Simulang v0 examples - Simular Developer Documentation

The best way to master Simular Pro is to learn from the example instructions (prompts) and corresponding Simulang v0 code on this page. Just run the instructions on your Simular Pro to reproduce similar Simulang v0 code, or copy the snippets on this page and execute them in the app.

Simulang v0 only — not the latest Simulang. These examples apply only to Simulang v0 embedded in Simular Pro. They do not match the current standalone Simulang CLI, simulang-js, or other newer Simulang surfaces; syntax and actions can differ. Use this page with the Simulang v0 API reference. For the latest scripting model, see the Simulang Primer and Simulang with Claude Code.

Find out how to:

You can always refer to the Simulang v0 API documentation if you need a refresher on each Simulang v0 action.

Most of the Simulang v0 code on this page was generated in one shot from the instructions. Since there may be differences in individual machine configurations (e.g. browser settings), we recommend that you double check the Simulang v0 snippets before executing.

If Simular Pro did not click on an element you intended, try these various methods for element localization.

Reading structured information

Many workflows start with extracting information from an application or webpage. Moreover, the extracted information often needs to be represented in a particular structure. For example:

A house on sale has the following fields: address, square footage, number of beds and baths, etc.
An email has these fields: sender address, time sent, title, etc.

This section shows you how to instruct Simular Pro to extract information from diverse sources into structured forms. The resulting information will be ready for downstream workflow steps, such as iterating a subtask over multiple elements or writing structured outputs to files.

Community and communication applications: Extracting channel names on a desktop community app

Open Discord
Get the page content and extract the top 10 server names visible in the left sidebar.
Do not include direct messages.

Show Simulang v0

function main() {
    // Open Discord
    open({app: "Discord"});

    let servers = [];

    // Get page content and analyze servers
    var content = pageContent();
    // Extract list of servers from the sidebar
    var serverList = ask({
        prompt: "List the top 10 Discord server names visible in the left sidebar. Do not include the direct messages. Return as JSON array. Do not say anything else.",
        context: content
    });
    servers = JSON.parse(serverList);

    return servers;
}

Shopping: Get all store locations of a grocery chain

Go to Wegmans stores webpage.
Get all the locaitons and print them out.

Show Simulang v0

function main() {
    // Open Wegmans stores webpage
    open({url: "https://www.wegmans.com/stores"});
    wait({waitTime: 2});
    
    // Get page content and extract all locations
    var content = pageContent();
    var locationsResponse = ask({
        prompt: "Extract all store locations from this page. Return a JSON array of location names (cities/towns where Wegmans stores are located). Do not say or explain anything else, just return the requested data.",
        context: content
    });
    
    var locations = JSON.parse(locationsResponse);
    
    // Print out all locations
    console.log("Wegmans Store Locations:");
    for (let i = 0; i < locations.length; i++) {
        console.log(`${i + 1}. ${locations[i]}`);
    }
    
    return {status: "completed", totalLocations: locations.length, locations: locations};
}

Go to simular.ai
Get all of their social media URLs and print them out

Show Simulang v0

function main() {
    // Go to simular.ai
    open({url: "https://simular.ai"});
    wait({waitTime: 3});
    
    // Get page content
    const content = pageContent();
    
    // Ask for social media URLs with explicit JSON format request
    const result = ask({
        prompt: "Find all social media URLs on this page (Twitter, LinkedIn, YouTube, Facebook, Instagram, Discord, etc.). Return as a JSON array of URLs only. Do not say or explain anything else, just return the requested data.",
        context: content
    });
    
    // Parse the JSON response
    const socialMediaUrls = JSON.parse(result);
    
    // Print out all social media URLs
    console.log("Social media URLs found on simular.ai:");
    for (const url of socialMediaUrls) {
        console.log(url);
    }
    
    return {success: true, socialMediaUrls: socialMediaUrls};
}

News: Get all headlines from a news site

Go to techcrunch, get all the news headlines, and print them out.

Show Simulang v0

function main() {
    // Open TechCrunch website
    open({url: "https://techcrunch.com"});
    wait({waitTime: 3});
    
    // Get page content
    const content = pageContent();
    
    // Ask LLM to extract all news headlines
    const headlinesResponse = ask({
        prompt: "Extract all news headlines from this TechCrunch page. Return only a JSON array of headline strings. Do not include any other text or explanation.",
        context: content
    });
    
    // Parse the JSON response
    const headlines = JSON.parse(headlinesResponse);
    
    // Print out all headlines
    console.log("TechCrunch News Headlines:");
    console.log("==========================");
    
    for (let i = 0; i < headlines.length; i++) {
        console.log(`${i + 1}. ${headlines[i]}`);
    }
    
    return {success: true, headlinesCount: headlines.length};
}

Investing: Get an investment firm’s list of portfolio companies

Go to a16z's portfolio page and get all the features company names on the page.

