{"id":30111008,"url":"https://github.com/github-insight-anz-lab/agentic-aiapp-in-a-day","last_synced_at":"2025-08-10T05:06:26.738Z","repository":{"id":305874157,"uuid":"1024228172","full_name":"GitHub-Insight-ANZ-Lab/agentic-aiapp-in-a-day","owner":"GitHub-Insight-ANZ-Lab","description":null,"archived":false,"fork":false,"pushed_at":"2025-08-09T02:36:04.000Z","size":12394,"stargazers_count":1,"open_issues_count":1,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-09T04:15:29.456Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GitHub-Insight-ANZ-Lab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-07-22T11:25:14.000Z","updated_at":"2025-08-09T02:36:08.000Z","dependencies_parsed_at":"2025-08-09T04:08:37.713Z","dependency_job_id":"b497c7eb-8ce0-4153-b065-a24e6dbff162","html_url":"https://github.com/GitHub-Insight-ANZ-Lab/agentic-aiapp-in-a-day","commit_stats":null,"previous_names":["github-insight-anz-lab/agentic-aiapp-in-a-day"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/GitHub-Insight-ANZ-Lab/agentic-aiapp-in-a-day","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GitHub-Insight-ANZ-Lab%2Fagentic-aiapp-in-a-day","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GitHub-Insight-ANZ-Lab%2Fagentic-aiapp-in-a-day/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GitHub-Insight-ANZ-Lab%2Fagentic-aiapp-in-a-day/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GitHub-Insight-ANZ-Lab%2Fagentic-aiapp-in-a-day/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GitHub-Insight-ANZ-Lab","download_url":"https://codeload.github.com/GitHub-Insight-ANZ-Lab/agentic-aiapp-in-a-day/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GitHub-Insight-ANZ-Lab%2Fagentic-aiapp-in-a-day/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269677801,"owners_count":24457876,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-10T02:00:08.965Z","response_time":71,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-08-10T05:06:26.105Z","updated_at":"2025-08-10T05:06:26.719Z","avatar_url":"https://github.com/GitHub-Insight-ANZ-Lab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Agentic AI App in a Day (Draft)\n\n![Agentic AI App in a Day Cover](res/workshop-cover.png)\n\n## Overview\n- Duration: 9am to 4pm\n- Demo: Azure Portal \u0026 VS Code\n- Lab: GitHub Codespaces\n\n### Goal\n\n- Build on the Agentic AI aspects\n- Inspire and Motivate \n- Real world ideas for Agentic AI\n- Focused on End-to-end building AI-powered applications\n- Frictionless learning environment, learn via lab, demo and teaching moments\n- Azure AI Protections\n- GitHub Copilot Agent Model to accelerate development\n- For some people without laptops or limited technical skills, allowing them to watch walkthroughs, whilst others do them\n\n### Audience\n- Technical teams\n- Senior management like C-levels\n\n### Labs\n\n- Keep lab simple and able to be done end to end\n- For experienced developers, share the accelerator repos and let them explore\n\n\nNote: some of the labs will be adjusted based on the resources and licences available for the participants to use.\n\n## Presentation #1: Morning, Kick-start – 30 min\n**Topics:** Basic Concepts and Overview\n- Azure AI + Agentic AI overview  \n- Agentic AI design patterns (Planning, Tool Use, Reflection, Multi-agent)  \n- Agent architectures: ReAct, Chain-of-Thought\n- Memory systems for agents (short-term, long-term, episodic)\n- Tool integration patterns and API orchestration\n- Intelligent data layers (Azure AI Search, RAG)  \n- Low/No Code option in Copilot Studio (vs pro-code)\n\n## Demo #1: AI App Demo - 15min\n**Showcasing a fun AI App**\n- use a Accelerator Repo\n- Daniel's LEGO coding chatbot app demo\n\n## Lab #1: AI Foundry Integration \u0026 Extension - 50min\n**Explore AI Foundry services:**\n- Use Playground and Model Catalog \n- Various Azure AI Services\n- Customize agent orchestration using no-code / low-code blocks (Functions)\n- Connect additional tools and knowledge bases (e.g., a calculator API, web search API)\n- Connect Agents\n\n## Demo #2: Complex AI App Demo - 15min\n***Demonstrating Advanced AI Solutions**\n- use a Accelerator Repo\n- refer to the repo list in the end\n\n## Lab #2: Add Intelligent Data Layer - 50min\n**Integrate Azure AI Search or Cosmos DB:**\n- Ingest doc into Azure AI Search\n- Use Document Intelligence Service\n- Connect agent to knowledge base\n- Demonstrate contextual reasoning\n- Build a memory/retrieval plugin with Semantic Kernel\n- Advance query, score profile, index, indexer in AI Search\n\n## Presentation #2: After Lunch – 30min\n**Topic:** Building Production-Ready AI Apps with Agentic Concepts\n- Technical Deep Dive: Advanced reasoning architectures and hybrid - approaches for complex problem-solving\n- Platform-First Strategies: Scaling, API management, DevOps, and platform selection best practices\n- Practical Considerations: Memory, cost, performance optimization - and error handling