# Table of Contents - [Overview | AirOps Docs](#overview-airops-docs) - [Core Concepts | AirOps Docs](#core-concepts-airops-docs) - [Knowledge Bases | AirOps Docs](#knowledge-bases-airops-docs) - [Brand Kits | AirOps Docs](#brand-kits-airops-docs) - [Building your First Workflow | AirOps Docs](#building-your-first-workflow-airops-docs) - [Knowledge Base Search | AirOps Docs](#knowledge-base-search-airops-docs) - [Knowledge Base API | AirOps Docs](#knowledge-base-api-airops-docs) - [Add Data | AirOps Docs](#add-data-airops-docs) --- # Overview | AirOps Docs GitBook Assistant GitBook Assistant Working...Thinking... GitBook Assistant ##### Good afternoon I'm here to help you with the docs. What is this page about?What should I read next?Can you give an example? Ctrli AI Based on your context Send AirOps streamlines your content marketing with a comprehensive toolkit that combines leading AI models, powerful SEO tools, image generation capabilities, and CMS integrations—all in one platform. With AirOps, you maintain editorial control through a balanced combination of automation and human oversight, preserving your unique voice. Built-in analytics help you track content performance and guide improvements, supporting your team's efforts to create high-quality content that drives growth. Here are some examples of what you can build with AirOps: * **On-Brand Content Creation**: Write high-quality, consistent content by combining AI with your brand voice, knowledge bases, and human oversight. Seamlessly publish to your CMS while maintaining complete control over quality. * **Content Refresh & Optimization**: Automatically analyze and update existing content across your CMS using real-time SEO data, competitive insights, and AI-powered recommendations. Monitor performance through our Google Search Console integration. * **Content Strategy & Research**: Build data-driven content strategies by leveraging AI analysis of search trends, competitor content, and market opportunities. Generate targeted content briefs and outlines backed by comprehensive research. [](https://docs.airops.com/#getting-started) Getting Started ----------------------------------------------------------------- [](https://docs.airops.com/chat-agents-legacy/agent-quick-start) ![Cover](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-00ac7d1e60a3f32d43aacbfdc2b9d0e6f7e8bdcd%252Fcore_four.png%3Falt%3Dmedia&width=752&dpr=4&quality=100&sign=2bbdbd2c&sv=2) [**Core Concepts**](https://docs.airops.com/getting-started/readme/readme) Dive into the core concepts of AirOps [](https://github.com/airopshq/airops-docs/blob/main/broken-reference/README.md) ![Cover](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-2cb098e92510a083335e553b0d85e6b8b0ce49da%252Fworkflow.png%3Falt%3Dmedia&width=752&dpr=4&quality=100&sign=af613c88&sv=2) [**Building your first Workflow**](https://docs.airops.com/getting-started/readme/building-your-first-workflow) Create and run your first AirOps Workflow Last updated 1 month ago Was this helpful? This site uses cookies to deliver its service and to analyze traffic. By browsing this site, you accept the [privacy policy](https://policies.gitbook.com/privacy/cookies) . AcceptReject --- # Core Concepts | AirOps Docs GitBook Assistant GitBook Assistant Working...Thinking... GitBook Assistant ##### Good night I'm here to help you with the docs. What is this page about?What should I read next?Can you give an example? Ctrli AI Based on your context Send The core concepts of AirOps work together to help you build AI-powered content workflows. These four components are the building blocks for creating and scaling your content operations while maintaining quality and brand voice. ![Cover](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-5e100a0f3364f343b6335ee0eca8b00cb8cff3fd%252Fyour_data.png%3Falt%3Dmedia&width=752&dpr=4&quality=100&sign=495efe95&sv=2) [**Your Data**](https://docs.airops.com/your-data/brand-kit) Upload your brand information, upload files, and connect data sources ![Cover](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-2cb098e92510a083335e553b0d85e6b8b0ce49da%252Fworkflow.png%3Falt%3Dmedia&width=752&dpr=4&quality=100&sign=af613c88&sv=2) [**Workflows**](https://docs.airops.com/building-workflows/workflow-concepts) Build powerful AI-powered workflows with an intuitive interface ![Cover](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-d30e8602c8dcff56c17d80cde633e356bd3b4096%252Fgrid.png%3Falt%3Dmedia&width=752&dpr=4&quality=100&sign=c5dd8ee7&sv=2) [**Grids**](https://docs.airops.com/grids/create-a-grid) Run