Host your own AI deep research agent with n8n, Apify and OpenAI o3
This template attempts to replicate OpenAI's DeepResearch feature which, at time of writing, is only available to their pro subscribers. > An agent that uses reasoning to synthesize large amount of online information and complete multi-step research tasks for you. Source Though the inner workings of DeepResearch have not been made public, it is presumed the feature relies on the ability to deep search the web, scrape web content and invoking reasoning models to generate reports. All of which n8n is really good at! Using this workflow, n8n users can enjoy a variation of the Deep Research experience for themselves and their teams at a fraction of the cost. Better yet, learn and customise this Deep Research template for their businesses and/or organisations. Check out the generated reports here: https://jimleuk.notion.site/19486dd60c0c80da9cb7eb1468ea9afd?v=19486dd60c0c805c8e0c000ce8c87acf How it works A form is used to first capture the user's research query and how deep they'd like the researcher to go. Once submitted, a blank Notion page is created which will later hold the final report and the researcher gets to work. The user's query goes through a recursive series of web serches and web scraping to collect data on the research topic to generate partial learnings. Once complete, all learnings are combined and given to a reasoning LLM to generate the final report. The report is then written to the placeholder Notion page created earlier. How to use Duplicate this Notion database template and make sure all Notion related nodes point to it. Sign-up for APIFY.com API Key for web search and scraping services. Ensure you have access to OpenAI's o3-mini model. Alternatively, switch this out for o1 series. You must publish this workflow and ensure the form url is publically accessible. On depth & breadth configuration For more detailed reports, increase depth and breadth but be warned the workflow will take exponentially longer and cost more to complete. The recommended defaults are usually good enough. Depth=1 & Breadth=2 - will take about 5 - 10mins. Depth=1 & Breadth=3 - will take about 15 - 20mins. Dpeth=3 & Breadth=5 - will take about 2+ hours! Customising this workflow I deliberately chose not to use AI-powered scrapers like Firecrawl as I felt these were quite costly and quotas would be quickly exhausted. However, feel free to switch web search and scraping services which suit your environment. Maybe you don't decide to source the web and instead, data collection comes from internal documents instead. This template gives you freedom to change this. Experiment with different Reasoning/Thinking models such as Deepseek and Google's Gemini 2.0. Finally, the LLM prompts could definitely be improved. Refine them to fit your use-case. Credits This template is largely based off the work by David Zhang (dzhng) and his open source implementation of Deep Research: https://github.com/dzhng/deep-research
By JimleukQualify new leads in Google Sheets via OpenAI's GPT-4
This n8n workflow was developed to evaluate and categorize incoming leads based on certain criteria. The workflow is triggered by adding a new row in a Google Sheets document. The workflow uses the OpenAI node to process the lead information. The system query contains detailed qualification rules and the response format. The user message contains the data for the individual lead. The JSON response from the OpenAI node is then processed by the Edit Fields node to extract the response. This response is merged together with the original lead data by the Merge node. Finally, the Google Sheets node updates the original lead entry in the Google Sheets document with the qualification result ("qualified" or "not qualified") in a separate column. This allows for easy tracking and sorting of the qualified leads.
By YuliaApi schema extractor
This workflow automates the process of discovering and extracting APIs from various services, followed by generating custom schemas. It works in three distinct stages: research, extraction, and schema generation, with each stage tracking progress in a Google Sheet. đ Jim Le deserves major kudos for helping to build this sophisticated three-stage workflow that cleverly automates API documentation processing using a smart combination of web scraping, vector search, and LLM technologies. How it works Stage 1 - Research: Fetches pending services from a Google Sheet Uses Google search to find API documentation Employs Apify for web scraping to filter relevant pages Stores webpage contents and metadata in Qdrant (vector database) Updates progress status in Google Sheet (pending, ok, or error) Stage 2 - Extraction: Processes services that completed research successfully Queries vector store to identify products and offerings Further queries for relevant API documentation Uses Gemini (LLM) to extract API operations Records extracted operations in Google Sheet Updates progress status (pending, ok, or error) Stage 3 - Generation: Takes services with successful extraction Retrieves all API operations from the database Combines and groups operations into a custom schema Uploads final schema to Google Drive Updates final status in sheet with file location Ideal for: Development teams needing to catalog multiple APIs API documentation initiatives Creating standardized API schema collections Automating API discovery and documentation Accounts required: Google account (for Sheets and Drive access) Apify account (for web scraping) Qdrant database Gemini API access Set up instructions: Prepare your Google Sheets document with the services information. Here's an example of a Google Sheet â you can copy it and change or remove the values under the columns. Also, make sure to update Google Sheets nodes with the correct Google Sheet ID. Configure Google Sheets OAuth2 credentials, required third-party services (Apify, Qdrant) and Gemini. Ensure proper permissions for Google Drive access.
