Over the past few months, Microsoft has announced various first-party Copilot applications for Microsoft 365, Dynamics 365, Power Platform, and more. Today I will be sharing the app development patterns I used to create these solutions and show how developers can use this Copilot stack to develop their own copilots. Additionally, we are pleased to announce our joint commitment with OpenAI to support and grow the AI plugin ecosystem, embracing open standards that enable plugin interoperability across ChatGPT and the broader range of Microsoft’s Copilot products. .
Developers can build plugins that work across both consumer and business surfaces such as ChatGPT, Bing Chat, Dynamics 365 Copilot, Microsoft 365 Copilot, and other Microsoft first-party Copilot apps. This means that developers can build the most natural user interface, an experience that allows them to interact with their app using human language.
Build next-generation AI-powered applications
We believe AI is the next big change in computing. That’s why Microsoft invests heavily in AI and the tools that deploy it to help developers and organizations do more. The latest innovations announced at Build empower developers to create unique experiences using comprehensive developer tools and new AI and machine learning capabilities. For more information, see this blog post by Jessica Hawk, CVP, Data, AI, and Digital Application Marketing.
The latest Azure AI and machine learning innovations include:
- Proud to announce Azure AI Studio New features for working with generative AI, including: simply Build an OpenAI model on your data, is coming to the preview. With just a few clicks, developers can now build his OpenAI models such as ChatGPT and GPT-4 on their data to quickly and easily build organization-specific conversational AI experiences.
- Azure AI prompt flow Coming to preview, it will provide a streamlined experience for prompting, evaluating, tuning, and operationalizing language models at scale. Hundreds of popular open source and proprietary models and data sources for developers and data scientists to build intelligent applications, assess workflow quality and select the best prompts for their use case You can quickly create prompt workflows that connect to
- Azure OpenAI plugin, The private preview launch streamlines the process of building and consuming APIs that extend the functionality of GPT-4. Plugins for Azure Cognitive Search, Azure SQL, Azure Cosmos DB, Microsoft Translator, and Bing Search will be available during private preview.
- To facilitate working with the open source model, we are also introducing the following features: The underlying model of Azure Machine Learning, This starts with a model catalog to select from a collection of foundational models, including both Azure OpenAI Service models and open source models curated by Azure Machine Learning and Hugging Face, and the ability to fine-tune and deploy these foundational models. provide. Use Azure Machine Learning components and pipelines.
- new Vector search capabilities in Azure Cognitive Searchin private preview, is allowed Users can store, index, and search within datasets based on vector representations of data, also known as embeddings, to find information that is semantically similar to search queries. Vector search can be used in conjunction with ChatGPT’s search plugin via the Azure OpenAI service.
- the current, Azure OpenAI service provisioned throughput modelprovides dedicated capacity.
- new Azure AI content safety The service makes it easy for developers to test and assess the safety of AI deployments by detecting and assigning severity scores to unsafe content across languages, both images and text. We are integrating Azure AI Content Safety across products such as Azure OpenAI Service, Azure AI Studio, and Azure Machine Learning to enable practitioners to evaluate models before deployment and as a content moderation tool.
We also announced exciting updates to our comprehensive developer tools and app platform portfolio, including:
- microsoft dev boxis an Azure service that will be generally available in July, giving developers access to code-ready, secure, centralized, project-specific development boxes. Microsoft Dev Box supports hybrid development teams of all sizes, letting developers focus on writing code by streamlining access to all the resources and tools they need for the project at hand.
- GitHub Advanced Security for Azure DevOps This is a solution that brings the three core capabilities of GitHub Advanced Security to the Azure DevOps platform, allowing customers to integrate automated security checks into their workflows. This includes code scanning powered by CodeQL to detect vulnerabilities, incognito scanning to ensure code repositories are free of sensitive information, dependencies to identify vulnerabilities in open source dependencies and provide update alerts Includes scans.
- Azure Deployment Environment (ADE), Now generally available, developer teams can quickly launch app infrastructure using project-based templates, minimizing setup time while maximizing security, compliance, and cost efficiency. increase. ADE provides self-service templates to deploy directly from development tools, code repositories, or custom developer portals, and maximizes security through centralized permissions and policy governance, access control, and full management of cloud resource configuration .
- Azure Kubernetes Service (AKS): To give businesses more control over their environments, we are announcing long-term support for Kubernetes that will allow customers to continue using the same release for two years, twice as long as they can today. AKS Confidential Containers will also be in preview soon, as a first-party offer to enable teams to run standard, unmodified containers in partnership with the Kata Confidential Containers open source project.