workflows in bulk and interact with their outputs ![Cover](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-c4c1214ba51af16ca9c337d27d98ffbcea3a3dd4%252Fmodels.png%3Falt%3Dmedia&width=752&dpr=4&quality=100&sign=335296a6&sv=2) [**Integrations**](https://docs.airops.com/building-workflows/workflow-steps/integrations) Use the latest AI models and connect your favorite tools [](https://docs.airops.com/getting-started/readme/readme#questions) Questions? ----------------------------------------------------------------------------------- Feel free to reach out to us. We are available on Live Chat to answer questions working hours EST. If you would like to discuss more support from our team, please get in contact with us. ![](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-39acf0f9c4e4dd96ec4cce43dada9ff4b99122e4%252FCleanShot%25202025-02-23%2520at%252018.03.58%25402x.png%3Falt%3Dmedia&width=768&dpr=4&quality=100&sign=5b1d0682&sv=2) [](https://docs.airops.com/getting-started/readme/readme#join-the-builder-community) Join the Builder Community -------------------------------------------------------------------------------------------------------------------- Interested in learning how to use AirOps to build your use cases? Join our [AirOps Builders Slack channel](https://join.slack.com/t/airopsbuilders/shared_invite/zt-26pxgdmvk-dyn3pCdJ4E5YGv1zVRkh2Q) to connect with us further! Last updated 10 months ago Was this helpful? * [Questions?](https://docs.airops.com/getting-started/readme/readme#questions) * [Join the Builder Community](https://docs.airops.com/getting-started/readme/readme#join-the-builder-community) Was this helpful? --- # Knowledge Bases | AirOps Docs GitBook Assistant GitBook Assistant Working...Thinking... GitBook Assistant ##### Good night I'm here to help you with the docs. What is this page about?What should I read next?Can you give an example? Ctrli AI Based on your context Send ![](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-b2911453009393ae0a04493b33ed648bc8a5182e%252FCleanShot%25202025-02-23%2520at%252017.54.24%25402x.png%3Falt%3Dmedia&width=768&dpr=4&quality=100&sign=167da009&sv=2) [](https://docs.airops.com/your-data/memory-stores#what-is-a-knowledge-base) What is a Knowledge Base? ----------------------------------------------------------------------------------------------------------- Knowledge Bases allow you to store and selectively retrieve context from larger bodies of relevant information, greatly improving the quality of your LLM outputs. By importing structured and unstructured data—such as blog content, product catalogs, internal documentation, or customer support materials—you can provide your LLM-powered workflows with deeper context and unlock higher quality responses. You can import data from a variety of sources, including file uploads (PDFs, CSVs, text documents, images), web scraping, Google Drive, SQL databases, and Shopify. At the core of Knowledge Bases is Semantic Search, a powerful retrieval method that returns the most similar content based on meaning rather than just keyword matching. This means that even if your query isn’t an exact match, AirOps can still find and surface related content. For example, if you’re writing an article on chocolate desserts, the system might retrieve content on chocolate cakes, different types of chocolate, and even related dessert recipes—helping you enrich your prompts with the most useful and contextually relevant information. [](https://docs.airops.com/your-data/memory-stores#creating-a-knowledge-base) Creating a Knowledge Base ------------------------------------------------------------------------------------------------------------ Setting up a Knowledge Base is easy. All you need to have ready is your content so you can upload it: Last updated 10 months ago Was this helpful? * [What is a Knowledge Base?](https://docs.airops.com/your-data/memory-stores#what-is-a-knowledge-base) * [Creating a Knowledge Base](https://docs.airops.com/your-data/memory-stores#creating-a-knowledge-base) Was this helpful? --- # Brand Kits | AirOps Docs GitBook Assistant GitBook Assistant Working...Thinking... GitBook Assistant ##### Good night I'm here to help you with the docs. What is this page about?What should I read next?Can you give an example? Ctrli AI Based on your context Send ![](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-e153f34c559357579a465a285199d94af22800ed%252FCleanShot%25202025-02-23%2520at%252018.02.05%25402x.png%3Falt%3Dmedia&width=768&dpr=4&quality=100&sign=88a2c60d&sv=2) [](https://docs.airops.com/your-data/brand-kit#what-is-a-brand-kit) What is a Brand Kit? --------------------------------------------------------------------------------------------- **Brand kits are portable personas that allow you to centrally store, manage, and update key contextual information for your LLM-powered workflows.