Module · Intermediate
Safety, ethics and compliance
Prompt injection and jailbreaks, privacy under LGPD and GDPR, bias and responsible AI, content moderation and usage policies, transparency and human escalation.
Agents talk to real people and touch real data. This module explains the risks in plain terms and the controls that keep them acceptable.
- 1 Prompt injection and jailbreaks Recognise attempts to redirect an agent and build practical layers that limit their impact.
- 2 Privacy, LGPD/GDPR and sensitive data Plan how an agent collects, uses, stores and deletes personal information without sending more than the task needs.
- 3 Bias, fairness and responsible AI Recognise unequal treatment, test for it and make human accountability part of an agent's design.
- 4 Content moderation and usage policies Define an agent's boundaries and respond to unsafe or out-of-scope requests without abandoning legitimate user needs.
- 5 Transparency and human escalation Make the agent's identity and limits clear, and design a handover that gives people useful context rather than more work.