By Polina MedvedievaSimple social: Instagram single image post with Facebook API
Simple Social: Instagram Single Image Post with Facebook API Who is this workflow for? This workflow is designed for businesses, social media managers, content creators, and developers who need to automate the process of posting single images to Instagram using the Facebook API. It is ideal for anyone looking to streamline their social media posting process, saving time and ensuring consistent content delivery. Use Case / Problem Solved Manually posting images and captions on Instagram can be time-consuming, especially for businesses and content creators managing multiple accounts. This workflow automates the process from image preparation to publishing, reducing manual effort and increasing efficiency. What this workflow does Trigger Initialization: The workflow starts with a manual trigger that can be adapted to other triggers (e.g., HTTP webhook or schedule). Set Parameters: The workflow includes a node that sets essential parameters, such as the image URL, Instagram business account ID, and caption. Prepare Instagram Media: A node prepares the media for upload using the Facebook API, sending the image and caption for pre-publication processing. Check Media Upload Status: The workflow verifies if the media preparation is complete. Conditional Check: If the media preparation is successful, the workflow proceeds to publish; otherwise, it triggers an error-handling path. Publish Media: The media is published on Instagram if the conditions are met. Post-Publish Check: The workflow checks the status after publication. Conditional Check for Publication: If the publication status is "PUBLISHED," it triggers a success path; otherwise, it triggers a failure handling. Email Notifications: The workflow sends email notifications to indicate successful or unsuccessful outcomes. Setup Here is a quick video in italian language with sub eng(https://youtu.be/obWJFJvg_6g) Add API Credentials: Ensure that valid Facebook API credentials are added and configured for use. Permissions Required: Ensure your app has the necessary permissions (adsmanagement, businessmanagement, instagrambasic, instagramcontentpublish, pagesread_engagement). App review may be required for external user access. Node Configuration: Customize the Set Instagram Parameters node to specify the image URL, caption, and Instagram business account ID. Trigger Adaptation: Adapt the initial trigger if needed to fit your workflow's requirements (e.g., schedule, webhook). How to customize this workflow Change the Image URL and Caption: Modify the Set Instagram Parameters node to change the image and caption. Trigger Customization: Replace the manual trigger with other triggers like a webhook to automate posting based on external events. Notifications: Adjust the email nodes to send customized messages or trigger other workflows based on the outcome. Limitations Image Format: Only JPEG images are supported. Extended JPEG formats such as MPO and JPS are not compatible. Unsupported Tags: Shopping tags, branded content tags, and filters are not supported. Instagram TV: Publishing to Instagram TV is not supported. Rate Limit: Instagram accounts are limited to 50 API-published posts within a rolling 24-hour period. Carousels count as a single post. Check usage with GET /{ig-user-id}/contentpublishinglimit. Example Usage Imagine managing a business account that needs consistent posts. You can schedule this workflow or trigger it manually to automatically post images with captions at the right time, ensuring that your audience stays engaged without manual posting efforts.
