Using the power of Generative AI at scale
3 likes4,467 views
The document discusses the applications and benefits of generative AI in various industries, emphasizing how businesses can leverage Azure OpenAI services to enhance their operations and engage customers. It highlights multiple use cases across sectors like finance, healthcare, and marketing, illustrating how AI can automate tasks, improve decision-making, and generate personalized content. Additionally, insights from companies like CarMax and Strabag demonstrate the practical impact of AI on efficiency and customer engagement.
![Prompt
Write a tagline for
an ice cream shop.
Prompt
Table customers, columns =
[CustomerId, FirstName,
LastName, Company, Address,
City, State, Country,
PostalCode]
Create a SQL query for all
customers in Texas named Jane
query =
Prompt
A ball of fire with vibrant
colors to show the speed of
innovation at our media and
entertainment company
Response
We serve up smiles
with every scoop!
Response
SELECT *
FROM customers
WHERE State = 'TX' AND
FirstName = 'Jane'
Response
Prompt
I’m having trouble getting
my Xbox to turn on.
Response
There are a few things you
can try to troubleshoot
this issue … …
Prompt
Thanks! That worked. What
games do you recommend for
my 14-year-old?
Response
Here are a few games that you
might consider: …
GPT-3.5 and GPT-4 ChatGPT Codex DALL·E 2](https://image.slidesharecdn.com/maximsalnikov-usinggenerativeaiatscale-230504131527-99eab498/85/Using-the-power-of-Generative-AI-at-scale-9-320.jpg)
Using the power of Generative AI at scale
- 1. Using the power of Generative AI at scale Maxim Salnikov Microsoft
- 2. • Building on web platform since 90s • Organizing developer communities and technical conferences • Speaking, training, blogging: Webdev, Cloud, OpenAI Helping developers to succeed with the Cloud & AI technology [email protected] Let’s connect and chat!
- 3. Of AI used by the enterprises over the past several years Of executives view AI and machine learning as priorities that they should be incorporating into their product lines and businesses
- 4. Redmond WA Montreal QB New York NY Boston MA Cambridge, UK India Beijing, China Shanghai, China Global research centers Researchers employed worldwide AI-related patents AI research papers published To human parity on vision, speech, and language
- 6. ML Platform Customizable AI Models Cognitive Services Scenario-Based Services Applied AI Services Application Platform AI Builder Applications Partner Solutions Power BI Power Apps Power Automate Power Virtual Agents Azure Machine Learning Vision Speech Language Decision Azure OpenAI Service Immersive Reader Form Recognizer Bot Service Video Indexer Metrics Advisor Cognitive Search Developers & Data Scientists Business Users
- 8. Ensure that artificial general intelligence (AGI) benefits humanity Empower every person and organization on the planet to achieve more GPT-3.5 and GPT-4 Text ChatGPT Conversation Codex Code DALL·E 2 Images
- 9. Prompt Write a tagline for an ice cream shop. Prompt Table customers, columns = [CustomerId, FirstName, LastName, Company, Address, City, State, Country, PostalCode] Create a SQL query for all customers in Texas named Jane query = Prompt A ball of fire with vibrant colors to show the speed of innovation at our media and entertainment company Response We serve up smiles with every scoop! Response SELECT * FROM customers WHERE State = 'TX' AND FirstName = 'Jane' Response Prompt I’m having trouble getting my Xbox to turn on. Response There are a few things you can try to troubleshoot this issue … … Prompt Thanks! That worked. What games do you recommend for my 14-year-old? Response Here are a few games that you might consider: … GPT-3.5 and GPT-4 ChatGPT Codex DALL·E 2
- 10. GPT-3.5 & 4 (preview) ChatGPT (preview) Codex DALL·E 2 (preview)
- 11. Fairness
- 12. Azure OpenAI Content generation Call center analytics: automatically generate responses to customer inquiries Generate personalized UI for your website Summarization Call center analytics: summary of customer support conversation logs Subject matter expert document: summarization (e.g. Financial reporting, analyst articles) Social media trends summarization Code generation Convert natural language to SQL (or vice versa) for telemetry data Convert natural language to query proprietary data models Code documentation Semantic search Search reviews for a specific product/service Information discovery and knowledge mining
