Skip to content

Heidelberg AI Curriculum

Search the curriculum

Heidelberg AI
Curriculum

1Pick your portal

MatrixListJourney

2Your references

AI newsDaily ChangelogDaily FAQ Tips How-tos

Canvases Glossary Tools index App store (opens in a new tab)LLM index (opens in a new tab)Videos

A living curriculum for practical AI work.

Home
FAQ
What is agent sandboxing?

FAQ

What is agent sandboxing?

Agent sandboxing limits what untrusted generated code can read, change, contact, and consume.

Continue with the source

Read Agents with real credentials

Read Put a lock on it: securing a self-hosted stack

CurriculumAll tracks

Heidelberg AI Curriculum · 2026