| Udacity Offers 40% Off |
| Written by Alex Denham | |||
| Monday, 29 December 2025 | |||
|
Udacity is encouraging us to put the holiday time to good use with a special offer running until the New Year - 40% off across all its programs when you pay in advance.
The deal ends on 12/31, so you need to get a move on, but there are plenty of useful looking courses to choose from, including a whole collection dedicated to artificial intelligence at a variety of levels, both individual courses and Udacity's popular Nanodegree longer courses.
Disclosure: When you make a purchase having followed a link to from this article, we may earn an affiliate commission. Agentic AIOne of the more recent additions that sounds well worth considering is the Agentic AI Nanodegree course. This overall course consists of four individual courses and 71 lessons. The courses are
Together, these courses take participants beyond single chatbots to engineer sophisticated, coordinated teams of AI agents. The course guides you from advanced prompting techniques like Chain-of-Thought and ReAct to designing agentic workflows with patterns like Routing and Parallelization. The course also covers how to build and orchestrate agents in Python that can reason, plan, and use tools to interact with databases and external APIs. The hands-on projects that you undertake include a multi-agent travel planner, an AI-powered project manager, and a fully automated sales system. Agentic AI requires participants to be familiar with the OpenAI API, basic Python, and Generative AI Fluency. AI Programming with PythonGiven that this is at Advanced Level and has as a pre-requisite knowledge of Python many students opt first to complete AI Programming with Python, which is billed at the top rated of the AI courses Udacity has on offer with students awarding it 4.7 out of 5, based on 1629 reviews. This is a 3-month program at Beginner Level that introduces the programming tools you need for AI - not only Python but also NumPy and PyTorch. It also covers the math you'll need - calculus and linear algebra - and the key techniques of neural networks - gradient descent and backpropagation. Generative AIComing in with a very impressive star rating of 4.9 out of a maximum 5 stars, the Generative AI course concentrates on teaching developers how to deploy reliable generative AI solutions. The course covers production techniques including model selection, cost estimation, and reliable prompt engineering to build efficient apps. Participants will also implement lightweight model adaptation using PEFT, then build end-to-end RAG systems, using vector databases to connect LLMs to your data and evaluate quality with frameworks like RAGAs. The three courses that this contains together run for 56 hours, and are:
By the end of the course, participants will have explored advanced multimodal applications that process text, images, and audio, and learned how to enforce structured outputs with Pydantic and implement system observability to build, trace, and debug modern AI apps. The three courses that this contains together run for 56 hours, starting from Generational AI Fundamentals. This course looks at how various models are developed, how they work, and how to use them to their full potential. The course gets into the nitty gritty of generational AI, including how to implement evaluations for Generative AI models including techniques such as ROUGE, semantic similarity, code correctness, Pass@k, and LLM-as-a-Judge scoring. Participants learn how to implement neural networks in PyTorch by mastering tensors, model building, loss functions, optimizers, data loading, and complete training loops for practical machine learning. They also learn to implement Role-Based prompting with Python, and how to adapt foundation models for specialized tasks using prompt engineering, RAG, fine-tuning, model compression, and agentic AI tools for efficient, tailored AI solutions. The second course moves on to Large Language Models (LLMs) and Retrieval Augmented Generation (RAG). This hands-on course looks at how to build sophisticated text generation applications using techniques including prompt engineering, optimization of model selection and costs. It also covers Retrieval-Augmented Generation (RAG), using vector databases to ground AI responses in external data and eliminate hallucinations. Finally, you'll evaluate system performance with RAGAS and build an end-to-end RAG application. The third course, Multimodal AI Applications, teaches how computers process and understand image data, then shows how to harness the power of the latest Generative AI models to create new images. Among the highlights we spotted in this course are lessons on audio sentiment analysis with Pydantic AI and Gemini to learn to extract emotions and recognize spoken commands from audio with real-world datasets and hands-on exercises; and building a basic voice moderation system with Gemini to transcribe audio, detect personal data disclosures, and flag policy violations in customer service recordings. There's a module on implementing object recognition & tracking in videos using YOLOv9; and another on video analysis and search using foundation models and CLIP4Clip. A module on using Gradio and Pydantic AI covers async programming, media inputs, rate limiting, and interface customization; while another module looks at implementing logging and performance monitoring for multimodal AI chatbots using Gradio and Arize Phoenix, enabling robust analytics, debugging, and cost tracking. The courses we've chosen are just a taster of the wide-ranging courses Udacity offers both on AI and other topics, and would make a great start to the new year.
More Information
Related ArticlesUdacity's New Discovering Ethical AI Course Udacity Launches Gen AI Nanodegree The Benefits of A Udacity Nanodegree Start Your Career With Udacity Nanodegree To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Facebook or Linkedin. 
Comments
or email your comment to: comments@i-programmer.info |