** They provide a structured way to maintain and supply essential context about your brand, product, customer, and business, ensuring that any LLM within AirOps has the necessary context to generate content that aligns with your voice and objectives. By using a brand kit, you can define and improve the context base that trains the LLM on unique characteristics of your business, ensuring that LLM outputs remain consistent, accurate, and on-brand across different workflows. Brand kits are centrally managed, meaning that as new insights are added—such as frequently asked questions, updated product details, or refined brand messaging—you can update the kit in one place, and all linked workflows will inherit the changes automatically. Each brand kit includes a default set of structured fields designed to capture core brand attributes. Additionally, you can define custom fields to support unique business needs. These fields can be referenced in their entirity—when applying an entire brand kit to an LLM call—or selectively for more targeted LLM calls. [](https://docs.airops.com/your-data/brand-kit#creating-a-brand-kit) Creating a Brand Kit ---------------------------------------------------------------------------------------------- [](https://docs.airops.com/your-data/brand-kit#brand-kit-variables) Brand Kit Variables -------------------------------------------------------------------------------------------- ### [](https://docs.airops.com/your-data/brand-kit#brand-attributes) Brand Attributes Attribute Default Variable Usage **Brand URL** `{{brand_kit.brand_url}}` Use the brand URL when referring to the brand to help provide context about the brand. **Brand Name** `{{brand_kit.brand_name}}` Use the brand name consistently throughout the content to maintain brand recognition. **About the Brand** `{{brand_kit.brand_about}}` Refer to the "About the Brand" section when creating content that requires background information or context about the brand and its offerings. **Customer Profile** `{{brand_kit.brand_customer}}` Use the customer profile when creating content to ensure that the messaging and tone are tailored to the brand's target audience. **Competitors** `{{brand_kit.brand_competitors}}` Be aware of the brand's competitors when creating content to differentiate the brand. **Brand Point of View** `{{brand_kit.brand_point_of_view}}` Incorporate the brand's mission and core values into the content to align with the brand's overall messaging, philosophy, and positioning. ### [](https://docs.airops.com/your-data/brand-kit#writing-style-attributes) Writing Style Attributes Attribute Default Variable Usage **Author Persona** `{{brand_kit.writing_persona}}` Use the writing persona in the `System` prompt of the Large Language Model step to maintain a consistent writing style. **Tone of Voice** `{{brand_kit.writing_tone}}` Adhere to the specified tone of voice when creating content to ensure that the brand's personality and style are consistently conveyed. **Call-to-Action (CTA) Text** `{{brand_kit.writing_cta}}` Use the brand's primary CTA text at the end of content to encourage users to take a specific action, such as signing up for the product. **CTA Destination** `{{brand_kit.writing_cta_url}}` Link the CTA text to the specified destination URL to direct users to the appropriate page or resource. ### [](https://docs.airops.com/your-data/brand-kit#writing-sample-attributes) Writing Sample Attributes Attribute Default Variable Usage **Writing Sample URL** `{{brand_kit.writing_sample_url}}` AirOps uses the writing sample URL to scrape the best example of ideal content, which is used for k-shot prompting during content generation. If the article cannot be scraped, we return a default article. **Writing Sample Title** `{{brand_kit.writing_sample_title}}` Use the writing sample title when creating a User-Assistant pair or k-shot prompting. **Writing Sample Outline** `{{brand_kit.writing_sample_outline}}` Use the writing sample outline when creating a User-Assistant pair in order to help the model understand the structure and organization of the brand's preferred content format. **Writing Sample Body** `{{brand_kit.writing_sample_body}}` Use the writing