis and Finished Intelligence
Keep human judgment in charge of confidence and conclusions.3 lessons
Structured Analytic Techniques with an AI Challenger
Admiralty Code, Estimative Language and Confidence
Writing Technical and Executive Intelligence Products
6
Module 6: Platforms and Pipelines
Put it together in open-source tooling and evaluate commercial options.3 lessons
Building an Enrichment Pipeline with MISP or OpenCTI and an LLM
Sharing Intelligence Safely: TLP and Data Handling
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 MITRE, OASIS, Google, Microsoft, CrowdStrike, Recorded Future, MISP, or OpenCTI. 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.