Documentation
HomeAPISign In
  • Getting Started
    • Overview
      • Core Concepts
      • Building your First Workflow
    • API Reference
  • Your Data
    • Brand Kits
    • Knowledge Bases
      • Add Data
        • Upload Files
        • Web Scrape
        • Import from Google Drive
        • Import from SQL Database
        • Import from Shopify
      • Knowledge Base Search
      • Knowledge Base Metadata
      • Knowledge Base API
  • Building Workflows
    • Workflow Concepts
      • Workflow Inputs
        • Input Types
      • Workflow Outputs
      • Variable Referencing
      • Liquid Templating
    • Workflow Steps
      • AI
        • Prompt LLM
          • Model Selection Guide
          • Prompting Guide
        • Transcribe Audio File
      • Web Research
        • Google Search
        • Web Page Scrape
      • Code
        • Run Code
        • Call API
        • Format JSON
        • Run SQL Query
        • Write Liquid Text
      • Flow
        • Condition
        • Iteration
        • Human Review
        • Content Comparison
        • Error
      • Data
        • Read from Grid
        • Write to Grid
        • Search Knowledge Base
        • Write to Knowledge Base
        • Get Knowledge Base File
      • AirOps
        • Workflow
        • Agent
      • Image & Video
        • Generate Image with API
        • Search Stock Images
        • Fetch Stock Image with ID
        • Resize Image
        • Screenshot from URL
        • Create OpenGraph Image
        • Create Video Avatar
      • SEO Research
        • Semrush
        • Data4SEO
      • Content Quality
        • Detect AI Content
        • Scan Content for Plagiarism
      • Content Processing
        • Convert Markdown to HTML
        • Convert PDF URL to Text
        • Group Keywords into Clusters
      • B2B Enrichment
        • Hunter.io
        • People Data Labs
      • CMS Integrations
        • Webflow
        • WordPress
        • Shopify
        • Contentful
        • Sanity
        • Strapi
      • Analytics Integrations
        • Google Search Console
      • Collaboration Integrations
        • Gmail
        • Google Docs
        • Google Sheets
        • Notion
        • Slack
    • Testing and Iteration
    • Publishing and Versioning
  • Running Workflows
    • Run Once
    • Run in Bulk (Grid)
    • Run via API
    • Run via Trigger
      • Incoming Webhook Trigger
      • Zapier
    • Run on a Schedule
    • Error Handling
  • Grids
    • Create a Grid
      • Import from Webflow
      • Import from Wordpress
      • Import from Semrush
      • Import from Google Search Console
    • Add Columns in the Grid
    • Run Workflows in the Grid
      • Add Workflow Column
      • Run Workflow Column
      • Map Workflow Outputs
      • Review Workflow Run Metadata
    • Review Content in the Grid
      • Review Markdown Content
      • Review HTML Content
      • Compare Content Difference
    • Publish to CMS from Grid
    • Pull Analytics in the Grid
    • Export as CSV
  • Copilot
    • Chat with Copilot
    • Edit Workflows with Copilot
    • Fix Errors with Copilot
  • Monitoring
    • Task Usage
    • Analytics
    • Alerts
    • Execution History
  • Your Workspace
    • Create a Workspace
    • Folders
    • Settings
    • Billing
    • Use your own LLM API Keys
    • Secrets
    • Team and Permissions
  • Chat Agents (Legacy)
    • Agent Quick Start
    • Chat Agents
    • Integrate Agents
      • Widget
      • Client Web SDK
  • About
    • Ethical AI and IP Production
    • Principles
    • Security and Compliance
Powered by GitBook
On this page
  • Building Your First AirOps Workflow: Keyword SERP Researcher
  • Interactive Tutorial
  • Step-by-Step Guide
  • Creating the Workflow
  • Setting Up the Google Search Step
  • Creating the LLM Analysis Step
  • Testing and Publishing Your Workflow
  • You did it

Was this helpful?

  1. Getting Started
  2. Overview

Building your First Workflow

Last updated 2 months ago

Was this helpful?

Building Your First AirOps Workflow: Keyword SERP Researcher

In this tutorial, we'll walk through building your first AirOps Workflow - a Keyword SERP Researcher that analyzes Google search results for your target keywords.

