Custom Vision is a machine learning service by Azure AI that empowers users to build, train, and deploy custom models that can recognize specific images. It supports a range of image classification tasks, including object detection and image tagging. Users can upload their own labeled images, train their models, and evaluate performance, all from a simple web interface. This service is designed to be scalable and cost-effective, ensuring that users only pay for what they use, whether that be training hours or image storage.

The LLM Maze Agent framework provides a Python-based environment for building intelligent agents capable of navigating grid mazes using large language models. By combining modular environment interfaces with chain-of-thought prompt templates and heuristic planning, the agent iteratively queries an LLM to decide movement directions, adapts to obstacles, and updates its internal state representation. Out-of-the-box support for OpenAI and Hugging Face models allows seamless integration, while configurable maze generation and step-by-step debugging enable experimentation with different strategies. Researchers can adjust reward functions, define custom observation spaces, and visualize agent paths to analyze reasoning processes. This design makes LLM Maze Agent a versatile tool for evaluating LLM-driven planning, teaching AI concepts, and benchmarking model performance on spatial reasoning tasks.

PromptsLabs is a platform where users can discover and share prompts to test new language models. The community-driven library provides a wide range of copy-paste prompts along with their expected outputs, helping users to understand and evaluate the performance of various LLMs. Users can also contribute their own prompts, ensuring a continually growing and up-to-date resource.