Data Protection for AI Systems
What crosses the wire, what ends up in logs, retention and training terms, redaction, residency, and deleting a record that was already embedded into an index.
10 lessons · about 86 minutes
What you'll go through
- 01What actually crosses the wire when you call a model9 min
- 02The prompt you would never store is stored9 min
- 03Reading what the terms actually say9 min
- 04Nobody put the address there on purpose8 min
- 05The agent's notes nobody classified8 min
- 06Residency, and why «the cloud» is not an answer8 min
- 07Removing it before it is sent, not after9 min
- 08Deleting a record that was already embedded into an index9 min
- 09The security review you will be sent8 min
- 10Drawing where the data goes before you ship9 min
Included in this pack
AI Security — Prompt injection, what an agent can reach when it is compromised, and where your data actually goes. Assumes the AI Agents pack. Three courses, 30 lessons.
Also in this pack
Prompt Injection
Why no parser separates instructions from data, where untrusted text enters, why delimiters are not a boundary, and how to design so a landed instruction cannot do damage.
10 lessons · ~91 min$19.90
Agent Permissions
Blast radius, least privilege per tool, the confused deputy, secrets the agent must never see, egress control and an audit trail you can read months later.
10 lessons · ~91 min$19.90