Show Simulang v0

function main() {
    // Open Chrome and navigate to a16z portfolio page
    open({url: "https://a16z.com/portfolio"});
    
    let allCompanies = new Set();

    // Get current page content
    let content = pageContent();
    
    // Extract visible company names
    let response = ask({
        prompt: "This is the a16z portfolio page. List all visible featured portfolio company names on the page. Do not include a16z itself or any navigation elements. Return as JSON array of strings. Do not say or explain anything else, just return the requested data.",
        context: content
    });
    
    allCompanies = JSON.parse(response);
    
    // Convert to sorted array and display results
    let sortedCompanies = Array.from(allCompanies).sort();
    
    console.log(`Found ${sortedCompanies.length} featured companies on a16z's portfolio page:`);
    console.log(sortedCompanies.join("\n"));
    
    return {
        success: true,
        totalCompanies: sortedCompanies.length,
        companies: sortedCompanies
    };
}

Email management: Get the sender, date, and summary of the first unread email.

Go to gmail.com
Click the first unread email
From the email content, get: sender email address, date, summary of topic

Show Simulang v0

function main() {
    // Go to Gmail
    open({url: "https://gmail.com"});
    wait({waitTime: 3});
    
    // Click the first unread email
    clickFirstUnreadEmail();
    
    // Get email information
    let emailInfo = getEmailInfo();
    
    // Output the results
    console.log(`Sender Email: ${emailInfo.senderEmail}`);
    console.log(`Date: ${emailInfo.date}`);
    console.log(`Summary: ${emailInfo.summary}`);
    
    return emailInfo;
}

//@ Click the first unread email
function clickFirstUnreadEmail() {
    let content = pageContent();
    let firstUnreadEmail = ask({
        prompt: "Find the first unread email in the inbox and return its subject line or identifying text that can be clicked. Return only the clickable text, nothing else.",
        context: content
    });
    
    click({concept: firstUnreadEmail});
    wait({waitTime: 2});
}

//@ Get email information including sender, date, and summary
function getEmailInfo() {
    let content = pageContent();
    let emailData = ask({
        prompt: "From this email content, extract: 1) sender email address, 2) date of the email, 3) a brief summary of the topic/subject. Return as JSON with keys 'senderEmail', 'date', 'summary'. Do not say or explain anything else, just return the requested JSON data.",
        context: content
    });
    
    return JSON.parse(emailData);
}

Real estate: Get address, number of bedrooms and bathrooms, square footage, and price of homes in Palo Alto

Go to redfin palo alto zip 14325
Get all the address, number of bed, number of bath, square feet, and price of the houses

Show Simulang v0

function main() {
    // Open Chrome and go to Redfin Palo Alto
    open({app: "Google Chrome"});
    wait({waitTime: 2});
    
    // Navigate to Redfin Palo Alto
    press({key: "l", cmd: true});
    type({text: "redfin.com/city/14325/CA/Palo-Alto", withReturn: true});
    wait({waitTime: 3});
    
    // Get all house listings data
    let houseData = getHouseListings();
    
    // Log the results
    console.log("House listings in Palo Alto:");
    for (let i = 0; i < houseData.length; i++) {
        console.log(`House ${i + 1}:`);
        console.log(`Address: ${houseData[i].address}`);
        console.log(`Bedrooms: ${houseData[i].bedrooms}`);
        console.log(`Bathrooms: ${houseData[i].bathrooms}`);
        console.log(`Square Feet: ${houseData[i].squareFeet}`);
        console.log(`Price: ${houseData[i].price}`);
        console.log("---");
    }
    
    return {status: "completed", houses: houseData};
}

//@ Get all house listings with address, bedrooms, bathrooms, square feet, and price
function getHouseListings() {
    // Get page content
    let content = pageContent();
    
    // Ask LLM to extract house data
    let result = ask({
        prompt: "Extract all house listings from this Redfin page. For each house, get: address, number of bedrooms, number of bathrooms, square feet, and price. Return as a JSON array with objects containing fields: address, bedrooms, bathrooms, squareFeet, price. Do not say or explain anything else, just return the requested JSON data.",
        context: content
    });
    
    let houseData = JSON.parse(result);
    return houseData;
}

Repeating a task on multiple objects on a page

Having successfully used Simular Pro to read structured information, such as getting

all the names of companies on a page, or
all the store locations of a grocery chain, or
all the influencer channel names, etc.

now you may need to repeat some task on each of those items, such as:

checking each company’s stock prices,
each grocery store’s items on sale
each influencer’s subscriber count

The following examples show how to instruct Simular Pro to iterate through all the items and do a follow-up task reliably on each item.

