Slide 1

Slide 1 text

Community Days NYC 2024 Keynote Copiloting Your Developer Journey with Azure AI Nitya Narasimhan, PhD Senior AI Advocate, Microsoft @nitya | #in/nityan

Slide 2

Slide 2 text

Hi, I’m Nitya! PhD & Polyglot (Mobile · Web · Cloud · AI) Research & Development (25+ years) Community & Education (15+ years) Illustrator & Storyteller (10+ years) Cloud Advocacy & Microsoft (5+ years) @nitya | #in/nityan | github/nitya

Slide 3

Slide 3 text

I’m Developer 0 For Azure AI Product Feedback (Focus on Developer Experience) Content Creation (Focus on Developer Education) Sample Creation (Focus on Developer Productivity) Community Interactions (Focus on Developers) @nitya | #in/nityan | github/nitya Join the Azure AI Discord

Slide 4

Slide 4 text

How do you see yourself? AI Beginner (How to I skill up on AI fundamentals!) Low-Code Dev (How do I get productive with AI?) Pro-Dev (How can I get control over e2e workflows?) Entrepreneur (How can I prototype my idea quickly?) We’re All On A Journey! @nitya | #in/nityan | github/nitya

Slide 5

Slide 5 text

Keeping up with Tech is .. Challenging https://aka.ms/bookofnews

Slide 6

Slide 6 text

Can I help you to see the big picture? @SketchTheDocs

Slide 7

Slide 7 text

I love to share my insights in Generative AI Responsible AI Agentic AI Careers

Slide 8

Slide 8 text

I love to build & empower local communities .. https://meetup.com/aide-hub

Slide 9

Slide 9 text

Join me on my AI Adventure! Copiloting Your Developer Journey With Azure AI 1 | Generative AI – Prompt Engineering 2 | LLM Ops– From Prompt To Production 3 | Copilot Stack - Developer Tools & Workflow 4 | Contoso Chat – Retail Copilot OSS Sample 5 | Responsible AI – From Evaluation to Safety| 6 | Agentic AI – From Assistants to AutoGen 7 | Hugging Face – From Open Source to Ops 8 | Resources – Discord, Collections & More

Slide 10

Slide 10 text

Generative AI = How Prompts Work PROMPT user request received as a text input Open AI GPT-3.5-turbo RESPONSE generated content returned as user response LANGUAGE MODEL 4097 Tokens Trained to Sep 2021 | Demo – Open AI Tokenizer

Slide 11

Slide 11 text

Generative AI = What Prompts Do PROMPT user request received as a text input Open AI GPT-3.5-turbo RESPONSE generated content returned as user response LANGUAGE MODEL 4097 Tokens Trained to Sep 2021 | Demo – Hugging Chat (Elementary)

Slide 12

Slide 12 text

Generative AI = What Prompts Do PROMPT user request received as a text input Open AI GPT-3.5-turbo RESPONSE generated content returned as user response LANGUAGE MODEL 4097 Tokens Trained to Sep 2021 | Demo – Hugging Spaces (AI Comics)

Slide 13

Slide 13 text

Prompt Engineering = Make it Better! Large Language Model Model Parameters System Context USER PROMPT CHAT HISTORY MODEL PROMPT MODEL RESPONSE PROMPT ENGINEERING VARIABLES RAG DATA PROMPT TEMPLATE | Demo – Open AI (Fine Tuning)

Slide 14

Slide 14 text

Generative AI For Beginners – Chapter 4 | https://aka.ms/genai-beginners

Slide 15

Slide 15 text

Generative AI For Beginners – Chapter 18 | https://aka.ms/genai-beginners

Slide 16

Slide 16 text

Challenge: Grounding Responses In My Data Large Language Model Model Parameters System Context USER PROMPT CHAT HISTORY MODEL PROMPT MODEL RESPONSE PROMPT ENGINEERING VARIABLES RAG DATA PROMPT TEMPLATE | Demo – Hugging Chat (“Hiking Shoes”)

Slide 17

Slide 17 text

Copilot Stack: Microsoft Runs on Azure AI | Demo – Azure AI Models Hub

Slide 18

Slide 18 text

Contoso Chat: A RAG-based Retail Copilot Contoso Web: Frontend A web app for user interactions. It is a client for the chat AI API. Contoso Chat: Backend A generative AI app that takes user query & returns response

Slide 19

Slide 19 text

Experience: Grounded, Personalized, Responsible AI • Grounded in Your Data. Ask a question, verify that answer uses product data. • Validate the Copilot. Ask a question and verify that you get an answer. • Personalized to User. Ask a question, verify if answer uses purchase history. • Default Safety Checks. Try simple jailbreaking to modify rules. It should fail. | Demo – Contoso Chat (“Chat UI”)

Slide 20

Slide 20 text

Architecture: Retrieval Augmented Generation

Slide 21

Slide 21 text

App Lifecycle E2E: Prompt Engineering to LLM Ops

Slide 22

Slide 22 text

Code-First Platform: Azure AI Studio (SDK & Portal)

