糖心传媒

After logging into your 糖心传媒 account, you can access the tools through the following web addresses:

You can also access these tools by clicking the Google Apps button in the upper right-hand corner of your 糖心传媒 Gmail account. Your 糖心传媒 account should be visible in the upper-right corner upon opening NotebookLM.

By using your 糖心传媒 account, you can ensure that your data will not be used to train Google's AI models. 

Note: The features available in the Google Gemini App and NotebookLM are frequently changing and may vary from those described here. Generally speaking, they can create results as text, image, audio or even code. For more tips on writing prompts, please review 糖心传媒鈥檚 and Google's .

You are responsible for ensuring that any information you enter or attach is suitable for use with Google's AI tools and complies with 糖心传媒 policy and legislation. With these tools, you can:

• Find writing support: Get feedback or help adjust the tone, clarity, and length: 鈥淗ow can I improve the following passage? Make it shorter and more persuasive.鈥�
• Create summaries: Summarize an existing document for a particular audience: 鈥淐ollect the key points in the attached document in a bulleted list, making them appealing to post-secondary students.鈥�
• Repurpose content: 鈥淩ecreate the main points of the attached document as a blog post/podcast script/website.鈥�
• Generate ideas: 鈥淲hat are some common questions about (topic)?鈥�
• Write code: 鈥淐reate a Javascript function that sorts an array in ascending numerical order.鈥�
• Explore topics: 鈥淧rovide sources that are in favour of and against (topic)鈥�. Keep in mind that Gemini , so it is best used as a starting point for finding sources and ways of writing about a topic.

Both the Gemini App and NotebookLM belong to the Google Gemini family and use the same Google LLM models. However, they are designed for different purposes or tasks, and therefore there are differences in terms of their features.

On a high level, here are the differences and best ways to use either Gemini App or NotebookLM:

** Please note that the Gemini App and NotebookLM available at 糖心传媒 are not the same as the consumer versions.

There are many ways you can use Google's AI tools to improve the accessibility of your communications and work. 

You are responsible for ensuring that any information you enter or attach is and complies with 糖心传媒 policy and legislation. Here are some examples of how to use these tools to improve the accessibility of your work:

• Plain language writing: 鈥淢ake this clearer by using active voice and plain language.鈥�
• Alternative text help: Get help writing alt text descriptions for images for people who are blind or have low vision and use assistive technology. Upload your image with the prompt: 鈥淧rovide alt text for this image.鈥� Provide additional context in the prompt to improve the accuracy of the alt text. 
• Captions for charts and visualizations: 鈥淪uggest a way to describe this chart for someone who is blind or has low vision and uses a screen reader" or 鈥減rovide a general summary or trend in the data.鈥� 
• Heading outline: Get help generating a good heading structure: 鈥淏reak up this content into sections using meaningful and succinct headings.鈥�

Activity history and Gems in the Gemini App

The "Activities" section in the Gemini App shows your full prompt history for three (3) months, after which the activities are deleted. This includes prompts, attached files, instructions and responses from Gemini. 

The version of Gemini available to 糖心传媒 users does not allow the deletion of your prior activities. By default, your Gemini Apps activity is set to "on" and cannot be disabled. All of your Gemini activities, including the files you attach to prompts, are retained in the "Activities" section of the app. 

Gems鈥搘hich comprise instructions and attached resources that are saved for ongoing use鈥揷an be deleted at any time. The prompts and responses that utilize a Gem are considered "Activities" and are deleted after three (3) months.

Chat history, sources and studio in NotebookLM

Individuals can delete their chat history at any time in NotebookLM. Keep in mind that even though your notebooks may be shared, the chat history is private to the individual and cannot be viewed by others. It may be beneficial to delete the chat history if you no longer want the notebook to use that history in its responses.

Similarly, the sources attached to a notebook and the resources saved in the "Studio" section of a notebook can be deleted at any time by any member of the notebook with sufficient privileges. Please note that this will remove the item from all members of the notebook.

When accessing the Gemini App or NotebookLM using your 糖心传媒 account, your data is not used or human-reviewed to improve AI models. This feature is covered by the . 