sample body when creating a User-Assistant pair in order to help the model understand the brand's writing style and tone. ### [](https://docs.airops.com/your-data/brand-kit#custom-attributes) Custom Attributes You can also add and name your own variables in Brand Kits at the bottom of the page. Last updated 2 months ago Was this helpful? * [What is a Brand Kit?](https://docs.airops.com/your-data/brand-kit#what-is-a-brand-kit) * [Creating a Brand Kit](https://docs.airops.com/your-data/brand-kit#creating-a-brand-kit) * [Brand Kit Variables](https://docs.airops.com/your-data/brand-kit#brand-kit-variables) * [Brand Attributes](https://docs.airops.com/your-data/brand-kit#brand-attributes) * [Writing Style Attributes](https://docs.airops.com/your-data/brand-kit#writing-style-attributes) * [Writing Sample Attributes](https://docs.airops.com/your-data/brand-kit#writing-sample-attributes) * [Custom Attributes](https://docs.airops.com/your-data/brand-kit#custom-attributes) Was this helpful? --- # Building your First Workflow | AirOps Docs GitBook Assistant GitBook Assistant Working...Thinking... GitBook Assistant ##### Good night I'm here to help you with the docs. What is this page about?What should I read next?Can you give an example? Ctrli AI Based on your context Send ![](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-664d15e5d07c9d8c742d017f8e8c852ed7d8832c%252FCleanShot%25202025-02-28%2520at%252005.43.36%25402x.png%3Falt%3Dmedia&width=768&dpr=4&quality=100&sign=40fa0dbc&sv=2) [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#building-your-first-airops-workflow-keyword-serp-researcher) 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. [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#interactive-tutorial) Interactive Tutorial ------------------------------------------------------------------------------------------------------------------------------ [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-by-step-guide) Step-by-Step Guide -------------------------------------------------------------------------------------------------------------------------- ### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#creating-the-workflow) Creating the Workflow #### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-1-create-a-new-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 ![](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-c16b9fd6a8bfab592b0250ada648bfc5daed737a%252FCleanShot%25202025-02-28%2520at%252005.55.08%25402x.png%3Falt%3Dmedia&width=768&dpr=4&quality=100&sign=15df7bc6&sv=2) #### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-2-configure-your-workflow-input) 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 ![](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-9b8f1147e78adfe9664b67a6f199f565400797b5%252FCleanShot%25202025-02-28%2520at%252005.54.25%25402x.png%3Falt%3Dmedia&width=768&dpr=4&quality=100&sign=4ad94da&sv=2) ### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#setting-up-the-google-search-step) Setting Up the Google Search Step #### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-1-add-a-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 #### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-2-configure-the-google-search-step) 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 ![](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-3ac79f9094894de8ecea9a93228c2841745ee6fc%252FCleanShot%25202025-02-28%2520at%252005.55.46%25402x.png%3Falt%3Dmedia&width=768&dpr=4&quality=100&sign=d9052402&sv=2) ### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#creating-the-llm-analysis-step) Creating the LLM Analysis Step #### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-1-add-a-prompt-llm-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 #### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-2-configure-the-llm-model) 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 ![](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-8af0cc54f204e8f8359bdd926b119302722ead15%252FCleanShot%25202025-02-28%2520at%252005.56.23%25402x.png%3Falt%3Dmedia&width=768&dpr=4&quality=100&sign=f27360&sv=2) #### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-3-craft-your-llm-prompt) 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: 1. Notice how this prompt references both the keyword input (`{{ keyword }}`) and the output from the previous Google Search step (`{{ step_1.output }}`) ### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#testing-and-publishing-your-workflow) Testing and Publishing Your