# Day 1 Lecture: Trusting your workflows (evaluation metrics and guardrails)

> Understanding how to trust your workflows is crucial for ensuring the quality of applications in production. This lecture covers evaluation metrics, guardrails, and the importance of preventing issues like hallucinations and prompt injections in AI systems. Participants will learn about multi-tenan…

- Web page: https://www.dataexpert.io/lesson/ml-ops-day1-lecture-july25
- Program: [AI Engineering Boot Camp Starting on July 7th, 2025](https://www.dataexpert.io/program/ai-boot-camp-starting-june-7th-8623)
- Access: Requires enrollment in AI Engineering Boot Camp Starting on July 7th, 2025
- Length: 27 min video
- Skills: NLP, MLOps, LLMs
- Academy: DataExpert.io Academy

## About this lesson

Understanding how to trust your workflows is crucial for ensuring the quality of applications in production. This lecture covers evaluation metrics, guardrails, and the importance of preventing issues like hallucinations and prompt injections in AI systems. Participants will learn about multi-tenant architecture for sensitive data, explore real-world examples of failures, and discover tools like OpenAI's moderation API and Guardrails AI to enhance application reliability and security.

## Navigation

- Previous lesson: [Day 2 Lab: Enhancing RAG with Agentic AI](https://www.dataexpert.io/lesson/advanced-rag-and-agentic-ai-day2-lab-july2025.md)
- Next lesson: [Day 1 Lab: Setting up CI/CD for an AI application](https://www.dataexpert.io/lesson/ml-ops-day1-lab-july25.md)