By Edoardo GuzziGenerate personalized sales emails with LinkedIn data & Claude 3.7 via OpenRouter
How it works The automation loads rows from a Google Sheet of leads that you want to contact. It makes a Google search via Apify for LinkedIn links based on the First name / Last name / Company. Another Apify actor fetches the right LinkedIn profile based on the first profile which is retuned The same process is done for the company that the lead works for, giving extra context. If the lead has a current company listed on their LinkedIn, we use that URL to do the lookup, rather than doing a separate Google search. A call is made to OpenRouter to get an LLM to generate an email based on a prompt designed to do personalized outreach. An email is sent via a Gmail node. Set up steps Connect your Google Sheets + Gmail accounts to use these APIs. Make an account with Apify and enter your credentials. Set your details in the "Set My Data" node to customize the workflow to revolve around your company + value proposition. I would recommend changing the prompt in the "Generate Personalized Email" node to match the tone of voice that you want your agent to have. You can change the guidelines to e.g. change whether the agent introduces itself, and give more examples in the style you want to make the output better.
By Adam JanesBuild an OpenAI assistant with Google Drive integration
Workflow Overview This workflow automates the creation and management of a custom OpenAI Assistant for a travel agency ("Travel with us"), leveraging Google Drive for document storage. --- How It Works Create the OpenAI Assistant Node: OpenAI Action: Creates a custom assistant named "Travel with us" Assistant using the gpt-4o-mini model. Instructions: Respond only using the provided document (e.g., agency-specific info). Stay friendly, brief, and focused on travel-related queries. Ignore irrelevant questions politely. Credentials: Requires OpenAI API key. Upload Agency Document Google Drive Node: Action: Downloads a Google Doc as a PDF. OpenAI2 Node: Action: Uploads the PDF to OpenAI with purpose: "assistants". Output: Generates a file_id. Update the Assistant with the Document OpenAI Node: Action: Updates the assistant to include the uploaded file. Chat Interaction Chat Trigger: Activates when a message is received ("When chat message received"). OpenAI Assistant Node: Action: Uses the updated assistant to respond to user queries. Memory: Window Buffer Memory retains chat context for coherent conversations. --- Set Up Steps Prepare the Document: Store your travel agency guide in Google Drive (e.g., as a Google Doc). Update the Google Drive node with your documentâs ID. Configure Credentials: Google Drive: Connect via OAuth2 (googleDriveOAuth2Api). OpenAI: Add your API key to all OpenAI nodes. Customize the Assistant: Modify the instructions in the OpenAI node to reflect your agencyâs needs. Ensure the document includes FAQs, policies, and travel info. Test the Workflow: Trigger manually ("Test workflow") to create the assistant and upload the file. Send a chat message (e.g., "What are your travel packages?") to test responses. --- Dependencies Google Drive Account: To store and retrieve the agency document. OpenAI API Access: For assistant creation and file uploads. --- Need help customizing? Contact me for consulting and support or add me on Linkedin.
By DavidePersonal shopper chatbot for WooCommerce with RAG using Google Drive and openAI
This workflow combines OpenAI, Retrieval-Augmented Generation (RAG), and WooCommerce to create an intelligent personal shopping assistant. It handles two scenarios: Product Search: Extracts user intent (keywords, price ranges, SKUs) and fetches matching products from WooCommerce. General Inquiries: Answers store-related questions (e.g., opening hours, policies) using RAG and documents stored in Google Drive. --- How It Works Chat Interaction & Intent Detection Chat Trigger: Starts when a user sends a message ("When chat message received"). Information Extractor: Uses OpenAI to analyze the message and determine if the user is searching for a product or asking a general question. Extracts: search (true/false). keyword, priceRange, SKU, category (if product-related). Example: json { "search": true, "keyword": "red handbags", "priceRange": { "min": 50, "max": 100 }, "SKU": "BAG123", "category": "women's accessories" } Product Search (WooCommerce Integration) AI Agent: If search: true, routes the request to the personal_shopper tool. WooCommerce Node: Queries the WooCommerce store using extracted parameters (keyword, priceRange, SKU). Filters products in stock (stockStatus: "instock"). Returns matching products (e.g., "red handbags under âŹ100"). General Inquiries (RAG System) RAG Tool: If search: false, uses the Qdrant Vector Store to retrieve store information from documents. Google Drive Integration: Documents (e.g., store policies, FAQs) are stored in Google Drive. Downloaded, split into chunks, and embedded into Qdrant for semantic search. OpenAI Chat Model: Generates answers based on retrieved documents (e.g., "Our store opens at 9 AM"). Set Up Steps Configure the RAG System Google Drive Setup: Upload store documents . Update the Google Drive2 node with your folder ID. Qdrant Vector Database: Clean the collection (update Qdrant Vector Store node with your URL). Use Embeddings OpenAI to convert documents into vectors. Configure OpenAI & WooCommerce OpenAI Credentials: Add your API key to all OpenAI nodes (OpenAI Chat Model, Embeddings OpenAI, etc.). WooCommerce Integration: Connect your WooCommerce store (credentials in the personal_shopper node). Ensure product data is synced and accessible. Customize the AI Agent Intent Detection: Modify the Information Extractorâs system prompt to align with your storeâs terminology. RAG Responses: Update the tool description to reflect your storeâs documents. --- Notes This template is ideal for e-commerce businesses needing a hybrid assistant for product discovery and customer support. Need help customizing? Contact me for consulting and support or add me on Linkedin.
By DavideWebsite scam risk detector with GPT-4o and SerpAPI
What It Does This intelligent workflow simplifies the complex task of determining whether a website is legitimate or potentially a scam. By simply submitting a URL through a form, the system initiates a multi-agent evaluation process. Four dedicated AI agentsâeach powered by GPT-4o and connected to SerpAPIâanalyze different dimensions of the website: domain and technical details, search engine signals, product and pricing patterns, and on-site content analysis. Their findings are then passed to a fifth AI agent, the Analyzer, powered by GPT-4o mini, which consolidates the data, scores the site on a scale of 1â10 for scam likelihood, and presents the findings in a clear, structured format for the user. Who It's For This workflow is ideal for anyone who needs to quickly and reliably assess the trustworthiness of a website. Whether you're a consumer double-checking a store before making a purchase, a small business owner validating supplier sites, a cybersecurity analyst conducting threat assessments, or a developer building fraud detection into your platform â this tool offers fast, AI-powered insights without the need for manual research or technical expertise. It's designed for both individuals and teams who value accurate, scalable scam detection. How It Works The process begins with a simple form submission where the user enters the URL of the website they want to investigate. Once submitted, the workflow activates four specialized AI agentsâeach powered by GPT-4o and connected to SerpAPIâto independently analyze the site from different angles: Agent 1 examines domain age, SSL certificates, and TLD trustworthiness. Agent 2 reviews search engine results, forum mentions, and public scam reports. Agent 3 analyzes product pricing patterns and brand authenticity. Agent 4 assesses on-site content quality, grammar, legitimacy of claims, and presence of business info. Each agent returns its findings, which are then aggregated and passed to a fifth AI agentâthe Analyzer. This final agent, powered by GPT-4o mini, evaluates all the input, assigns a scam likelihood score from 1 to 10, and compiles a neatly formatted summary with organized insights and a disclaimer for context. Set UP You will need to obtain an Open AI API key from platform.openai.com/api-keys After you obtain this Open AI API key you will need to connect it to the Open AI Chat Model for all of the Tools agents (Analyzer, Domain & Technical Details, Search Engine Signals, Product & Pricing Patterns, and Content Analysis Tools Agents). You will now need to fund your Open AI account. GPT 4o costs ~$0.01 to run the workflow. Next you will need to create a SerpAPI account at https://serpapi.com/users/sign_up After you create an account you will need to obtain a SerpAPI key. You will then need to use this key to connect to the SerpAPI tool for each of the tools agents (Domain & Technical Details, Search Engine Signals, Product & Pricing Patterns, and Content Analysis Tools Agents) Tip: SerpAPI will allow you to run 100 free searches each month. This workflow uses ~5-15 SerpAPI searches per run. If you would like to utilize the workflow more than that each month, create multiple SerpAPI accounts and have an API key for each account. When you utilize all 100 free searches for an account, switch to the API key for another account within the workflow. Disclaimer This tool is designed to assist in evaluating the potential risk of websites using AI-generated insights. The scam likelihood score and analysis provided are based on publicly available information and should not be considered a definitive or authoritative assessment. This tool does not guarantee the accuracy, safety, or legitimacy of any website. Users should perform their own due diligence and use independent judgment before engaging with any site. N8N, OpenAI, its affiliates, and the creators of this workflow are not responsible for any loss, damages, or consequences arising from the use of this tool or the actions taken based on its results.
