The Sec Guy
Open Menu

The course · AI Security for Cloud Folks

Secure what you build with AI — from your laptop to AWS

The hands-on AI security course for people who already work in tech. Defender-first, starts from zero, and every lab runs free on your laptop before you ever touch the cloud.

Pre-sale opens 1 Nov See the full curriculum

Founding price $49 until 30 Nov 2026 (then $199). Start with the free lessons today.

How the labs work

Every lab runs free first

Local twin · $0

On your laptop

Docker, small open models through Ollama, a local vector database and open-source security tools. Break the app, fix it, and run make test to prove the fix works.

AWS twin · optional

In your AWS account

The same lab on Bedrock and AgentCore with Terraform: make cost prints the estimate, then make up, make test, make down. Budget alarms and auto-teardown tags on everything.

Who it's for

Built for nine kinds of people

Everyone who works near AI and was never taught to secure it. No AI or maths background needed.

SOC analyst / detection engineer

You already knowLogs, alerts, triage, ATT&CK, incident response

You'll learnWhat AI attacks look like in logs, LLMjacking, and running an AI incident end to end

Cloud security engineer / architect

You already knowIAM, SCPs, VPC endpoints, KMS, logging, guardrails as code

You'll learnBedrock, Guardrails, AgentCore and SageMaker AI controls; signing off AI launches on AWS

AppSec engineer / pentester

You already knowOWASP Top 10, injection, threat modelling, testing

You'll learnPrompt injection, agents and MCP as attack surface; AI security tests in CI

Developer / ML engineer

You already knowApps, APIs, auth, secrets, CI/CD

You'll learnThe AI-specific mistakes: trusting model output, over-powered tools, RAG leaks

Vibe coder / no-code builder

You already knowShipping fast with AI tools and APIs

You'll learnWhy AI-written apps leak keys and data, plus a 10-point "before I launch" checklist

Founder / business owner

You already knowCustomers, risk, budgets, vendors

You'll learnWhat AI may do in your product, a 1-page AI policy, and what to ask vendors

GRC / risk / compliance

You already knowFrameworks, controls, audits, policies

You'll learnNIST AI RMF, ISO 42001, EU AI Act and OWASP mapped to real technical controls

IT / DevOps / platform engineer

You already knowInfrastructure, Terraform, containers, networking

You'll learnSelf-hosting models safely, the model supply chain, private AI endpoints

Student / career switcher

You already knowCuriosity (that is enough)

You'll learnEverything from scratch, plus portfolio projects and a capstone for interviews

Every lesson, the same shape

Basics first, every time

  1. 1

    Real incident

    Every lesson opens with something that actually happened, with the source.

  2. 2

    You already know

    We bridge from what you know (SQL injection, IAM, a help desk) to the AI version.

  3. 3

    Everyday picture

    A plain analogy, and where it stops working.

  4. 4

    Break it

    The attack, live, in the lab app.

  5. 5

    Fix it and spot it

    The control, and what it looks like in the logs.

  6. 6

    Recap card

    Three lines, plus how to say it in an interview.

What's inside

6 parts, 33 modules

Every lesson →

Part 1

Foundations

How LLMs really work and how to threat-model them. Anyone can follow.

  • M0Start here: you belong in AI security
  • M1How LLMs actually work (for security people)
  • M2Threat modelling AI systems

Part 2

Attack and defend any AI app

Prompt injection, data leaks, RAG, agents, MCP and the AI supply chain. All local, all $0.

  • M3Prompt injection and jailbreaks
  • M4Data security and privacy
  • M5Output handling and LLM app security
  • M6RAG security
  • M7AI agent security
  • M8MCP security
  • M9Open-source models and the AI supply chain

Part 3

AI security on AWS

Bedrock, Guardrails, Knowledge Bases, AgentCore, SageMaker AI, and detection and response.

  • M10The AWS AI footprint and shared responsibility
  • M11Securing Amazon Bedrock
  • M12Amazon Bedrock Guardrails
  • M13Bedrock Knowledge Bases and Bedrock Agents
  • M14Amazon Bedrock AgentCore (attack and defend)
  • M15SageMaker AI security (self-hosted and open models)
  • M16Detection and response for AI on AWS

Part 4

Prove it

Red teaming, security evals in CI, governance, and a graded capstone with a certificate.