Keep in mind that access to a Google Gemini or NotebookLM account outside of 糖心传媒 does not fall under these terms of service and therefore any data you enter in an account outside of 糖心传媒 is subject to review or could be used to improve their AI models.

We recommend that you always confirm you are accessing Gemini or NotebookLM from your 糖心传媒 account each time you begin a new prompt by clicking your profile picture in the top-right corner. You鈥檒l want this to show your @torontomu.ca email address instead of your personal one. By using your 糖心传媒 account, you can ensure that your data will not be used to train Google's AI models. 

Prior to the release of the Gemini App and NotebookLM at 糖心传媒, we conducted privacy and AI impact assessments with the Office of the General Counsel and Board Secretariat, and a security risk assessment with the Office of the Chief Information Security Officer.

Although your activities in the Gemini App and NotebookLM are not public, 糖心传媒's Google administrators in Computing and Communications Services (CCS) can view prompt histories in the Gemini App, but not in NotebookLM. Our administrators cannot access any files you upload to either Gemini or NotebookLM. For more on how the university鈥檚 technologies are monitored, please visit 糖心传媒's Student Computing Guidelines under the "Privacy" section (for students) and 糖心传媒鈥檚 Electronic Monitoring Policy (for employees).

Each person is responsible for ensuring they don't share inappropriate information with 糖心传媒's Google AI tools.

• Only public or low-sensitivity information should be input to these tools. Sensitive and confidential information should never be used in prompts, uploaded files or other activities. For help defining what is considered sensitive information, please review 糖心传媒鈥檚 Information Classification Standard and Handling Guidelines.
• Do not upload, input or share any personal information about yourself or any 糖心传媒 student, faculty or staff member into Google's AI tools. Examples of personal information include any data that is personally identifiable such as protected health information, social insurance numbers, student/staff numbers, birthdates, credit card data, etc. Failure to abide by this guidance may result in a privacy breach and/or non-compliance with privacy legislation.
• It isn't appropriate to share copyrighted information nor the intellectual property of others with Google's AI tools, including your students' work and resources provided through the 糖心传媒 Libraries.
• Have a discussion with your leadership around the types of information relevant to your work that may or may not be appropriate to share.
• Students should refer to their course instructors for guidance on the use of AI tools in their courses. Certain uses are prohibited by Policy 60: Academic Integrity.

Please review the Privacy and Access to Information Policy, consult with the Privacy office at privacy@torontomu.ca or report any concerns or incidents through the Privacy Incident Management Process.

Gemini and NotebookLM should be used as temporary working spaces for generating ideas and analyzing information rather than permanent storage for your important documents. This is because the Gemini App automatically deletes your activity history, including your questions and the AI's responses, after only three (3) months. 

Furthermore, in NotebookLM, ownership of a notebook cannot be transferred to another user; if the person who created the notebook leaves the university and their account is deleted, the entire notebook and its contents are permanently lost. 

To ensure you do not lose your work, you should export any useful results into a long-term storage solution, such as a document in your Google Drive. For collaborative team resources, it is best to store these final materials in a Google Shared Drive to ensure the whole group maintains access regardless of individual account changes.

Advice for exporting and saving your results can be found in this page in the Using the Gemini App and Using NotebookLM sections.

Please discuss the potential for the use of Google Gemini, NotebookLM and other generative AI tools with your leadership to determine if they are right for your work. 

We recommend that each school or department review the Responsible Use of Generative AI page to familiarize yourself with the benefits, drawbacks and responsibilities of using Generative AI tools.

GenAI systems are not the same as search engines; each prompt requires the system to process and generate an entirely new response. This makes Gemini and NotebookLM good options when working with complex questions, creative tasks and conversational interactions to improve productivity.

Search engines are effective tools to find specific information and browsing sources to identify reliable resources.

At its core, Gemini is a tool that generates responses based on prompts that you provide. The prompts and responses may include different and multiple formats, including text, documents, images and code, all within one window. Find out more about how to .