Slide 23

Slide 23 text

Workshop: { Build – Evaluate – Deploy – Use }

Slide 24

Slide 24 text

| Try It Out!  Pre-Reqs: GitHub, Azure, AOAI, Quota  Visit - https://aka.ms/aitour/contoso-chat  Fork it – uncheck box so you get branches  Launch Codespaces – wait till it is ready  Validate setup – azd version  Authenticate – azd auth login  Provision & Deploy – azd up

Slide 25

Slide 25 text

https://prompty.ai  “Agency with Observability”  New asset class – versionable, actionable  Specification – language agnostic templates  Tooling – developer experience (IDE as playground)  Runtime – engine agnostic execution “It just works” with Azure AI Studio | Demo – Prompty Extension (“Playground In Your IDE”)

Slide 26

Slide 26 text

| Demo – Flex Flow (“Bring Your Own Framework or Code”) https://aka.ms/promptflow

Slide 27

Slide 27 text

https://aka.ms/ai-studio/intelligent-apps | 5-part Blog Series Responsible AI: Evaluation Flows & Safety Filters

Slide 28

Slide 28 text

| Demo – AZD Template Gallery https://aka.ms/ai-studio/azd-templates

Slide 29

Slide 29 text

If Time Permits 1 | Generative AI – Prompt Engineering 2 | LLM Ops– From Prompt To Production ( 3 | Copilot Stack - Developer Tools & Workflow 4 | Contoso Chat – Retail Copilot OSS Sample 5 | Responsible AI – From Evaluation to Safety| 6 | Agentic AI – From Assistants to AutoGen 7 | Hugging Face – From Open Source to Ops 8 | Resources – Discord, Collections & More See Microsoft Build Session For More Details

Slide 30

Slide 30 text

Building Generative AI Solutions Can be .. Challenging Large Language Models for rich multi-media content generation Conversational Interactions driven by natural language processing capabilities End-to-End Workflows from prompt-engineering to operationalization Chat-based experiences require human guidance (prompts) and intervention (instructions) to execute complex tasks, creating challenges in workflow automation and optimization

Slide 31

Slide 31 text

Agentic AI Application Development Can Help Autonomous Agents capable of planning & executing decisions Task Execution Tools identify and execute the right tools for each task Conversational Workflows coordinate actions across agents, user, environment Agentic AI Applications use autonomous agents to execute tasks on behalf of users, interacting with their environment or remote services as needed, and coordinating actions with other agents for efficiency

Slide 32

Slide 32 text

Building Agentic AI requires new tools & mindset Conversational Agents configurable (LLM) customizable (prompt) chainable (planning) Execution Workflows infer required skill execute relevant tool behave responsibly Conversational Patterns agent-human agent-environment agent-agent Traditional Agentic Application Frameworks are not versed in natural language. We need conversational design patterns and intelligent task inference and execution for generative AI usage scenarios

Slide 33

Slide 33 text

AutoGen Framework: Multi-Agent Collaboration Open-Source Framework & Samples Docs: https://aka.ms/autogen/website Discord: https://aka.ms/autogen/discord Customizable Conversable Agents, LLMs Research-Driven Tools & Patterns No-Code and Code-First Development

Slide 34

Slide 34 text

AutoGen Studio: Get Started With Low-Code UI/UX Define Skills Create reusable functions, tools Docs: https://microsoft.github.io/autogen/blog/2023/12/01/AutoGenStudio/ Define Models Define & configure required LLMs Define Workflows Create agents, multi-agent conversations Create Sessions Test and validate agent workflows Define Agents Configure LLM, skills, behaviors Publish Sessions Share sessions to a gallery to revisit

Slide 35

Slide 35 text

Your Turn! 1 | Generative AI – Prompt Engineering 2 | LLM Ops– From Prompt To Production ( 3 | Copilot Stack - Developer Tools & Workflow 4 | Contoso Chat – Retail Copilot OSS Sample 5 | Responsible AI – From Evaluation to Safety| 6 | Agentic AI – From Assistants to AutoGen 7 | Hugging Face – From Open Source to Ops 8 | Resources – Discord, Collections & More Look For Slides Soon!

Slide 36

Slide 36 text

Join The Discord 1 | https://aka.ms/genai-beginners 2 | https://aka.ms/ai-studio/collection 3 | https://aka.ms/rai-hub/collection 4 | https://aka.ms/aitour/contoso-chat 5 | https://aka.ms/ai-studio/intelligent-apps 6 | https://aka.ms/ai-studio/code-first-blog 7 | https://aka.ms/ai-studio/azd-templates 8 | Find Me – @nitya #in/nityan github/nitya Look For Slides Soon!

Slide 37

Slide 37 text

© Copyright Microsoft Corporation. All rights reserved. Thank You!