Workflow #### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-1-test-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 #### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-2-publish-your-workflow) 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 ![](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-d6d0fd12845d8c7e36765281369257aa8bc851ec%252FCleanShot%25202025-02-28%2520at%252005.56.46%25402x.png%3Falt%3Dmedia&width=768&dpr=4&quality=100&sign=5c3d8133&sv=2) ### [](https://docs.airops.com/getting-started/readme/building-your-first-workflow#you-did-it) You did it 🎉 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. Last updated 10 months ago Was this helpful? * [Building Your First AirOps Workflow: Keyword SERP Researcher](https://docs.airops.com/getting-started/readme/building-your-first-workflow#building-your-first-airops-workflow-keyword-serp-researcher) * [Interactive Tutorial](https://docs.airops.com/getting-started/readme/building-your-first-workflow#interactive-tutorial) * [Step-by-Step Guide](https://docs.airops.com/getting-started/readme/building-your-first-workflow#step-by-step-guide) * [Creating the Workflow](https://docs.airops.com/getting-started/readme/building-your-first-workflow#creating-the-workflow) * [Setting Up the Google Search Step](https://docs.airops.com/getting-started/readme/building-your-first-workflow#setting-up-the-google-search-step) * [Creating the LLM Analysis Step](https://docs.airops.com/getting-started/readme/building-your-first-workflow#creating-the-llm-analysis-step) * [Testing and Publishing Your Workflow](https://docs.airops.com/getting-started/readme/building-your-first-workflow#testing-and-publishing-your-workflow) * [You did it 🎉](https://docs.airops.com/getting-started/readme/building-your-first-workflow#you-did-it) Was this helpful? Copy 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. --- # Knowledge Base Search | AirOps Docs GitBook Assistant GitBook Assistant Working...Thinking... GitBook Assistant ##### Good night I'm here to help you with the docs. What is this page about?What should I read next?Can you give an example? Ctrli AI Based on your context Send [](https://docs.airops.com/your-data/memory-stores/knowledge-base-search#knowledge-base-search) Knowledge Base Search -------------------------------------------------------------------------------------------------------------------------- AirOps' Knowledge Base search feature uses semantic search to find information based on meaning rather than exact keyword matches. When you search, the system returns the most relevant chunks of content from your documents, not necessarily entire files or articles, making it easier to pinpoint specific information. You can test this functionality using the "Search Test" button for any Knowledge Base you've created, allowing you to see how effectively the system retrieves contextually relevant information from your data. This approach ensures you get precise, focused results that address your query's intent rather than just matching words. [](https://docs.airops.com/your-data/memory-stores/knowledge-base-search#what-is-semantic-search) What is Semantic Search? ------------------------------------------------------------------------------------------------------------------------------- Semantic databases differ from normal keyword-based databases like SQL. They return results with the closest semantic meaning, not just exact matches. For example, searching for "vanilla ice cream" would return results like "vanilla icecream, vanilla custard, chocolate icecream, icecream sundae". It's great for retrieval use cases where you want to find content relevant to a particular topic or user request and is the foundation of every single chatbot "trained on your data". Last updated 10 months ago Was this helpful? * [Knowledge Base Search](https://docs.airops.com/your-data/memory-stores/knowledge-base-search#knowledge-base-search) * [What is Semantic Search?](https://docs.airops.com/your-data/memory-stores/knowledge-base-search#what-is-semantic-search) Was this helpful? --- # Knowledge Base API | AirOps Docs GitBook Assistant GitBook Assistant Working...Thinking... GitBook Assistant ##### Good night I'm here to help you with the docs. What is this page about?What should I read next?Can you give an example? Ctrli AI Based on your context Send The AirOps REST API allows users to both read and write to their Knowledge Bases as needed. [](https://docs.airops.com/your-data/memory-stores/memory-stores-api#using-the-rest-api) Using the