Gemini includes various models and modes, allowing you to interact with the tool in different ways based on your needs, some of which are: 

• Generative AI chat: Share a prompt and optional attachment and Gemini will generate a text or image response based on what you provide.
• Gems: Save a custom chat for reuse, containing the instructions and resources it needs to respond to prompts. Visit Google鈥檚 guide to learn more. 
• Canvas: An interactive space that allows you to write and edit text collaboratively with Gemini. Canvas also includes a code editor and preview option to facilitate code-based testing and prototyping within the interface. Visit Google鈥檚 guide to learn more. 
• Gemini Models: AI models are used to interpret your prompts and provide responses. Gemini offers a few different models, each with unique strengths. Visit to choose one that best suits your task.
• Deep Research: Generate a more in-depth response with citations. Visit guide to learn more.
• Guided Learning: Use Gemini Apps as a tutor with guided learning, visual aids and educational resources. Visit Google鈥檚 guide to learn more.
  
  

Note: With our 糖心传媒 license, we may not have access to all models or features listed in Google鈥檚 documentation.

The Gemini prompting experience is individual, meaning you can't collaborate with others on a conversation. Additionally, Gemini's features do not permit targeted sharing of the content it generates. 

Sharing Gems

Unlike prompts, Gems can be shared with individuals and Google Groups. This allows the creation of a shared set of resources and instructions with which to prompt. Please note that prompting is an individual activity, and so you will not view the prompts by others on a Gem that you have created and shared.

For more information, please review .

Exporting results from Gemini

Once you have generated a response or created a resource using Gemini, you may consider one of the methods listed below to save or export the content so that it can be stored for a longer term or shared with others.

• to your Google Workspace apps, including a new Google Doc or Gmail draft.
  Note: This method of sharing is best suited to plain-text responses, as non-text elements may not be included in the export. 
• Copy and paste Gemini鈥檚 response. Either use the inline 鈥淐opy鈥� button (if generated), or select the ellipsis (...) under the response and select 鈥淐opy.鈥�
• Images generated by Gemini can be directly downloaded by pressing the download button on the image.

When sharing with others, use a method that allows you to control exactly who has access, with the ability to revoke access at any time. To do so, you can export your Gemini work and with others.

Before sharing the results of your work with Gemini, be sure to review the Responsible use guidelines on this page.

All 糖心传媒 Google account holders can now use their university Google Workspace account to access the education version of Google NotebookLM, an artificial intelligence (AI) tool designed for analysis, content organization and note-taking.

Key features of NotebookLM:

• Targeted analysis: You can upload or select specific files from your 糖心传媒 Google Drive (such as documents, PDFs or videos) or link to websites. NotebookLM only analyzes these selected materials to summarize information, create study guides and answer questions with citations.
• Collaboration: The "notebooks" you create in NotebookLM can be shared. You can grant others viewer or editor access to contribute to the sources used and generate content.

NotebookLM includes the following features:

• Source-grounded chat: Ask questions about your uploaded materials and receive responses tied to your sources. NotebookLM uses direct quotes, text and images from your sources as inline citations, making it easier to verify where information came from. You can also choose which sources to include or exclude when asking a question.
• Notebook-based organization: Organize work by project using separate notebooks. In each notebook, you can add multiple sources and work within a dedicated space focused on that topic or task. Google currently documents support for up to 50 sources per notebook.
• Notes: Create your own notes, save useful chat responses as notes and build a working set of ideas inside a notebook. Google also documents that notes can be converted into sources when needed.
• Audio Overviews: Generate podcast-style audio summaries based on your notebook sources. These are designed to help you review or absorb information in an audio format.
• Video Overviews: Create explainer-style videos that summarize source content and can incorporate visuals such as images, diagrams and quotes from your materials. Google notes that availability may vary by platform.
• Mind Maps: Generate a visual map of key ideas and relationships across your sources. This can help users quickly view themes, topic groupings and connections between documents.
• Study tools: NotebookLM can generate flashcards, quizzes and study guides from your uploaded materials, making it useful for review, learning and preparation.
• Visual outputs: Google also documents features such as infographics and slide decks/PDF presentations generated from notebook sources. Some of these features may have age or platform limitations.

Features in NotebookLM change frequently, and some capabilities may vary depending on device, user age and Google Workspace for Education licensing.

