Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Video course · 15 chapters · 713 min · certificate

Build an Agentic AI SOC Analyst with Python for Threat Hunting

Build an agentic AI SOC analyst in Python: Python fundamentals, the OpenAI API with JSON output and tools, querying Log Analytics with KQL, tokens and cost, rate limits, an agent that maps tools to KQL, guardrails, threat-hunt prompting and automated VM isolation.

Become a memberAlready a member? Sign in

What you'll learn

  • Write Python for security automation
  • Call the OpenAI API with JSON output and tools
  • Query Log Analytics with KQL from Python
  • Manage tokens, cost and rate limits
  • Build a baseline threat-hunting agent
  • Add guardrails and agentic remediation

Chapters

15 chapters · 712:54
  1. 36:24 01Intro Members Agentic AI SOC introduction How AI is changing cybersecurity, an AI SOC agent demo and course objectives.
  2. 46:41 02Python Members Python basics Environment setup, debugging, variables, types, I/O, comments and if statements.
  3. 60:52 03Python Members Lists, JSON, dicts, loops and functions Collections, JSON, strings, loops and functions.
  4. 27:16 04Python Members Modules Built-in and local modules.
  5. 45:44 05API Members Error handling and the OpenAI API Handling errors, installing the OpenAI library and getting an API key.
  6. 65:46 06API Members ChatGPT with Python and JSON output Calling ChatGPT from Python and forcing JSON output.
  7. 34:05 07Tools Members The tools parameter Using the tools parameter so the model can choose functions.
  8. 45:39 08KQL Members Querying Log Analytics Querying the Log Analytics workspace with KQL from Python.
  9. 56:31 09Cost Members Structured queries and cost Querying with functions, and tokens, cost and models.
  10. 55:48 10Cost Members Tokens, models and rate limits More on cost and handling API rate limits.
  11. 42:27 11Cost Members Optimize KQL to save cost Reducing log volume sent to the model.
  12. 48:32 12Agent Members Baseline agent Agentic cyber AI, a baseline agent flowchart and code.
  13. 42:07 13Agent Members Mapping tools to KQL Mapping agent tools to KQL tables and queries.
  14. 69:08 14Safety Members Guardrails and threat-hunt prompting Guardrails to keep decisions aligned, and prompting for hunts.
  15. 35:54 15Response Members Agentic remediation: VM isolation Letting the agent isolate a VM in Defender for Endpoint, and wrap-up.

Jobs this course suits

Our AI checked this course against 500 jobs; these get the most out of it. Each job links to its learning path.

Cybersecurity AnalystsInformation Security AnalystsSecurity EngineersSite Reliability EngineersChief Information Security Officers (CISOs)Systems AdministratorsSystems Engineers