By AiAgentFlux dev image generation (Fal.ai) to Google Drive
This workflow automates AI-based image generation using the Fal.ai Flux API. Define custom prompts, image parameters, and effortlessly generate, monitor, and save the output directly to Google Drive. Streamline your creative automation with ease and precision. Who is this for? This template is for content creators, developers, automation experts, and creative professionals looking to integrate AI-based image generation into their workflows. Itâs ideal for generating custom visuals with the Fal.ai Flux API and automating storage in Google Drive. What problem is this workflow solving? Manually generating AI-based images, checking their status, and saving results can be tedious. This workflow automates the entire process â from requesting image generation, monitoring its progress, downloading the result, and saving it directly to a Google Drive folder. What this workflow does Sets Custom Image Parameters: Allows you to define the prompt, resolution, guidance scale, and steps for AI image generation. Sends a Request to Fal.ai: Initiates the image generation process using the Fal.ai Flux API. Monitors Image Status: Checks for completion and waits if needed. Downloads the Generated Image: Fetches the completed image once ready. Saves to Google Drive: Automatically uploads the generated image to a specified Google Drive folder. Setup Prerequisites: ⢠Fal.ai API Key: Obtain it from the Fal.ai platform and set it as the Authorization header in HTTP Header Auth credentials. ⢠Google Drive OAuth Credentials: Connect your Google Drive account in n8n. Configuration: ⢠Update the âEdit Fieldsâ node with your desired image parameters: ⢠Prompt: Describe the image (e.g., âThai young woman net idol 25 yrs old, walking on the streetâ). ⢠Width/Height: Define image resolution (default: 1024x768). ⢠Steps: Number of inference steps (e.g., 30). ⢠Guidance Scale: Controls image adherence to the prompt (e.g., 3.5). ⢠Set your Google Drive folder ID in the âGoogle Driveâ node to save the image. Run the Workflow: ⢠Trigger the workflow manually to generate the image. ⢠The workflow waits, checks status, and saves the final output seamlessly. Customization ⢠Modify Image Parameters: Adjust the prompt, resolution, steps, and guidance scale in the âEdit Fieldsâ node. ⢠Change Storage Location: Update the Google Drive node with a different folder ID. ⢠Add Notifications: Integrate an email or messaging node to alert you when the image is ready. ⢠Additional Outputs: Expand the workflow to send the generated image to Slack, Dropbox, or other platforms. This workflow streamlines AI-based image generation and storage, offering flexibility and customization for creative automation.
By Sira EkabutSync Google Sheets data with MySQL
This workflow performs several data integration and synchronization tasks between Google Sheets and a MySQL database. Here is a step-by-step description of what this workflow does: Manual Trigger: The workflow starts when the user clicks "Execute Workflow." Schedule Trigger: This node schedules the workflow to run at specific intervals on weekdays (Monday to Friday) between 6 AM and 10 PM. It ensures regular data synchronization. Google Sheet Data: This node connects to a specific Google Sheets document and retrieves data from the "Form Responses 1" sheet, filtering by the "DB Status" column. SQL Get inquiries from Google: This node retrieves data from a MySQL database table named "ConcertInquiries" where the "source_name" is "GoogleForm." Rename GSheet variables: This node renames the columns retrieved from Google Sheets and transforms the data into a format suitable for MySQL, assigning a value for "source_name" as "GoogleForm." Compare Datasets: This node compares the data retrieved from Google Sheets and the MySQL database based on timestamp and source_name fields. It identifies changes and updates. No reply too long?: This node checks if there has been no reply within the last four hours, using the "timestamp" field from the Google Sheets data. DB Status assigned?: This node checks if the "DB Status" field is not empty in the compared dataset. Update GSheet status: If conditions are met in the previous nodes, this node updates the "DB Status" field in Google Sheets with the corresponding value from the MySQL dataset. DB Status in sync?: This node checks if the "source_name" field in Google Sheets is not empty. Sync MySQL data: If conditions are met in the previous nodes, this node updates the "source_name" field in the MySQL database to "GoogleFormSync." Send Notifications: If conditions are met in the "No reply too long?" node, this node sends notifications or performs actions as needed. Sticky Notes: These nodes provide additional information and documentation links for users.
