Using AI to Build an AI Java App

Brian Benz shows several demos that highlight how to use Generative AI and Spring to build a Java codebase, then use OpenAI and GitHub Copilot to improve the experience of building, updating and deploying the application. We’ll share insights about Azure, OpenAI, and the power of Java when working with AI. Code will be provided!

Transcript

1. Using AI to Build an AI Java App Brian Benz Cloud Advocate, Microsoft @bbenz
3. Azure AI Azure AI services Bot Service Cognitive Search Form Recognizer Video Indexer Metrics Advisor Immersive Reader Vision Speech Language Decision ML Platform AI Infrastructure Azure OpenAI Service Azure Machine Learning
4. Announcing Azure AI Studio Build and train your own models Ground Azure OpenAI Service and OSS models using your data Built-in vector indexing Retrieval augmented generation made easy Create prompt flows AI safety built-in
5. Azure OpenAI Service on your data App or Copilot agent API & SDK Azure OpenAI Service on your data Data Sources (search, files, databases, storage etc.) Additional 3P Data Sources (files, databases, storage data etc.)
6. A copilot for every Microsoft Cloud experience Microsoft 365 Copilot Dynamics 365 Copilot Copilot in Power Platform GitHub Copilot Increase developer productivity to accelerate innovation Imagine it, describe it, and Power Platform builds it Turbocharge your workforce with a copilot for every job role Works alongside you in the apps you use every day Learn more Learn more Learn more Learn more Microsoft Security Copilot Defend at machine speed with Microsoft Security Copilot Learn more
7. Offers code suggestions, contextualized to your project Convert comments to code Autofill for repetitive code Show alternatives
8. Keep flying with your favorite editor VS Code Visual Studio (Windows) JetBrains IDEs Neovim GitHub Codespaces
9. Once enabled… OpenAI Codex Context Suggestions
10. Copilot Chat awareness: • File names • Open files • Cursor • Selected
11. • Inline completions: • Ctrl/Cmd+enter to get a list of suggestions • option+] or [ to navigate the possible suggestions. • Ctrl/Cmd+> to accept word by word • Tab to accept suggestions.
12. Our responsible AI journey 2016 Satya Nadella’s article on AI Design Principles 2017 Aether Committee established 2018 AI Principles adopted 2018 Facial Recognition Principles adopted 2019 Office of Responsible AI established 2019 Responsible AI Standard v1 2020 Responsible AI Strategy in Engineering established 2021 Responsible AI Dashboard 2022 Responsible AI Standard v2
13. Privacy & Security Inclusiveness Accountability Fairness Reliability & Safety Transparency Microsoft’s Responsible AI Principles Tools and processes Governance Rules Training and practices Building blocks to enact principles
14. Microsoft AI Principles Fair | Accountable | Transparent | Ethical AI must maximize efficiencies without destroying the dignity of people 1 AI must guard against bias 2 AI needs accountability so humans can undo unintended harm 3 AI must be transparent 4 AI must be designed for intelligent privacy 5 AI must be designed to assist humanity 6
16. Using AI to Build an AI Java App Brian Benz Cloud Advocate, Microsoft @bbenz https://microsoft.com/java https://aka.ms/githubcopilot https://learn.microsoft.com/en-us/ai https://resources.github.com/copilot-trust-center/ https://learn.microsoft.com/en-us/legal/cognitive- services/openai/data-privacy