strategies\n- Enterprise Readiness: Security, evaluation, testing, and compliance frameworks for production deployment\n- Real-World Implementation Patterns: Customer service, document processing, developer tools, and multi-modal applications\n\n## Demo #3: GitHub Copilot Coding Assistant for AI App - 15min\n**Developer experience showcase:**\n- Prompt-driven coding assistant (e.g., auto-generate unit tests, fix bugs)  \n- Refactoring, adding comments/images, reformatting examples  \n- Show how devs stay in control but move faster\n\n## Lab #3: AI Agent 101 \u0026 Semantic Kernel + MCP - 70min\n**Build and extend your first agentic AI app:**\n- Implement the Prompt → Plan → Act → Reflect loop  \n- Use Semantic Kernel for memory, planning, and tool integration  \n- Chain outputs between tools and functions\n- Build and integrate MCP for advanced orchestration and extensibility\n- Experiment with adding new skills,\n\n## Demo #4: Multi-Agent Solution Walkthrough - 15min\n**Showcase advanced agent collaboration and orchestration:**\n- Demonstrate multi-agent workflows using Azure AI Foundry Services\n- Highlight agent collaboration: perception → planning → action loop\n- Explore coordination strategies and communication between agents\n- Present a real-world scenario (Daniel's agentic LEGO demo) to illustrate practical applications\n\n## Lab #4: AI Integration, Deployment \u0026 Productionise - 70min\n**Deploy and operationalize your agentic AI app:**\n- Containerize the agent app for portability and scalability\n- Deploy to Azure using ACA, AKS, or App Service with CI/CD\n- Expose APIs securely via Azure API Management (auth, rate limits, monitoring)\n- Implement logging, monitoring, and alerting for production readiness\n- Apply security best practices and cost controls\n\n## Presentation #3: Afternoon – 30min\n**Topic:** Wrap-Up: Responsible AI \u0026 Future Considerations\n- Responsible AI and Guiderails: Content filtering, prompt injection defense, evaluation, and monitoring\n- Observability \u0026 Operations: Agent analytics, performance metrics, cost tracking, and debugging\n- Advanced Topics \u0026 Future Trends: Fine-tuning, multi-modal agents, edge deployment, and emerging frameworks\n- Lessons Learned \u0026 Best Practices: Common pitfalls, testing strategies, and migration patterns\n- Next Steps \u0026 Resources: Certification paths, community support, and building your first production agent\n\n\n## Azure Services to be considered\n- **Azure AI Foundry (Model Catalog, Playground)** – To explore and test models  \n- **Azure AI Foundry – Agent Service** – For orchestrating multi-agent systems  \n- **Azure AI Services** – For integrating vision, speech, etc.  \n- **Azure OpenAI** – LLMs for chat, planning, coding, summarization  \n- **Azure AI Search** – Intelligent data layer for RAG\n- **APIM** – Secure, scalable API layer\n- **Azure Functions** – Serverless compute for tool integration\n- **Azure Logic Apps** – Workflow automation for tool orchestration\n- **App Service / AKS / ACA** – App hosting  \n- **Azure DevOps / GitHub Actions** – CI/CD for agent apps\n- **Azure Monitor / Application Insights** – Monitoring and logging\n- **Azure Key Vault** – Secure secrets management\n- **Azure Storage / Cosmos DB** – Data storage for agent state and knowledge\n\n## Dev toolchain to be considered\n- **Semantic Kernel** – For agent memory, planning, and tool integration\n- **Visual Studio Code** – IDE for development\n- **Jupyter Notebooks** – For interactive data exploration and model testing\n- **GitHub Codespaces** – Cloud-based dev environment for labs\n- **GitHub or Azure DevOps** – Source control and CI/CD pipelines and project management\n- **Azure CLI / PowerShell** – Command-line tools for Azure management\n- **Bicep** – Infrastructure as Code for Azure resources\n\n## Lab Exercise to be considered\n\n- https://github.com/Azure-Samples/AI-Gateway\n- https://github.com/microsoft/AI-For-Beginners\n- https://github.com/microsoft/ai-agents-for-beginners\n\n## Accelerator Repo to be considered\n\n- https://github.com/Azure-Samples/get-started-with-ai-chat\n- https://github.com/Azure-Samples/get-started-with-ai-agents\n- https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator\n- https://github.com/microsoft/content-processing-solution-accelerator\n- https://github.com/microsoft/document-generation-solution-accelerator\n- https://github.com/microsoft/Build-your-own-copilot-Solution-Accelerator\n- https://github.com/microsoft/Modernize-your-code-solution-accelerator\n- https://github.com/Azure-Samples/Azure-Language-OpenAI-Conversational-Agent-Accelerator\n- https://github.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgithub-insight-anz-lab%2Fagentic-aiapp-in-a-day","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgithub-insight-anz-lab%2Fagentic-aiapp-in-a-day","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgithub-insight-anz-lab%2Fagentic-aiapp-in-a-day/lists"}