Sources are the materials you add to a NotebookLM notebook so it can work with a specific set of information. After sources are added, NotebookLM can use them to answer questions, summarize content, identify key points and generate new materials based on the information provided. To learn how to add or discover sources, visit Google鈥檚 page.

To learn how to add or discover sources, visit Google鈥檚 Add or discover new sources for your notebook page.

NotebookLM supports several types of sources, including:

• Copied and pasted text
• Google Docs
• Google Slides
• Google Sheets
• PDFs
• Microsoft Word files
• PowerPoint files
• CSV files
• Text and Markdown files
• Images
• Web URLs
• ePub files
• Public YouTube URLs with captions
• Audio files

Each source can contain up to 500,000 words or up to 200 MB for uploaded files. A notebook can include up to 50 sources.

Adding webpages as sources

When you add a webpage URL, NotebookLM imports the text content from that specific webpage only. It does not import images, embedded videos or other webpages linked from that page. Paywalled webpages are not supported.

Updating Google Drive sources

Google Drive sources do not update automatically in NotebookLM. If the original Google Drive file changes, the source must be manually synced in NotebookLM. If the source is eligible to be updated, a 鈥渃lick to sync with Google Drive鈥� option may appear in the Sources panel. This option is only available to users who have editing access to the original Google Drive file.

Updating other source types

Other source types, such as uploaded files and web URLs, cannot be synced with the original source. To update these materials in NotebookLM, remove the existing source and add the updated version again.

Deleting sources

Sources can be removed from a notebook when they are no longer needed. Removing a source may affect future responses, since NotebookLM uses the sources in the notebook to answer questions and complete requests. For shared notebooks, users should be careful when deleting sources because the source is removed from the notebook itself, not only from their individual view.

NotebookLM is intended to support analysis and content generation based on the materials you provide, but it should not be relied upon as a permanent storage solution. If you produce content that you would like to keep, revise or share with others, you should save it to your Google Drive.

Sharing a notebook with others

NotebookLM notebooks can be shared with other 糖心传媒 users to support collaboration on a defined set of sources, notes and generated materials. Notebooks can be shared with individual 糖心传媒 users or Google Groups within the organization. Public notebook sharing is not available for Google Workspace Enterprise or Education accounts.

To share a notebook, use the Share button in the top-right corner of the notebook and add the appropriate users or Google Groups. When sharing a notebook, you can assign either Viewer or Editor access.

A Viewer has read-only access to the source documents and notes shared in the notebook. An Editor can view, add or remove sources and notes, and may be able to share the notebook with other users.

What collaborators can access

When a notebook is shared, collaborators may be able to access the notebook鈥檚 shared sources, notes and generated materials, depending on their role. This includes sources added from Google Drive.

When a Google Drive file is added as a source, NotebookLM uses a copied version of that file in the notebook. Because of this, do not rely only on the original Google Drive file permissions to control access after the file has been added to a shared notebook. Before sharing a notebook, review the sources and remove any material that should not be visible to the people or groups receiving access.

Notebook access can be managed from the notebook鈥檚 Share settings. To remove access:

1. Open the notebook in NotebookLM.
2. Select Share in the top-right corner.
3. Find the individual user or Google Group in the sharing list.
4. Remove their access or change their role, depending on what is needed.
5. Review the sharing list to confirm only the appropriate people or groups still have access.

Removing access prevents the user or group from continuing to access the shared notebook through NotebookLM. However, any sources, notes or other content added by an editor may remain in the notebook unless they are reviewed and removed separately. Viewers have read-only access to shared sources and notes, while editors can view, add or remove sources and notes and share the notebook with other users.

Before removing access, review whether the user has contributed sources, notes or other content to the notebook. Editors can add and remove sources and notes, so changes made before their access is removed may remain in the notebook unless they are reviewed and removed separately. Viewers have read-only access to shared sources and notes, while editors can view, add or remove sources and notes and share the notebook further.

For 糖心传媒 accounts, access should be managed through individual 糖心传媒 users and Google Groups. Public notebook sharing is disabled, so notebooks should not be shared through public links.

Notebook ownership should be considered when using NotebookLM for ongoing team or departmental work. Notebooks are created within an individual user鈥檚 account, and ownership of a notebook cannot be transferred to another user.