By n8n TeamSuspicious login detection
This n8n workflow is designed for security monitoring and incident response when suspicious login events are detected. It can be initiated either manually from within the n8n UI for testing or automatically triggered by a webhook when a new login event occurs. The workflow first extracts relevant data from the incoming webhook payload, including the IP address, user agent, timestamp, URL, and user ID. It then splits into three parallel processing paths. In the first path, it queries GreyNoise's Community API to retrieve information about the investigated IP address. Depending on the classification and trust level received from GreyNoise, the alert is given a High, Medium, or Low priority. This priority is assigned based on the best practices documentation from GreyNoise on how to apply their data to analysis. Once a priority is assigned, a message is sent to a Slack channel to notify users about the alert. The second path involves fetching geolocation data about the IP address using IP-API's Geolocation API and merging it with data from the UserParser node. This data is then combined with the data obtained from GreyNoise. In the third path, the UserParser node queries the Userparser IP address and user agent lookup API to obtain information about the user's IP and user agent. This data is merged with the IP-API data and GreyNoise data. The workflow then checks if the IP address is considered an unknown threat by examining both the noise and riot fields from GreyNoise. If it is considered an unknown threat, the workflow proceeds to retrieve the last 10 login records for the same user from a Postgres database. If there are any discrepancies in the login information, indicating a new location or device/browser, the user is informed via email. Potential issues when setting up this workflow include ensuring that credentials are correctly entered for GreyNoise and UserParser nodes, and addressing any discrepancies in the data sources that could lead to false positives or negatives in threat detection. Additionally, the usage of hardcoded API keys should be replaced with credentials for security and flexibility. Thorough testing and validation with sample data are crucial to ensure the workflow performs as expected and aligns with security incident response procedures.
By n8n TeamAmazon affiliate marketing automation
Who this is for This workflow is for Amazon affiliate marketers and social media managers who want to quickly turn product links into engaging Facebook posts with AI-generated captions and images â fully automated. --- What this workflow does This workflow starts every time a new Product Link is added to a connected Google Sheet. It then: Extracts the ASIN from the product link. Fetches product details from Amazon using RapidAPI. Generates a short, scroll-stopping Facebook caption with OpenRouter AI. Creates a product image prompt and sends it to Google Gemini for high-quality image generation. Uploads the creative directly to Facebook via the Facebook Graph API. Marks the Google Sheet row as âDone â â after posting. The Facebook post includes: Product image (AI-enhanced) Short, benefit-focused caption with emojis Affiliate link --- Setup To set this template up, follow the sticky notes inside the workflow and: Google Sheets â Connect your sheet and ensure the columns âProduct Linkâ & âFacebook Uploadâ exist. RapidAPI â Add your API key in the âAmazon Product Detailsâ node. OpenRouter â Add credentials for caption generation. Google Gemini â Add your API key for image generation. Facebook Graph API â Connect your Facebook account for posting. --- How to customize this workflow to your needs Change the Facebook caption prompt to match your tone or branding. Adjust the AI image generation prompt to fit your preferred photography style. Modify the Google Sheet update logic if you want to track additional info (e.g., posting date, engagement stats). Switch Facebook posting to Instagram or another platform by replacing the final API call.
By Rakin Jakaria