AI Moderation and Security with Mistral
Secure your AI applications with Custom Guardrails and the Moderation API featuring 11 content categories, detection thresholds, and content policy implementation in production.
12 lessons About 1 h 15 min Developer
What you'll learn
- Implement Custom Guardrails that block a request before the model call
- Call the Moderation API and interpret scores for the eleven content categories
- Set detection thresholds consistent with the defined content policy
- Detect and neutralize prompt injection attempts in user inputs
- Design a complete security architecture, GDPR compliant, for a production application
Course details
- Who it's for
- Developers, engineers, and integrators looking to leverage Mistral AI via API in their applications.
- Prerequisites
- Ability to read Python and JSON, and basic command line skills. A Mistral AI Studio API key to try the examples.
- Length
- 1 h 15 min · 12 lessons
- Format
- 100% online self-paced course, accessible 24/7 from a browser. Progress is saved, allowing you to resume at any time. Estimated duration: 1 h 15 min.
- Assessment
- Self-assessment based on the Key takeaways concluding each lesson, and direct implementation of the examples on your own examples. A final quiz of 5 corrected questions at the end of the last lesson validates acquired skills.
- Accessibility
- Course accessible to people with disabilities: text content compatible with screen readers, keyboard navigation, and compliant contrasts. For any adaptation needs, email [email protected].
- Price
- Free
- Recognition
- Certificate of completion issued by Corsen AI, verifiable online.
- Syllabus
- Download the syllabus (PDF)