For important team materials, it is recommended to save final notes, reports and other outputs in Google Drive or a Shared Drive, where access can be managed more easily over time. This helps ensure the department can continue to access and manage important work if the notebook creator leaves 糖心传媒, changes roles or no longer manages the notebook.

After exporting content from NotebookLM, review the Google Drive sharing settings for the exported file, since NotebookLM sharing permissions do not automatically carry over to files saved in Drive.

Exporting results from a notebook

NotebookLM should not be used as the only place to store important work. If you create results that need to be kept, revised or shared outside of NotebookLM, export or save them to another location.

Depending on the type of output, you may be able to:

• Export notes to Google Docs or Google Sheets
• Download generated files, such as slide decks, where supported
• Share or download Studio outputs, such as Audio Overviews, Mind Maps or Slide Decks, depending on the available options
• Copy useful chat responses into a Google Doc for further editing and long-term storage

Sharing permissions from NotebookLM do not carry over to exported Google Docs or Sheets. After exporting, review the file鈥檚 Google Drive sharing settings to make sure only the appropriate people have access.

Gemini App

Please note that some features of the Gemini App are only available to users who are .

Each person may use the Gemini App up to 1,000 times per month. This usage limit can't be shared with other people, and it doesn't roll over to the next month. Your usage limit resets on the first day of each month. .

Some of Gemini's AI models have additional usage limits imposed. For example, the Deep Research queries are limited to five (5) per month.

NotebookLM

Please note that some features of NotebookLM are only available to users who are .

Each 糖心传媒 NotebookLM user may have up to 100 notebooks containing up to 50 sources and 500,000 words. Each user has a daily chat limit of 50. NotebookLM can generate responses in various formats, each with their own daily limit.

Google has many different AI offerings under the Gemini brand and otherwise. The only components available to 糖心传媒 at this time are the prompt-based Gemini App and NotebookLM described here. In addition, some of the features of the consumer Gemini App and NotebookLM are not available at 糖心传媒.

The following features are not available to 糖心传媒 at this time:

• Gemini for Workspace, which provides Gemini functionality within your other Google Workspace applications, such as Drive, Docs, Calendar or Chat. 
• Access to developer tools and APIs, including Vertex AI.
• The ability to make your Gemini chats public or share them with others. You can, however, to your Google Workspace apps.
• Personalization of Gemini output based on your Google Search history.

We continue to investigate Gemini's Workspace features and will be considering their impact on privacy and security, as well as potential cost.

Development and refinement of AI tools is moving quickly, and Google's AI tools are no exception to this rule. You may find that the interface and functionality within these tools change frequently. We will do our best to update our resources to reflect significant changes, but may not be able to keep up with the pace of changes.

Google's AI tools are not an 鈥淎I detection鈥� tool, and cannot identify if a body of text was written by a generative AI model like Gemini or ChatGPT. In addition, it is inappropriate to submit a student's work through an AI tool on their behalf, as it does not fall under the "public or low sensitivity" classification for content that is eligible for use with these tools.

For concerns around academic integrity and AI, the Academic Integrity Office (AIO) is the best resource at 糖心传媒. More information can be found in their Artificial Intelligence FAQs.

The data produced by Google's AI tools cannot be relied upon and must be checked for accuracy. Before you use or share this content, you are responsible for ensuring it is accurate and appropriate.

Gemini is a family of multimodal large language models (LLMs) that generates responses by identifying patterns in the data it was trained on, including text, images and more. Therefore, inherent biases or inaccuracies may exist. Unlike information retrieval systems that search and retrieve specific, existing data, all responses generated by Gemini are novel and should be verified independently rather than accepted as definitive fact.

Gemini cannot be relied upon to provide accurate information about itself, its abilities or 糖心传媒's access to its features.

This example demonstrates how to use NotebookLM to create an audience-appropriate summary from a set of sources. Unlike the Gemini App, NotebookLM is designed to work from the materials you add to a notebook, and its responses can include inline citations so you can verify where the information came from.

