Keryn Academy

Learn to secure software that uses AI.

Courses, hands-on labs, flash cards and scored assessments for the people who build, review and defend AI systems. Finish the labs and you hold a credential that anyone can verify.

  1. 01Take a lesson

    Pick a course and read the modules.

  2. 02Drill the cards

    Flash cards across 14 domains.

  3. 03Check yourself

    A short check, then a scored assessment.

  4. 04Pass the labs

    Two passed labs earn your first credential.

  5. 05Share a verifiable credential

    Anyone can confirm it on a public page.

6
Courses
11
Credential labs
216
Flash cards
14
Assessment domains
4
Credential levels

Courses

Courses for every role on an AI team.

Written for the people who build, test, sell, govern and operate AI products. Each course ends in checks you can take for credit.

Defendintermediate6h

Keryn Academy course

Secure Coding with GenAI

Build, review, test, and ship AI-assisted code safely.

Evidenceintroductory5h

Keryn Academy course

AI Security for Sales Engineers

Speak clearly about AI risk, controls, and buyer trust.

Attackintermediate6h

Keryn Academy course

AI Red Teaming for Product Teams

Test LLM, RAG, and agentic systems before users and attackers do.

Mapintroductory5h

Keryn Academy course

AI Product Management for Secure AI Features

Define, scope, and ship AI products buyers can trust.

Defendintermediate6h

Keryn Academy course

AI Model Gateways and Secure Platforms

Build the approved path for safe AI adoption.

Talent AIIntroductory5h

Keryn Academy course

Hiring AI-Savvy Talent Without Unicorn Hunting

Build better reqs, sharper scorecards, and roles the market can fill.

How it fits together

Four pillars. One workflow.

Every course, lab and assessment maps to Map, Attack, Defend or Evidence, so you always know which part of the work a gap belongs to.

Map: discover and model

Inventory AI systems, draw trust boundaries, trace retrieval paths, identify agent authority.

Explore
Attack: test and validate

Probe for prompt injection, indirect injection, retrieval leakage, tool misuse and workflow bypass.

Explore
Defend: harden and verify

Design controls, approval gates, evals, telemetry and rollback paths, then check they hold.

Explore
Evidence: package and communicate

Write findings, retest records and residual-risk summaries a reviewer can act on.

Explore

Start with ten minutes.

Run the speed run to see where you stand, or check your team's AI-security basics. Create an account when you want your lab completions saved and your credential issued.