- 13. Azure OpenAI Finance Automatically generate financial summaries Create natural language responses for financial queries IT Convert natural language to SQL (or vice versa) for telemetry data Convert natural language to query proprietary data models Auto generate code documentation Human resources Automate recruitment process by screening resumes and identifying the most qualified candidates Analyze employee sentiment (e.g., email, etc) providing insights into company culture Automate routine tasks during the onboarding process, such as sending welcome emails and scheduling orientation sessions Marketing Generate idea for content across different formats (blog posts, articles, videos, and social media) Copywriting: generate ideas, creating outlines, and writing dialogue and product descriptions Create personalized and targeted email campaigns to promote products or services to a specific audience
- 14. Azure OpenAI Finance Intelligent Compliance & Risk Management Retail Healthcare Personalised Customer Care Cost Savings through Optimised Engagement Innovation w/ Better / Alternative Treatment Comms & Media Hyper-personalisation Innovative Content Creation Intelligent Contact Center Personalised Customer Care Cost Savings through Optimised Engagement Hyper-personalisation Innovative Marketing and Campaigning Intelligent Contact Center
- 15. Example Discovery/ exploration Virtual agents communicate in clear, conversational language in customer’s native tongue Customers get detailed answers to policy and brand inquiries in human language After customer calls, agents receive automatically generated notes, recommendations, and call highlights Agent can use auto generated emails to expeditiously follow up and close sales Agent can use auto generated visuals to craft customized offers and marketing material Buying/using Following purchase, customer gets automated and hyper-personalized onboarding docs Customers can easily understand what they have bought as complex contract language is presented in lay terms Customer can initiate claims digitally (Digital FNOL) using non-technical terms Prior to customer appts, agents can generate script to drive conversation, based on customer profile and conversation history Agent can auto generate emails and replies in Outlook to collect/inform customers on important issues like claims Asking In chat, insurer provides an expanded knowledge base to answer customer inquiries Agents can automate follow up activities and track, measure, and evaluate the inquiries they receive Agents/reps can retrieve knowledge base responses to customer queries in lay terms Engaging During milestones, outreach to customer is automated and relevant to their risk aversion and protection needs Alert agents on important events (birthdays, weddings) and generate automated emails to drive engagement Scale Customer Agent
- 16. CarMax produced 11 years' worth of car summaries in a matter of months. Using Azure OpenAI Service reduces their marketing freelancer spend. It also enables them to provide new information to their customers faster than their competitors. “With Azure OpenAI Service, we are able to create content that empowers our customers so they can be informed before they make a decision,” ‒ Shamim Mohammad, CarMax executive vice president and chief information and technology officer. “ “Azure OpenAI Service is definitely playing a big part in our SEO improvement.” ‒ Sean Goetz, Director, Application Systems
- 17. Strabag SE builds a risk management solution to improve efficiency Challenge Strabag specializes in construction and related services. The company was seeking a solution to centralize and better leverage their data in order to optimize their operations. Solution With Microsoft’s Intelligent Data Platform serving as the foundation of Strabag’s Data Science Hub, they were able to leverage Azure OpenAI Service to create a solution that allows it to assess the potential impacts of a project in its earliest stages by comparing it against all its realized projects – therefore minimizing the risks. “With this solution, enabled by Azure OpenAI Service, we know when the weather will prevent us using a crane on-site. Moreover, by the aid of Generative Design our real estate development unit knows with a few clicks how much maximum gross floor area they can develop on a site. This kind of information is vital when you have projects worth two million euros with a margin of 4-5%.” Manufacturing Austria Corporate (10,000+ employees)
- 18. The solution to the size and fit problem is knowing the personal preferences of your customers on each item-model-level
- 19. • Skjold.ai protects all traffic • Check suspicious messages • Cybercrime is growing • Criminals adopt new technology • Instant feedback if the messages is considered safe or could be fraud • Explain red flags and educate the user • Integrated in the iPhone SMS app • Available for iPhone and Android AI-powered scan of suspicious messages Read more www.skjold.ai/demo Mobile first protection against cyber crime built with Azure OpenAI