1. Create a notebook in NotebookLM: Open NotebookLM and create a new notebook for your project or topic. Each notebook acts as a separate workspace for a defined set of source materials
2. Provide your source material: Add relevant sources to the notebook, such as PDFs, websites, Google Docs, Google Slides, Google Sheets, YouTube videos, audio files, copied text or other supported file types. You can add or discover sources from Google Drive and from the web within NotebookLM.
3. Create a prompt in NotebookLM chat: In the chat panel, write your prompt and ask NotebookLM to work from the sources in your notebook.
   
   For instance, try a prompt like this to start the conversation: 鈥淓xtract the key points from the sources in this notebook and present them in a bullet-point list for university administrators. Create a separate section highlighting any inconsistencies between the documents.鈥�
4. Review the generated response: Check whether the response meets your needs and expectations. If it does not, use a follow-up prompt to adjust the tone, structure, audience or level of detail. You can also review the inline citations to understand exactly where the information came from in your sources.
   
   For instance, try a prompt like this to follow up: 鈥淢ake the tone more formal, and provide suggestions to resolve the inconsistencies.鈥�
   
5. Save your results and revise: When you are happy with the generated response, you can save it as a note in NotebookLM. Notes can be exported to Google Docs or Google Sheets for further revision and sharing. Be sure to review and update these results for accuracy and appropriateness before sharing them with others.

Gems are customized chat tools within the Gemini App that allow you to save a set of parameters, instructions and resources that can be applied to prompts. They are useful when you鈥檙e frequently creating content for the same audience or using a particular format. This example demonstrates how to use Gemini to create a social media post for any event using publicly-available information; only basic information is provided in the prompt for Gemini to use.

1. Create a new Gem: Launch the Gemini App; click on the 鈥淕em Manager鈥� option in the bottom-left corner and choose 鈥淣ew Gem.鈥�
2. Define the Gem Instructions: Give the Gem a title, then provide your instructions. Identify main objectives, capabilities and response style. Visit Google鈥檚 to learn about writing effective Gem instructions.
   
   Try a prompt like this to set up the Gem: 鈥淐reate a social media post for our new event, targeting young adults.鈥�
3. Refine your Gem Instructions: Write your initial instructions, then click the pencil icon within the 鈥淚nstructions box鈥� to have Gemini re-write and expand your instructions to meet the intended structure. This will include sections related to the tool鈥檚 purpose and goals, as well as behaviours and rules. Read the new instructions to ensure they still match your goals, then click Save.
4. Test how the Gem works: In the preview window, enter a prompt for Gemini to respond to in the persona that you specified.
   
   Try a prompt like this to start the conversation with your Gem: 鈥�Toronto Met Film Festival on May 16th鈥� or "糖心传媒 IT Conference on May 21st". You should receive promotional content for the event and advice around how to post it to various platforms.
5. Make changes as needed: If the response isn鈥檛 as expected, revisit your instructions or resources. Adjust the content to be more precise or add additional rules and test again. Once you are happy with the responses you are receiving, you can access this trained chat under the 鈥淕ems鈥� heading in the Gemini App鈥檚 left sidebar.

Canvas is an interactive space within the Gemini App that allows you to write and edit in your browser collaboratively with Gemini. It is useful for real-time content generation as a writing assistant, and allows you to edit text within the Gemini App. This example demonstrates how to use Gemini to collect ideas in a Canvas document that can be edited by the user and Gemini; specific resources are not provided in the prompt for Gemini to use.

1. Engage the Canvas function: In the prompt textbox, click on the 鈥淐anvas鈥� button to switch to the tool. 
2. Provide initial task information: Through a prompt and optional attached documents, outline the intended task. The window will be split into two sections; the content will be generated in the Canvas section, and Chat will remain open
   
   Try a prompt like this: 鈥�Write a one-page report summarizing the key trends in [your field of work].鈥�
3. Edit the generated text: In the Canvas, you can make changes to the text and formatting as you would to a Google Doc. While editing, you can direct Gemini to modify the content.
   
