Skip to content
Flag of Europe
Made in the European Union · Independently built · Released under EUPL 1.2

AI-Security for Developers

AI features fail in ways classic AppSec never taught: untrusted text becomes control flow, retrieval pulls in data you didn't vet, and agents act with your credentials. This hands-on course gives developers the mental model and the patterns to build RAG, chat and agent systems that hold up under adversarial use.

Hands-on labs ≈ 1 day On-site · live-online EN / DE No ML background needed

What your team can do after

Concrete, transferable skills — not a vendor demo.

Agenda

Six modules, each ending in a hands-on lab — tailored to your stack and use case.

  1. The new attack surface Why text = control flow; the LLM / RAG / agent threat map.
    Lab: threat-model a sample assistant.
  2. Prompt injection Direct & indirect (poisoned retrieval), and how to contain it.
    Lab: break and harden a RAG prompt.
  3. Data exfiltration & leakage System-prompt & secret leakage, cross-tenant bleed.
    Lab: plug a leakage path.
  4. Retrieval & tool guardrails Source trust, tenant isolation, least-privilege tools, confirmations.
    Lab: sandbox an over-eager tool.
  5. AuthZ for AI Constrain what the model may read & do — maps to jSentinel.
    Lab: gate an agent action by permission.
  6. Evaluations Adversarial test suites, red-team prompts, CI wiring.
    Lab: build an injection eval suite.

Who it's for

Developers and tech leads adding RAG, chat, copilots or agents to a product — anyone who has to ship AI features and own the consequences.

Prerequisite: general development experience; no ML background required.

Logistics

📋 Course details

Formats
On-site · live-online · on-demand (in preparation)
Duration
Typically 1 day — tailored to your stack & use case
Languages
English or German
Trainer
Sven Ruppert
Need the systems themselves reviewed or designed, not just the team trained? See AI-Security consulting. Request this course to get started.