Red, Blue, Purple AI 2.0

Super‑charge your day‑to‑day security workflow with AI tactics.

Course Schedule:

Day 1: July 15 - 10am-5pm MST
Day 2: July 17 - 10am-5pm MST

Red Blue Purple AI – Course Description

Over the past few years, I’ve had the privilege of straddling two passions: offensive security and generative AI. That obsession has snowballed into a series of talks, tools, and now—this course. Red Blue Purple AI is a deep-dive into using LLMs like GPT, Claude, and others to supercharge your work across all major domains of cybersecurity.

This course isn’t just theory. It’s built from real-world consulting, hands-on research, and daily workflows I use as a practitioner. We’ll walk through not just how LLMs think—but how to train, trick, and optimize them to perform at a high level. By the end, you’ll have the knowledge to build domain-specific, high-performance bots that augment your workflow or even act autonomously.

If you're a security practitioner (offensive, defensive, or hybrid) or a curious leader looking to infuse AI into your security program, this course is for you.

See you in Red Blue Purple AI.

Who This Is For

Security engineers, SOC analysts, red‑/blue‑/purple‑teamers who already know the fundamentals of their role but want to 10× their output
Solo consultants and small teams that need “force‑multipliers” without head‑count increases
Tech‑savvy CISOs & security managers evaluating AI adoption for their operations

What You’ll Learn

Model IQ: quick‑start on LLM architecture, fine‑tuning options, context windows, cost models
Prompt Engineering Patterns: reusable templates for creating bots and agents.
Bot Factory: hands‑on labs building GPTs and micro‑agents that tackle repetitive tasks.

Red, Blue, Purple AI

$2,000

v2.0 Syllabus:

AI History & LLMs for Power Users

The modern rise of AI: GPT-3 onward...
My own LLMs in action (e.g., Arcanum Cyber Security Bot, GPT Store bots)
Model evaluations: Claude, GPT, DeepSeek, Gemini, Llama 3, ++
My choices for security tasks, research, and user use cases
Privacy strategies: obfuscation, local-first, Azure OpenAI
LLM architecture basics: context windows, temperature, system prompts, RAG, Agents
MCP and MCP in Security
Chat interfaces vs APIs
Playgrounds for APIs
Cloud vs local models
Frontends: Ollama, LM Studio, OpenWebUI, Fabric, ++

Prompt Engineering:

Problem solving for humans
Single-shot vs multi-shot
Chain-of-thought prompting
Metadata seeding
“Weird machine” tricks
The Arcanum System Prompt Methodology
Automation of best in class prompting via Systembot

New ways to use LLMS:

NotebookLM
Browser "driving"
General agents
Streaming
AI aided development and best practices
Multiprompting
Automation frameworks

Breaking Down Security Programs

Mental modeling of Red, Blue, and Purple domains
Mapping day-to-day workflows to AI agents
Tools, pain points, and how AI fits into daily security tasks

Red AI (Offensive Security & AI)

Augmenting Recon, OSINT

Custom GPTs: Subdomain Doctor, Acquisition and Recon GTP
Phishing and pretexting with AI

Vuln Analysis and Exploitation (Web)

LLM-assisted AppSec testing questions
JavaScript Analysis
LLM assisted filter bypass
Web CVE Bot
Scaling automated scanners (Nuclei, Nessus)

Burp Suite

A compete overview of all new Burp Suite AI features and extensions

Vuln Analysis and Exploitation (Red Teaming)

Initial access payload modification with LLMs
Ducky Script
Extending your C2 and research capabilities with LLMs
MCPs for Red Teaming

Reverse Engineering

A overview of the current RE assist extensions and MCPs for:

Ghidra
IDA Pro
LLDB
RADARE
Binary Ninja

Automating Pentesting with AI

An overview of the open source space, research space, and startup space when it comes to automating hacking. With a breakdown of the most common architectures and technologies to achieve that goal.

Misc

CloudSec, Privilege Escalation, Reporting with AI, and more

Blue AI (Defensive Operations & AI)

SOC, DFIR, and Threat Hunting bots:

ELK Sec Bot
Splunk Bot
Suricata Bot
YARA
OSQuery
Wireshark
PolicyBot
IR playbook creation with Incident Responder Bot
Tabletop and exec briefing bots
STIX data transformation bot

The future of blue teaming - MCP SIEM

Vuln management:

Best practices
Augmenting with LLMs
Automation approaches

Purple AI (Training & Simulation)

Code Analysis

Semgrep Bot
Snyk Bot
CodeQL resources
VulnHunter

MITRE ATT&CK

LLM-generated tabletops and security training tools

LLMs as force multipliers in program maturity and paved road security documentation

LLM Assisted Threat Modeling

Silver AI (Leadership, Strategy & Management)

AI for CISO-level decision making
Bots for risk communication and planning
Automation of executive briefs and strategic alignment

Future Tech and AI Research Frontiers

AI agents and autonomous security tools
The edge of AI-driven vulnerability discovery
Preparing for AGI-level assistants and ethical dilemmas

Some Reviews...

Just completed an outstanding "Red Blue Purple AI" training with Jason Haddix that explored how to leverage AI in cybersecurity from a Red Team perspective. The session was packed with practical strategies, including creating custom ChatGPT prompts to streamline and enhance cybersecurity workflows. Highly recommend this training for anyone eager to integrate generative AI into their security operations.

— Bharanisai M

Been slippin on my pimpin on this, but completed J a so n H a dd i x’s Red, Blue Purple AI course a couple weeks ago. My last post was after Day 1, but Day 2 continued to raise the bar. In my 7 years of learning all the security things I have never walked away from a machine, article, course, etc. with the amount of desire and inspiration to just dive into the things I learned from it. It not only gives you the knowledge required to start doing some cool things with AI, but for the ones with a mind built for discovery (i.e the hackers), it lays all the carrots you need to just dive into the rabbit hole and see what you come out with.

— Kristoffer Sketch

I’m happy to share that I’ve completed a new training on "Red Blue Purple AI".

It was wonderful and so much to learn, explore and brainstorm in the world of LLM, prompt engineering and security. It is just the beginning & this rabbit hole goes deep.

— Rishi N

This past week, I attended the Red Blue Purple AI course by Arcanum Information Security, and it was an incredible experience. Jason Haddix once again delivered a pioneering course, this time diving into security and AI. The depth of the technical content was impressive, and the active participation of some of my security heroes made it even more outstanding.

— Michael Medenblik

A huge thank you to Jason Haddix from Arcanum Security for the fantastic class: Red, Blue, Purple AI!

I thoroughly enjoyed the sessions this past Thursday and Friday and am eagerly looking forward to more classes with Jason. I've got my eye on the Bug Hunters Methodology class next. 👀

Shout out to anyone looking to dive deeper into becoming an LLM power user, improving at manipulating models, writing bots, and developing innovative systems and use cases. Jason's class is a must!

— Peter Drybrough

Day 2 of Jason Haddix's Red Blue Purple AI delivered powerful insights into using AI for creating everything from policy development, working bypasses, detection rules all the way to a functional vCISO bot - you name it. The class was truly extraordinary, with myself having multiple lightbulb moments. Phenomenal job! Highly recommend you take this when it's next available