Opening and reading all Simular blog posts

Go to simular.ai/blog
Get all the blog post URLs
For each blog post URL, open it, extract the post title and a short summary, then close the tab.
Print out the post titles and summaries.

Show Simulang v0

//@ Go to simular.ai/blog and get all blog post URLs
function getBlogPostUrls() {
    open({url: "simular.ai/blog"})
    wait({waitTime: 3})
    
    var content = pageContent()
    
    var result = ask({
        prompt: "Find all blog post URLs on this page. Return as a JSON array of complete URLs only. Do not say or explain anything else, just return the requested data.",
        context: content
    })
    
    return JSON.parse(result)
}

//@ Extract title and summary from a blog post
function extractPostInfo(url) {
    open({url: url})
    wait({waitTime: 3})
    
    var content = pageContent()
    
    var result = ask({
        prompt: "Extract the blog post title and create a short summary (2-3 sentences) of the main content. Format as a JSON object with fields 'title' and 'summary'. Do not say or explain anything else, just return the requested data.",
        context: content
    })
    
    return JSON.parse(result)
}

function main() {
    // Get all blog post URLs
    var blogUrls = getBlogPostUrls()
    
    var allPosts = []
    
    // Process each blog post
    for (var i = 0; i < blogUrls.length; i++) {
        var url = blogUrls[i]
        
        // Extract title and summary
        var postInfo = extractPostInfo(url)
        postInfo.url = url
        allPosts.push(postInfo)
        
        // Close the current tab
        press({key: "w", cmd: true})
        wait({waitTime: 1})
        
        console.log(`Title: ${postInfo.title}`)
        console.log(`Summary: ${postInfo.summary}`)
        console.log(`URL: ${url}`)
        console.log("---")
    }
    
    return {
        success: true,
        posts: allPosts
    }
}

Structured information output

The sections above show you how Simular Pro can read structured information and repeats a task on 100 webpages - now you need it to write that valuable information somewhere. This section shows you many options to write structured output to a local file on disk or a web browser application. If you cannot find an output format you need, just ask us on Discord.

Writing information into a Google Sheet

Open a new Google Sheet
Add headers Name, Summary, Date
Write "Simular", "Simular pro can do anything!", "08/30/2025" into the first row.

Show Simulang v0

function main() {
    // Create a new Google Sheet
    open({url: "https://sheets.google.com/create"});
    wait({waitTime: 2});
    
    // Add headers
    setGoogleSheetCellValue({cell: "A1", value: "Name"});
    setGoogleSheetCellValue({cell: "B1", value: "Summary"});
    setGoogleSheetCellValue({cell: "C1", value: "Date"});
    
    // Add data to the first row (row 2, since row 1 has headers)
    setGoogleSheetCellValue({cell: "A2", value: "Simular"});
    setGoogleSheetCellValue({cell: "B2", value: "Simular pro can do anything!"});
    setGoogleSheetCellValue({cell: "C2", value: "08/30/2025"});
    
    return {success: true};
}

Writing information into Excel

Open a new blank sheet in Excel
Add headers Name, Summary, Date
Write "Simular", "Simular pro can do anything!", "08/30/2025" into the first row.

Show Simulang v0

function main() {
    // Open Excel and create a new blank sheet
    open({app: "Microsoft Excel"});
    
    // Create new blank workbook
    press({key: "n", cmd: true});
    wait({waitTime: 2});
    
    // Add headers in the first row
    click({concept: "cell A1"});
    type({text: "Name"});
    
    press({key: "tab"});
    type({text: "Summary"});
    
    press({key: "tab"});
    type({text: "Date"});
    
    // Move to the second row and add the data
    click({concept: "cell A2"});
    type({text: "Simular"});
    
    press({key: "tab"});
    type({text: "Simular pro can do anything!"});
    
    press({key: "tab"});
    type({text: "08/30/2025"});
    
    return {success: true};
}

Clicking on UI elements

Sometimes, the basic click({at: <description of some element>}) may not be enough for Simular Pro to identify a unique element. This may happen when more than one element share the same text description, or when the target element only has a visual label (e.g., image or icon). In these cases, you have two options:

In Settings, enable vision fallback for the click action. Simular Pro will automatically attempt to use the best method for UI localization.
Use more precise inputs to the click function, as shown by examples below. You can find the full specification of inputs to the click function here.

Use the element picker tool

to check the text description of your target element.

Clicking one of multiple elements that have the same description or image.