  • M17Red teaming and security evals
  • M18Governance that engineers can use
  • M19Capstone and career

Part 5

Advanced track

Agent identity, deterministic authorization, secure-by-design agents, adaptive attacks and more.

  • M20Agent identity and delegated authorization
  • M21Deterministic authorization for tool calls
  • M22Secure-by-architecture agents
  • M23Breaking defences: adaptive red teaming
  • M24Multi-agent and protocol security
  • M25Advanced AI supply chain
  • M26Inference infrastructure hardening
  • M27Isolation, egress and computer-use agents
  • M28Privacy engineering for AI
  • M29AI security operations at scale
  • M30Security evals as a release gate
  • M31Agentic commerce and fraud
  • M32Advanced capstone (graded)

Part 6

Future watch

A short "what changed" update every quarter, free for every student.

How it compares

AWS hands-on depth, without the bootcamp price

Hands-on Bedrock and SageMaker labs are usually only found in $8,000+ bootcamps. Most mid-priced AI security courses are cloud-agnostic and focused on red teaming.

This courseTypical AI security coursesHands-on bootcamps
Hands-on AWS labs (Bedrock, Guardrails, AgentCore)Yes, every AWS moduleRare; most are cloud-agnosticYes
Defender-first: detection and response for AIYes, a full moduleMostly red-team focusVaries
A $0 local version of every labYesVariesRarely
Starts from zero (no AI or maths background)YesVariesUsually assumes experience
Price$49 founding, then $199Usually subscriptions or $500–$1,800Often $8,000+

One price, everything included

Founding price

$49 $199

$49 / ₹499 founding price. Then $199 / ₹1,999.

Founding price ends .

Local pricing applies at checkout based on your billing country (for example India: ₹499, then ₹1,999). One-time payment, no subscription.

  • Every video, reading page and lab across all 6 parts
  • Local and AWS lab solutions
  • Downloadable slide deck (PDF) for every module
  • Graded capstone and certificate
  • Every future update, including the quarterly future-watch
Pre-sale opens 1 Nov

Release schedule

New modules every two weeks

  1. 1 Nov 2026Pre-sale opens · M0–M1 (+ public lab repo)
  2. 14 NovM2–M3: threat modelling, prompt injection
  3. 28 NovM4–M5 + lesson 9.6 for vibe coders
  4. 12 DecM6 RAG + M8 MCP (+ M9 supply chain)
  5. 26 DecM7 agents + M10 AWS AI footprint
  6. 9 Jan 2027M11–M13: Bedrock, Guardrails, Knowledge Bases
  7. 23 JanM14 AgentCore + M16 detection and response
  8. 30 JanM15, M17–M19: capstone opens
  9. Feb–Apr 2027Part 5 advanced track, about one module a week
  10. Every quarterPart 6 future-watch update

Try before you buy

17 free lessons

Free lessons are published here and on YouTube as they're recorded.

Questions

FAQ

Do I need an AI, machine-learning or maths background?

No. The course starts at "what is a token" and every term gets a one-line plain meaning before it's used. If you can follow a cloud console or a terminal, you can follow this.

Will the labs cost me money?

Every lab runs free on your laptop first (Docker + small open models). The AWS versions are optional; each prints its estimated cost before it deploys, uses budget alarms, and tears itself down. New AWS accounts can get free credits.

How do I access the course after buying?

Lemon Squeezy emails you a receipt with a license key. Sign in at thesecguy.com/learn with your email and that key. You can be signed in on up to 3 devices.

When do modules unlock?

Modules are released on the schedule above. You get every module as it ships, and every future update, with one payment.

Why is the price different in my country?

Lemon Squeezy applies local pricing at checkout based on your billing country. For example, India is ₹499 at the founding price (₹1,999 regular).

Who handles payment, tax and invoices?

Lemon Squeezy is the merchant of record: it takes the payment, handles VAT/GST, and sends the invoice. We never see your card details.

What is the refund policy?

Refunds are processed by Lemon Squeezy. The exact refund terms will be published here before the pre-sale opens. Questions before then: [email protected].

Do I get a certificate?

Yes, when you pass the graded capstone (secure the full course app locally and on AWS, scored against a published rubric).

Can my team buy it?

Email [email protected] for team purchases and invoices in your company's name.

Be the person who can secure the AI your team ships.

Pre-sale opens 1 NovAsk a question

Made by a cloud and AI security architect with a decade and a half in the field. Questions: [email protected]