   - Use the built-in features 鈥渇loating鈥� in the window to change length, tone or request edit suggestions to the document. Gemini will automatically apply the changes, without review.
   - To direct a prompt to specific text, highlight the relevant words, and an 鈥淎sk Gemini鈥� box will appear directly below. Input a prompt, such as "Check this statement for factual accuracy," then press enter. The response to your prompt will appear as a Gemini Chat in the on-screen panel; you can ask follow-up questions about the response provided.
4.  Analyze the content: Use the Gemini Chat window for prompts for assistance with the document as a whole, or to switch between Canvas documents generated in the Gemini Chat. Try these sample prompts:
   
   - "How can I improve my document? I want to make it more engaging to people outside of the industry.鈥�
   - 鈥淩eformat the entire document, making it easier to read.鈥�
5.  Save your results and revise: When you are happy with the generated document in the Canvas, either export or copy/paste the content to your preferred format. Details can be found at the sharing and exporting my results from Gemini resource above. Be sure to review and update these results for accuracy and appropriateness before sharing with others.

Canvas serves as an interactive space within the Gemini App that allows you to write and edit code in your browser collaboratively with Gemini in Python, HTML and more. This example demonstrates how simple interactive objects are coded; specific resources need not be provided as Gemini will gather the information needed to complete the task.

1. Engage the Canvas function: In the prompt textbox, click on the 鈥淐anvas鈥� button to switch to the tool.
2. Provide initial task information: Through a prompt and optional attached documents, outline the intended code-related task and desired programming language. The window will be split into two sections; the content will be generated in the Canvas section, and Chat will remain open.
   
   Try this sample prompt: 鈥�Generate a grid of circles using p5.js. Make the colour of the circles change to a random colour when I hover over them.鈥�
3. Make changes to the code: View the content as either an interactive window or as the generated code. Use the Gemini Chat window to instruct changes or or ask directed questions by selecting relevant lines of code before prompting. Some sample prompts to try might be:
   
   - 鈥淢ake the circles move randomly, and bounce off of each other and the boundaries of the window.鈥�
   - 鈥淧rint the x,y coordinates of each circle that I hover over to the console.鈥�
   - 鈥淲hat does this function do?鈥� (using the 鈥淎sk Gemini鈥� box that appears after highlighting a section of code).
4. Improve through iterations: With each requested change, an overview explanation is provided. Read it to understand the impact of the changes, then test the interactivity. If the functionality in the preview is not working as you would hope, identify the issue to the tool. Some sample follow-up prompts might be:
   
   - 鈥淭he circles aren't changing colour when I hover over them.鈥�
   - 鈥淥nly change each circle鈥檚 colour once per second.鈥�
5. Save your results and revise: When you are happy with the generated code in the Canvas, copy/paste it to your preferred format. Details can be found at the Sharing and exporting my results from Gemini resource above. Be sure to review and update these results for accuracy and appropriateness before sharing with others.

Deep Research is a tool that uses your prompt to plan research, search the web, show its progress and then provide a research report to you. In this example, we are not providing specific resources; Gemini鈥檚 Deep Research collects relevant information from the web.

1. Engage the Deep Research function: In the prompt textbox, click on the 鈥淒eep Research鈥� button to switch to the tool. 
2. Provide the topic to research: This can be broad or specific; the level of detail you provide will determine how focused the research will be. As Deep Research queries are limited to five (5) per month, we advise testing the tool with topics within your area of interest. 
   
   Try this sample prompt: 鈥淐ollect benefits and drawbacks to using Generative AI for [your field of work]. Focus on concrete examples of situations where it was demonstrably useful and when it resulted in significant errors or limitations. Include Ontario-based considerations, including policies and industry-specific guidelines.鈥� 
3. Review the research plan: The tool will create an overview of the steps to complete the research. Review the plan to ensure it aligns with your expectations; if it does not, choose the option to edit the plan and specify the changes you would like. When the plan meets your expectations, click 鈥淪tart Research.鈥� 
4. Watch as the plan is executed: Deep Research displays 鈥渢hinking.鈥� This is the tool reporting as it completes the steps outlined in the plan. It accesses resources on the web to collect and synthesize information from various websites.
5. Use your report: Once completed, a report based on the research will be auto-generated in the same Gemini App window. You can choose to export the report鈥檚 content. Review Sharing and exporting my results from Gemini for more details.