This pattern is a powerful and fast way to localize a target element whose textual description may not be unique:

click({
    at: <something not unique>, 
    spatialRelation: <a comma-separated string of spatial relationships>, 
    anchorConcept: <something unique>
})

You may use one from each of the following three spatial relation categories for spatialRelation:

distance: closest, furthest
positional filters: left, right, above, below,
containment filters: contains, containedIn

For example, this will find the unique element called “link Introduction” that is above of and closest to a unique element called “heading Simular Pro”:

click({
    at: "link Introduction", 
    spatialRelation: "above,closest", 
    anchorConcept: "heading Simular Pro"
})

Here is an example drawn from this current page:

Go to docs.simular.ai
Click on Introduction closest to Getting Started
Click on Introduction closest to Simulang
Click on Introduction closest to Agent S
Click on Introduction closest to Simular

Show Simulang v0

function main() {
    // Go to docs.simular.ai
    open({url: "https://docs.simular.ai"});
    
    // Click on Introduction closest to Getting Started
    click({at: "Introduction", spatialRelation: "closest", anchorConcept: "Getting Started"});
    wait({waitTime: 1});
    
    // Click on Introduction closest to Simulang
    click({at: "link Introduction", spatialRelation: "below,closest", anchorConcept: "heading Simulang", mode: "anchorGrounding"})
    wait({waitTime: 1});
    
    // Click on Introduction closest to Agent S
    click({at: "link Introduction", spatialRelation: "above,closest", anchorConcept: "heading Agent S", mode: "anchorGrounding"})
    wait({waitTime: 1});
    
    // Click on Introduction closest to Simular
    click({at: "link Introduction", spatialRelation: "below,furthest", anchorConcept: "link Blog", mode: "anchorGrounding"})
    wait({waitTime: 1});
    
    return {success: true};
}

When attempting to close a popup window, you may need to distinguish between the close button of the popup window and the close button of the outer application. You can instruct Simular Pro to click the close button contained in the dialog window.

Use the element picker tool

to get the description of the anchor element.

Click the close button contained in the group dialog.

Show Simulang v0

function main() {
    Click({ at: "button close", spatialRelation: "containedIn", anchorConcept: "group dialog Find and replace" });
}

Clicking on an element without text description

If your target element is a pure image without any text description, then you should use the vision mode to localize the element:

click({at: <describe your element>, mode: "vision"})

Use the element picker tool

to check whether your target element has any useful text description.

Go to docs.simular.ai
Click the Simular logo using vision

Show Simulang v0

function main() {
    // Navigate to docs.simular.ai
    open({url: "https://docs.simular.ai"});
    click({at: "simular logo", mode: "vision"})
}

Sometimes you may need to click on an empty space on the current screen, such as when applying a signature to some area of a document.

Click the empty space below the date.

Show Simulang v0

function main() {
    click({at: "the space below the date", mode: "vision"})
}

Clicking on an element using both text and screenshot

If neither specifying spatial relations nor pure vision work, you may need a combination of both to localize an element. The mode textAndScreenshot is able to localize any element that has a text description.

click({at: <description of element>, mode: "textAndScreenshot"})

You may use any natural language for the description of the element, including any referring expressions (e.g., “link Introduction in the Simulang section”)

Open docs.simular.ai
Click the introduction link in the simulang section

Show Simulang v0

function main() {
    open({url: "https://docs.simular.ai"})
    click({at: "link Introduction in the Simulang section", mode: "textAndScreenshot"})
}

​Reading structured information

​Community and communication applications: Extracting channel names on a desktop community app

​Shopping: Get all store locations of a grocery chain

​Social media URL scraping: Get a company’s social media URLs

​News: Get all headlines from a news site

​Investing: Get an investment firm’s list of portfolio companies

​Email management: Get the sender, date, and summary of the first unread email.

​Real estate: Get address, number of bedrooms and bathrooms, square footage, and price of homes in Palo Alto

​Repeating a task on multiple objects on a page

​Opening and reading all Simular blog posts

​Structured information output

​Writing information into a Google Sheet

​Writing information into Excel

​Clicking on UI elements

​Clicking one of multiple elements that have the same description or image.

​Clicking on an element without text description

​Clicking on an element using both text and screenshot

Reading structured information

Community and communication applications: Extracting channel names on a desktop community app

Shopping: Get all store locations of a grocery chain

Social media URL scraping: Get a company’s social media URLs

News: Get all headlines from a news site

Investing: Get an investment firm’s list of portfolio companies

Email management: Get the sender, date, and summary of the first unread email.

Real estate: Get address, number of bedrooms and bathrooms, square footage, and price of homes in Palo Alto

Repeating a task on multiple objects on a page

Opening and reading all Simular blog posts

Structured information output

Writing information into a Google Sheet

Writing information into Excel

Clicking on UI elements

Clicking one of multiple elements that have the same description or image.

Clicking on an element without text description

Clicking on an element using both text and screenshot