DeepLearning.AI has recently launched a new, free short course titled “Safe and Reliable AI via Guardrails” in partnership with Guardrails AI. The course, taught by founder Shreya Rajpal, aims to help learners explore and mitigate common failure modes in LLM-based apps, such as hallucinations and exposure to sensitive information. It also teaches how to implement ‘guardrails’ to prevent these failure modes by accessing pre-built guardrails on GuardrailsAI.
According to DeepLearning.AI, the course will show learners how to build robust guardrails from scratch to mitigate common failure modes of LLM-powered applications. These guardrails will be implemented on a small pizzeria’s ‘RAG-powered customer service chatbot’ to help learners understand the concepts through a real-world example. The course will also cover setting up a guardrail to limit the chatbot’s output relevant to the pizzeria and using a ‘Personal Identifiable Information’ guardrail to detect sensitive information in both input prompts and output responses. The only prerequisite for the course is basic Python knowledge.
In a preview video for the course, Andrew Ng, the founder of DeepLearning.AI, stated that guardrails will become increasingly important in the AI applications stack, especially in industries with stricter safety, privacy, or regulatory requirements. This course is the latest addition to DeepLearning.AI’s collection of over 50+ short and free courses focusing on safe and efficient deployment of generative AI products. The platform also offers dedicated courses and specializations on broader topics like data engineering, machine learning, deep learning, and more.
Andrew Ng’s efforts in democratizing AI education have reached over 7 million students, who are using the platform to future-proof their skills. He is also the co-founder of Coursera and was recently inducted into Amazon’s board of directors. Last week, DeepLearning.AI released another short course titled “LLMs as Operating Systems: Agent Memory” to help learners build agents that can successfully manage the memory and context of an LLM using Letta’s open-source framework.
In conclusion, DeepLearning.AI’s new short course on building safe and reliable AI is a valuable addition to their collection of courses and specializations. With Andrew Ng’s expertise and efforts in democratizing AI education, the platform continues to provide accessible and high-quality learning resources for students worldwide.