REST API ---------------------------------------------------------------------------------------------------------------- You can call the Knowledge Bases REST API directly from the AirOps UI. To get started, simply navigate to the desired Knowledge Base and click on its "Rest API" tab as shown below: [](https://docs.airops.com/your-data/memory-stores/memory-stores-api#supported-api-calls) Supported API Calls ------------------------------------------------------------------------------------------------------------------ Currently, the AirOps Knowledge Bases API supports the following calls: 1. **Search** -- a read-only endpoint that performs a semantic search with filtering through the Knowledge Base. See our document on [Knowledge Bases Metadata](https://docs.airops.com/your-data/memory-stores/memory-stores-metadata) for more details on filtering. 2. **Insert** -- a write endpoint to populate your Knowledge Base with additional content 3. **Update** -- a write endpoint that lets you edit the underlying information of your connected content 4. **Delete** -- a write endpoint to remove content from your Knowledge Bases The "REST API" tab shown above walks through how to execute each of these calls, as well as the expected results. If there are any additional functions that are critical to your business, but currently missing an API call to help you automate, we would love get your feedback! Last updated 10 months ago Was this helpful? * [Using the REST API](https://docs.airops.com/your-data/memory-stores/memory-stores-api#using-the-rest-api) * [Supported API Calls](https://docs.airops.com/your-data/memory-stores/memory-stores-api#supported-api-calls) Was this helpful? --- # Add Data | AirOps Docs GitBook Assistant GitBook Assistant Working...Thinking... GitBook Assistant ##### Good night I'm here to help you with the docs. What is this page about?What should I read next?Can you give an example? Ctrli AI Based on your context Send ![](https://docs.airops.com/~gitbook/image?url=https%3A%2F%2F3762890407-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FX2n5yPRPynbnWuO4SH0M%252Fuploads%252Fgit-blob-6c5ba14d5748be3d28a4b27425fac89a66d84f7e%252FCleanShot%25202025-02-23%2520at%252017.59.34%25402x.png%3Falt%3Dmedia&width=768&dpr=4&quality=100&sign=7800a43e&sv=2) [](https://docs.airops.com/your-data/memory-stores/add-data#uploading-data-to-the-knowledge-base) Uploading Data to the Knowledge Base ------------------------------------------------------------------------------------------------------------------------------------------- AirOps Knowledge Bases support a wide variety of file formats including PDFs, CSVs, text files, HTML, images, Microsoft Office documents, and more, with additional options to import content directly from Sitemaps, Google Drive, SQL databases, or even Shopify! You can easily add content by uploading files individually, scraping websites, or importing data through the intuitive interface, creating a rich resource of searchable information for your AI workflows. [](https://docs.airops.com/your-data/memory-stores/add-data#supported-content-types) Supported Content Types ----------------------------------------------------------------------------------------------------------------- AirOps currently supports the following content types for populating Knowledge Bases: 1. **File Uploads** — Add individual files. Supported formats include: .pdf, .csv, .txt, .text, .log, .html, .htm, .md, .org, .odt, .ppt, .pptx, .rst, .rtf, .tsv, .doc, .docx, .xml, .png, .jpg, .jpeg, .gif, .webp, .eml, .msg, .epub. 2. **Web Page Scrape** — Import content from a sitemap's hierarchy of pages to crawl 1. **Import Sitemap** — Import content from a sitemap's hierarchy of pages to crawl 2. **Import from URL** — Import content directly from a specific URL 3. **Sync Google Drive File** — Connect a Google Drive file (supports Google Docs, Google Sheets, and .pdf files) 4. **Sync SQL Database** — Import data directly from your connected database(s) via a SQL query 5. **Import from Shopify** — Import products and collections from your Shopify store Currently, individual documents must be loaded one-at-a-time. If you have more advanced content load requirements, please speak with our team. Last updated 10 months ago Was this helpful? * [Uploading Data to the Knowledge Base](https://docs.airops.com/your-data/memory-stores/add-data#uploading-data-to-the-knowledge-base) * [Supported Content Types](https://docs.airops.com/your-data/memory-stores/add-data#supported-content-types) Was this helpful? ---