This n8n workflow performs automated menstrual cycle tracking, reminders, and personalized wellness guidance by managing subscriber data and delivering timely emails based on each user’s cycle phase. It starts when a user submits their menstrual cycle details through a form, capturing inputs such as last period date and cycle length. The workflow calculates key cycle milestones including next period, ovulation, fertile window, and PMS phase, and stores this data in Google Sheets as a centralized database. A personalized welcome email is immediately generated and sent to the user with their cycle overview. The system then runs daily at 8 AM to evaluate each subscriber’s current cycle phase and determine whether a reminder should be sent, such as period alerts, ovulation insights, or PMS preparation tips. It ensures duplicate messages are avoided by tracking previously sent emails. Additionally, the workflow runs a weekly AI-powered wellness digest that generates personalized insights, tips, and guidance based on the user’s current cycle phase. Finally, all emails are logged and tracked to maintain consistency and provide a complete history of user engagement, enabling a fully automated and personalized menstrual wellness experience.

This n8n workflow performs automated LinkedIn lead monitoring and alerting by detecting LinkedIn notification emails and matching them against a tracked lead database. It starts when the workflow is manually triggered inside n8n, allowing users to run the alert system on demand. The workflow fetches LinkedIn notification emails from Gmail and extracts the sender names from each message. These sender names are cleaned and normalized to ensure accurate comparison. In parallel, the workflow loads a lead database from Google Sheets and processes the stored lead names along with their categories. Both datasets are then merged into a single flow where the system compares LinkedIn senders with tracked leads. When a match is found, the workflow identifies the lead and its category and triggers an alert email. Finally, the alert is sent to notify the user about the LinkedIn interaction, enabling quick follow-up on important leads without manually checking messages.

This n8n workflow performs AI-powered workflow architecture analysis by evaluating a submitted automation problem and generating a recommended workflow design. It starts when a webhook receives a POST request containing a problem description from an external source such as a form, app, or API request. The workflow extracts the problem statement from the incoming request and prepares it for AI analysis. Using an AI reasoning agent powered by GPT-4o-mini through Azure OpenAI, the system analyzes the problem to determine whether the solution requires a multi-agent architecture or a simpler n8n workflow. If a multi-agent approach is needed, the AI defines the required agents, their roles, node types, and the recommended execution order of the workflow. The AI response is then parsed and structured into clear data fields including the final decision, the list of agents, and the workflow steps. Finally, the system generates a styled HTML report that visually presents the architecture recommendation and returns it through the webhook response, allowing the requester to instantly review the suggested automation design in the browser.

This n8n workflow performs automated LinkedIn profile enrichment by converting a LinkedIn profile URL into a structured profile summary page. It starts when a webhook receives a POST request containing a LinkedIn profile URL from an external source. The workflow sends this URL to the Apollo People Match API to retrieve enriched profile and company information associated with that LinkedIn account. The returned data includes details such as name, title, email, location, company information, role history, and organization insights. The workflow then cleans and normalizes the API response to extract only the most relevant profile fields. After structuring the data, the system generates a styled HTML profile card that presents the enriched information in a clean and readable format. Finally, the workflow returns the generated HTML page through the webhook response, allowing the requester to instantly view a formatted LinkedIn profile summary in the browser without manually researching the profile.

This n8n workflow performs AI-powered workflow optimization automatically by analyzing an existing n8n workflow JSON and returning an improved version. It starts when a webhook receives a POST request containing a workflow JSON from an external source. The workflow first validates the incoming payload to ensure a proper workflow structure exists before continuing. Using an AI reasoning agent powered by GPT-4o-mini through Azure OpenAI, the system analyzes the workflow to identify improvements in node structure, execution efficiency, and overall cleanliness while keeping the functionality unchanged. The AI then generates an optimized version of the workflow. The response is cleaned and parsed into valid JSON to ensure it contains the required nodes and connections. After validation, the optimized workflow is converted into a downloadable JSON file. Finally, the workflow returns the optimized file back through the webhook response so it can be imported directly into n8n, making it easier for developers to improve their automations without manually restructuring workflows.