- 21. 1. A secret step (on the last slide) 2. Request access by submitting a form on azure.microsoft.com 3. Send your first request to Completions API 4. Experiment with models, prompts, parameters 5. Try different options to use your own data 6. Build a product and share with the world! 🎉
- 22. Prompt—Text input that provides some context to the engine on what is expecting. Completion—Output that GPT-3 generates based on the prompt. some context Token — partial or full words processed and produced by the GPT models
- 23. “Classic” GPT-3 models Previous models were text-in and text-out (i.e., they accepted a prompt string and returned a completion to append to the prompt). Answer questions from the context below. Context: A neutron star is the collapsed core of a massive supergiant star, which had a total mass of between 10 and 25 solar masses, possibly more if the star was especially metal-rich. Q: What is a neutron star? A: The ChatGPT model The ChatGPT model is conversation-in and message-out. (i.e., it expects a prompt string that is formatted in a specific chat- like transcript format and returns a completion that represents a model-written message in the chat) <|im_start|>system Assistant is an AI Chatbot designed to answer questions from the context provided below. Context: A neutron star is the collapsed core of a massive supergiant star, which had a total mass of between 10 and 25 solar masses, possibly more if the star was especially metal-rich. <|im_end|> <|im_start|>user What is a neutron star? <|im_end|> <|im_start|>assistant
- 24. Context Write a tagline for our ice cream shop. Prompt Response Scoops of heaven in the heart of Phoenix! ## This is a conversational agent whose code name is Dana: - Dana is a conversational agent at Gourmet Ice Cream, Inc. - Gourmet Ice Cream’s marketing team uses Dana to help them be more effective at their jobs. - Dana understands Gourmet Ice Cream’s unique product catalog, store locations, and the company’s strategic goal to continue to go upmarket ## On safety: - Dana should moderate the responses to be safe, free of harm and non-controversial. ## On Dana’s ability to gather and present information: - Dana’s responses connect to the Product Catalog DB, Store Locator DB, and Microsoft 365 it has access to through the Microsoft Cloud, providing great CONTEXT ## On Dana’s profile and general capabilities: - Dana’s responses should be informational and logical - Dana’s logic and reasoning should be rigorous, intelligent and defensible
- 25. Extract precise answers from your unstructured documents with Azure OpenAI + Cognitive Search: article + repo
- 26. 1. Give clearer instructions 2. Split complex tasks into simpler subtasks 3. Structure the instruction to keep the model on task 4. Prompt the model to explain before answering 5. Ask for justifications of many possible answers, and then synthesize 6. Generate many outputs, and then use the model to pick the best one 7. Fine-tune custom models to maximize performance
- 28. Fine-Tuning Domain Data Small Set of Labeled Data • minimum of several thousand examples • Maximum of 2.5M tokens or 80-100mb size Fine-Tuned GPT-3 Model Perform any domain-specific NLP tasks Model parameters adjusted (Weights and Bias) Gradient Update high-dimensional vector space (Embeddings) GPT-3 Fine-tuning • Higher quality results than prompt design • Ability to train on more examples than can fit in a prompt • Token savings due to shorter prompts • Lower latency requests
- 30. ◉ Learn more in the Azure OpenAI WorkshopI ◉ See examples in the Open AI Cookbook ◉ Start experimenting and developing your MVP ◉ Get support and help ◉ How-to guides: Generate embeddings and Fine-tune ◉ Complete embeddings and document search tutorial. ◉ How your/your customer data is processed, used and stored in Azure OpenAI: Data, privacy and security ◉ Review the Enterprise Data with ChatGPT tech blog, and work through the accompanying GitHub repository. ◉ Become familiar with the APIs ◉ Understand “What is Azure OpenAI?”: compare Azure OpenAI and OpenAI. Review key concepts. ◉ Work through Introduction to Azure OpenAI Service training module ◉ Explore key Responsible AI guidelines and principles ◉ Create an Azure subscription ◉ Apply for access to the Azure OpenAI Service: https://aka.ms/oai/access ) ◉ Watch the video: An Introduction to Azure OpenAI ◉ Get Familiarized with the product content: Azure OpenAI Page ◉ Review how other customers are using Azure AI
- 31. [email protected] Let’s connect and chat!