Arcade Chatbot: Interactive Generative AI Leader Revision - arc138-genai
Overview
In this lab you will learn the fundamentals of prompt engineering using Generative AI and Google Cloud. During the lab you will have access to a chatbot that will act as a Google Cloud exam revision knowledge agent
.
If you are new to Generative AI or looking for an overview of how to get started, you are in the right place. Read on to learn about the specifics of this lab and areas that you will get hands-on practice with.
In this lab learn use a chat application to interact and learn:
The basics of prompt engineering
Why context in relation to AI is important
How to work with Generative AI
Prerequisites
Over the course of this lab the following elements are required:
Vertex AI
Generative AI models
Task 1. Access the Chat Application
Open the genai-chatbot-702066707285.us-east1.run.app
to gain access to the lab chat application.
Note: The chat bot link works in both a normal browser tab and an incognito window. An initial loading screen will appear while the lab data is being prepared.
From here you will be able to interact with a Generative AI model during the course of this lab.
Note: The above image is the main chat screen. The chat screen includes multiple personas reflecting different knowledge domains. Each persona has specific but limited abilities to demonstrate the functionality of generative ai on a defined topic.
The lab mimics a chat application interface to provide access to a generative ai model. Select a persona from the contacts list to initiate a discussion on a specified topic.
Note: The application uses a simplified version of the Gemini Flash model. In this demo, each query is distinct and therefore, the user must input the full context per query.
The application allows the user to perform interactions with the generative ai from Google Cloud. From here you will be able to sample the power of generative ai in a scenario reflecting real-world usage.
Task 2. Using Prompt Engineering
In this lab we will interact with a Generative AI model to discuss Google Cloud Generative AI Leader
. Don't worry, if you don't know much about this, use it as a learning exercise.
Generative AI is a type of artificial intelligence that can be used to create new information, such as text, images, or music. This makes it a powerful tool for learning about Google Cloud Generative AI Leader
, as it can be used to generate realistic new content.
Generative AI can be used in competitive activities in a number of ways, including:
Generating new training routines: Generative AI can be used to generate new training routines for participants. This could be done by providing the AI with a set of parameters, such as the desired skill to be trained, the level of difficulty, and the number of participants involved. The AI could then generate a routine that meets these requirements.
Creating new strategic approaches: Generative AI can be used to create new strategic approaches for teams or individuals. This could be done by providing the AI with a set of parameters, such as the strengths and weaknesses of the team/individual, the strengths and weaknesses of the opponents, and the desired outcome. The AI could then generate a strategy that meets these requirements.
Improving existing strategic approaches: Generative AI can be used to improve existing strategic approaches for teams or individuals. This could be done by providing the AI with a set of parameters, such as the desired outcome, the strengths and weaknesses of the team/individual, and the strengths and weaknesses of the opponents. The AI could then generate suggestions for how to improve the strategy.
Personalizing the training experience: Generative AI can be used to personalize the training experience for participants. This could be done by providing the AI with a set of parameters, such as the participant's skill level, strengths and weaknesses, and desired areas of improvement. The AI could then generate a personalized training plan for the participant.
Here are some examples of how generative AI is being used in competitive environments today:
Professional organizations are using generative AI to develop new training routines for their participants. The AI is being used to generate routines that are tailored to the individual needs of each participant.
Competitive teams are using generative AI to create new strategic approaches. The AI is being used to generate strategies that are based on the strengths and weaknesses of the team and the opposing teams/individuals.
Organizations are using generative AI to improve their existing strategic approaches. The AI is being used to generate suggestions for how to improve their offense and defense.
Training facilities are using generative AI to personalize the training experience for their participants. The AI is being used to generate personalized training plans for each participant based on their individual needs.
Overall, generative AI has the potential to revolutionize competitive activities. By generating new training routines, creating new strategic approaches, improving existing strategic approaches, and personalizing the training experience, generative AI can help participants to train more effectively, compete more intelligently, and achieve better results.
Task 3. Context is Key
Generative AI Chat Bot needs context to answer questions. In the demo lab bot we have taken away some of its smarts to show the importance of context.
In the application we can put our questions to the AI model. To start, let's establish some basics around the importance of context relating to crafting questions.
- Click on the
Mary
persona
Note: Clicking on the chatbot persona will open the chat interface. From this interface you can interact with the generative ai model.
- Start by saying hello to the chat bot, enter the following text
Hello what is your name?
Note: The chatbot will respond to this initial interaction with a helpful message to let you know it's ready to interact with you.
- Let's start by asking a broad question to the AI
What can you tell me about Google Cloud Generative AI Leader?
- Let's try a more specific question
Who is Mary?
- Let's try to test the chatbots breadth of knowledge
What can you tell me about Implement explainable gen Al policies.?
Amazingly, we have just set the context for our Google Cloud Generative AI Leader
journey. The Generative AI model has knowledge on lots of subjects. Here we are interested in finding out more about Google Cloud Generative AI Leader
.
Task 4. Improving Google Cloud Generative AI Leader
knowledge
Now that we have learned the basics, let's improve our knowledge of Google Cloud Generative AI Leader
.
Note: Remember generative ai models are based on data taken from a point in time. The models need to be continually generated when working with time based information.
In the following section, we use Generative AI to create questions. Pay attention, you will be tested on these later in the lab!
- Can you use the chatbot to answer the following question?
A human resources department deploys a generative Al (gen Al) model to screen job applications and provide a shortlist of candidates to recruiters. Recruiters notice that some seemingly qualified candidates are consistently being overlooked, but the Al provides no explanation for its rankings or exclusions. The company needs to address this lack of transparency. What should they do?
- Can you use the chatbot to answer the following question?
A company is evaluating the use of large language models (LLMs) to enhance its operations and customer interactions. What is a primary characteristic of LLMs?
- Can you use the chatbot to answer the following question?
An Al robot learns optimal package delivery routes in a city. It receives positive scores for fast, successful deliveries and negative scores for delays or failures. Through this feedback, the robot improves its navigation over time. What type of machine learning is being used to train the robot?
- Can you use the chatbot to answer the following question?
A company wants to use generative Al (gen Al) to automate complex workflows and improve decision-making across its various departments. They are considering implementing Al agents as a key component of their strategy. What is the primary function of an Al agent in a gen Al system?
Note: Want to learn more? Ask the chatbot more questions and see if it can help.
Great, it looks like you really know your stuff. Let's move onto the final assessment.
Task 5. Taking the Assessment
Finally, answer the assessment question based on Google Cloud Generative AI Leader
.
Note: The lab assessment is accessed using the bottom navigation bar. Click on the Assess option to move to this screen. Answer correctly to pass the assessment. Once done, you can return from the chatbot application to the lab interface.
Click on the assess bottom navigation button to reveal the lab question. Select the correct answer to successfully complete the lab.
To successfully complete the lab assessment, each question presented must be answered correctly.
Note: The lab assessment is accessed using the bottom navigation bar. Click on the Assess option to move to this screen. Answer correctly to pass the assessment. Once done, you can return from the chatbot application to the lab interface.
Click Check my progress to verify the objective.
Assess my progress
Check my progress
Solution of Lab