Interactive Tutorial

Step-by-Step Guide

Creating the Workflow

Step 1: Create a New Workflow

  1. From the Home screen, click the "Create" button in the top-right corner

  2. Select "Workflow" from the dropdown menu

  3. You'll be directed to the AirOps Workflow Studio where you'll build your workflow

Step 2: Configure Your Workflow Input

  1. In the Workflow Studio, you'll see a node labeled "Set Inputs" at the top of your workflow

  2. Click on this node to configure your input field

  3. Click "Add field to group" or a similar option

  4. Select "Short Text" as the input type

  5. Label the field "keyword" - this will be the search term you want to analyze

  6. Make sure the variable name is also "keyword" (this happens automatically)

  7. Toggle "Required" to ensure a keyword is always provided

  8. Save your configuration

Setting Up the Google Search Step

Step 1: Add a Google Search Step

  1. You'll need to add a Google Search step after your inputs

  2. Look for the "+" button or "Add Step" option below your input node

  3. Navigate through the categories and select "Web Research" category

  4. Choose "Google Search" from the available steps

  5. This will add a Google Search step to your workflow, similar to what's shown in Image 2

Step 2: Configure the Google Search Step

  1. Click on the Google Search step

  2. In the "Search Query" field, click on the variable explorer (pink icon on the top right of the input field) and choose {{ keyword }}

  3. Leave the "Search Parameters" field empty for now

  4. Save your configuration

Creating the LLM Analysis Step

Step 1: Add a Prompt LLM Step

  1. After your Google Search step, add another step

  2. Choose "Prompt LLM" (Large Language Model) from the available steps

  3. This will add an LLM step after your Google Search step

Step 2: Configure the LLM Model

  1. Click on the LLM step

  2. We're using "GPT-4o" as our model in this example

  3. You can leave other settings at their defaults for now

Step 3: Craft Your LLM Prompt

  1. In the LLM step panel, enter the following prompt in the input field that says "User" on its left:

You are tasked with analyzing the themes and best practices of top-performing Google search results for a given keyword. This analysis will help understand what makes these pages successful and provide insights for content creation.

The keyword for analysis is:
{{ keyword }}

Here are the top-performing results from Google for this keyword:
{{ step_1.output }}

To complete this task, follow these steps:

1. Carefully read through all the top-performing results.

2. Analyze the themes:
   a. Identify common topics or subjects addressed across multiple results.
   b. Note any unique angles or perspectives on the main topic.
   c. Observe the depth and breadth of information covered.

3. Identify best practices:
   a. Examine the content structure (headings, subheadings, lists, etc.).
   b. Assess the use of media (images, videos, infographics, etc.).
   c. Evaluate the writing style and tone.
   d. Look for patterns in content length and detail level.
   e. Note any common external resources or references used.
   f. Observe how the content addresses user intent.

4. Present your analysis in the following format:

# Analysis
## Themes
[List and briefly describe 3-5 main themes you've identified]


## Best Practices
[List and explain 5-7 best practices you've observed]

## Recommendations
[Provide 3-5 actionable recommendations for creating content based on your analysis]

Remember to be thorough in your analysis and objective in your observations. Focus on patterns and practices that appear to contribute to the success of these top-performing pages. Your insights should be valuable for anyone looking to create high-quality content on this topic.
  1. Notice how this prompt references both the keyword input ({{ keyword }}) and the output from the previous Google Search step ({{ step_1.output }})

Testing and Publishing Your Workflow

Step 1: Test Your Workflow

  1. Click "Test Workflow" in the top right of the Studio navigation bar (play icon next to it)

  2. Enter a test keyword (e.g., "content marketing tips" or "best running shoes")

  3. Click "Test Workflow" to run your workflow

  4. Review the results to ensure both steps are working correctly

Step 2: Publish Your Workflow

  1. Once you're satisfied with the results, look for a "Publish" button on the top right of the Studio

  2. Give your workflow a descriptive name like "Keyword SERP Researcher"

  3. Add a brief description of what the workflow does

  4. Publish your workflow to make it available for running

Congratulations! You've successfully built your first AirOps Workflow. This Keyword SERP Researcher provides insights for your content creation strategy by analyzing what makes top-ranking content successful for any keyword.

As you become more familiar with AirOps, you can expand this workflow by adding more steps, incorporating human review steps, or connecting it to other workflows to create a comprehensive content creation pipeline.

You did it

🎉