Гинисов Рекорд

• Use AI to simplify your daily tasks and make your life easier
• Get set up with Microsoft Copilot to try some of the example prompts

Understand the basics of generative AI

• Create new unique content (not just analyze data or make predictions)
  • Large Language Models (LLMs)
  • Natural Language Processing (NLP)

Smart assistant to help with everyday tasks

• Everyday use cases (examples, no prompt samples yet)
  • Creative writing and content creation
  • Organizing and planning (plan a trip, create meal plan)
  • Personal assistance
  • Etc.
• [TIP] AI Agents – your intelligent virtual assistant
  • What are agents
  • What to agents do
  • Link to further learning

Use AI responsibly and effectively (Importance of ethical considerations and guidelines for responsible use)

• Ensure transparency and accountability
• Address potential biases (top 3-5 common biases with real-life examples)
• Responsible prompting

• Understand prompting basics
  • Write effective prompts- examples of good, better, and best prompts
• Identify easy opportunities to try AI
• Prompting examples to try
  • Prompting Example: Ask Copilot to draft a simple email for you. Try saying, 'Copilot, write an email to my friend about our weekend plans.'
  • Prompting example: Ask Copilot “Help me create a study plan for the next month that helps me gain the skill [enter skill]
  • Prompting Example: Ask Copilot to help you create a podcast. Try saying "I'm thinking about starting a personal podcast. Can you help me brainstorm a month's worth of episode ideas centered around [technology, culture, and personal development]? Each episode should cover a unique topic that would intrigue listeners." Then iterate with “For each episode idea, provide a catchy title and a brief outline of key discussion points."
  • TIP: Commit to your daily experiment: Build a microhabitat, one prompt you’ll try every day and iterate as needed.

• Personalize fill-in-the-blank prompts with goals / timelines / topics / specifics in Copilot
• Use Think Deeper to expand on the prompt results.

Identify useful prompting resources

• Copilot Prompt Gallery walk through some examples
• Do More with AI | Microsoft Copilot
  • Plan the Perfect Trip Itinerary Using Copilot | Microsoft Copilot
  • Train for a Marathon with Copilot | Microsoft Copilot
• Copilot Scenario library

Use different AI tools to prompt and build on results (flows) using example from library as a walkthrough

https://adoption.microsoft.com/en-us/copilot-scenario-library/ existing prompts by functions, roles.

Example walkthrough

• Recap of key points
• Sign up for 50-day challenge
• Further learning/resources
• Link to Guinness attestation/badging?

• Overview of GitHub Copilot Extensions and agents and their role in the software development life cycle
• How GitHub Copilot supports AI pair programming
• Examples of GitHub Copilot Extensions and agents in real-world development workflows

• Explain how Copilot Extensions differ from standard Copilot suggestions
• Copilot Extensions provide context-aware, task-specific guidance rather than just inline code suggestions
• GitHub Copilot Extensions expand Copilot Chat's functionality by enabling integration with external tools and services. These extensions can perform various tasks such as:
  1. Querying third-party documentation services
  2. Providing AI-assisted coding through third-party models
  3. Retrieving data from external services
  4. Executing specific actions in external systems
• Importantly, GitHub Copilot Extensions are powered by GitHub Copilot Agents, which serve as the underlying extensibility platform. Copilot agents are custom tools embedded in Copilot Extensions. They integrate with Copilot Chat to provide additional functionalities tailored to specific needs.Copilot Agents provide:
  • The ability to integrate external services and APIs into Copilot Chat
  • Support for complex integrations requiring full control over request processing
  • Flexibility to implement custom logic
  • Integration capabilities with other LLMs and the Copilot API
  • Management of conversation context
  • Complete control over user interaction handling
  • While Agents require more engineering effort and ongoing maintenance, they provide the robust foundation needed to support Copilot Extensions and enable sophisticated workflows with maximum flexibility.

• Components of a Copilot Agent:
  • Actions: Define what tasks the agent can perform
  • Directives: Instructions given to guide the agent’s behavior
  • Tools: APIs or external integrations that extend functionality
  • Explain how Copilot Agents leverage context (e.g., open files, repository data, user prompts)
  • Describe how to create a Copilot Agent using Copilot Extensions
  • Understanding API/SDK usage for extending Copilot

GitHub Extensions use cases when you want to expand the functionality of GitHub Copilot Chat in the following way.

• Querying third-party documentation services
• Providing AI-assisted coding through third-party models
• Retrieving data from external services
• Executing specific actions in external systems

• Guide learners through setting up a Copilot extension
• Implement a basic Copilot extension with defined actions and directives
• Showcase how to test the agent’s responses and refine its functionality

• In this hands-on GitHub Skills exercise, participants will build a GitHub Copilot extension for a practical developer workflow. Learners will:
  1. Start a pre-configured development environment with required tools.
  2. Configure a web service in python or javascript to support your Copilot extension.
  3. Create a GitHub App and configure it to use with Copilot.
  4. Add custom abilities to make your extension unique.
  5. Try your extensions on real github.com and in VS Code.
  6. Optionally deploy your service to Azure and publish to the Copilot extensions marketplace.

• Potential extension abilities (pending):
  1. Code Reviewer – Create an extension that includes private documentation to help analyze pull requests, identify bugs, and suggest improvements.
  2. Refactor – Build an extension that uses your company’s standards to reliably refactor legacy code into your current tech stack.
  3. Domain Knowledge – Build an extension that incorporates your industry’s nomenclature, lingo, and domain knowledge to create product specific features.
  4. Personality – Does your company have a unique personality? Or do you love easter eggs, emoji, and inside jokes? Customize Copilot to fit your company’s culture.
  5. Gamification – Encourage your users to grow by offering challenges related to recent prompts.
  6. Personal Library - Do you keep a classic snippets repo or love Gists? Create a copilot extension to surface them at the right moments.
  7. Documentation Generator – Develop an extension to extract function metadata and auto-generates structured documentation.
  8. Issue Triage Assistant – Build an extension to scan GitHub issues, categorize them with relevant labels, and suggest resolutions based on past issues.

• Multiple-choice and scenario-based questions to reinforce learning objectives

• Recap of key points
• Sign up for 50-day challenge
• Further learning/resources
• Link to Guinness attestation/badging?