Ai prompt generator workflow
đ§ AI Prompt Generator Workflow â n8n Documentation Who is this for? This workflow is for AI builders, prompt engineers, developers, marketers, and no-code creators who want to convert rough user input into structured, high-quality prompts for LLMs. Itâs especially useful for tools that rely on precision prompting and want to automate the discovery of intent and constraints. --- What problem is this workflow solving? / Use case Many users struggle to write effective prompts due to vague ideas or unclear formatting needs. This workflow: Collects structured user input. Dynamically generates clarifying questions. Returns a well-formatted AI prompt based on the user's intent and context. This ensures the generated prompt is useful for downstream AI agents without requiring technical understanding from the end user. --- What this workflow does Start with a branded form UI The user is shown a styled form with questions like: What do you want to build? What tools can you access? What input can be expected? What output do you expect? Analyze and generate relevant follow-up questions The workflow sends the user's answers to Google Gemini (via LangChain) which outputs 1â3 clarifying questions. These questions are parsed into a dynamic form. Loop through and collect follow-up answers Each follow-up question is shown in a form one at a time to capture additional context. Merge all inputs The base intent and follow-up responses are merged into a single context block. Generate a final AI-ready prompt The prompt generator node formats everything into a clean, six-section structure: <constraints> <role> <inputs> <tools> <instructions> <conclusions> Display the final result The finished prompt is shown in a clean UI where users can easily copy and reuse it. --- Setup Credentials Required Google Gemini (PaLM) API credentials (already integrated as Google Gemini(PaLM) Api account 2). Form Trigger Ensure the On form submission trigger is exposed via a webhook or public endpoint (e.g. using ngrok or deployed server). Styling Custom CSS is included in all form nodes for a beautiful UI. You can modify this to match your branding. Environment This workflow is compatible with self-hosted n8n or n8n.cloud. Webhooks must be accessible to users who will fill out the form. --- How to customize this workflow to your needs Change the base questions Update the BaseQuestions form node to add or remove fields depending on your use case. Modify Gemini prompts You can edit the system prompt inside PromptGenerator to change tone, output structure, or AI instructions. Change prompt formatting If you use a different AI agent (like GPT, Claude, or Mistral), adjust the section labels and formatting to suit that agentâs expected input. Send results elsewhere Add integration nodes after PromptGenerator, such as: Google Docs / Notion (to log prompts) Gmail / Slack (to notify your team) Zapier / Make (to push to other automation flows) Skip follow-up questions (optional) If your base form collects all needed info, you can bypass the RelevantQuestions form section by modifying conditional logic. --- Example Output Prompt (Structure) <role> You are an AI assistant that converts videos into LinkedIn posts with a witty tone. </role> <inputs> - A short video (max 5 minutes) - Desired tone: witty - Style: both summary and quotes - Audience: general network </inputs> <tools> You do not have access to APIs or web search. </tools> <instructions> 1. Parse transcript. 2. Extract insights and quotes. 3. Write an engaging, witty LinkedIn post under 3000 characters. </instructions> <constraints> Avoid technical jargon. No generic intros. Make it platform-native. </constraints> <conclusions> Return a LinkedIn-ready post that starts with a hook and ends with hashtags.
By Anurag SrivastavaAutomate event scheduling from emails with Gmail & Google Calendar keywords
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. â How It Works This workflow operates as an automated personal assistant for your calendar. It listens to your Gmail inbox for new emails. When an email arrives, it checks the subject and body for keywords like "Meeting" or "Appointment." If a match is found, the workflow extracts key details from the email and automatically creates a new event on your Google Calendar, eliminating the need for manual data entry. --- Setup Steps Follow these steps to get the workflow running in your n8n instance. Prerequisites You'll need a working n8n instance and access to both your Gmail and Google Calendar accounts. Workflow Import Import the workflow's JSON file into your n8n instance. All the necessary nodes will appear on your canvas. Configure Credentials Click on the Gmail Trigger node and Google Calendar node. You will see a red error icon indicating that credentials are not set. Click on it. Click "Create new credential" and follow the instructions to connect your Gmail and Google Calendar accounts. Customize the If Node This node determines which emails will trigger a calendar event. Click on the If node. Review the Value 2 field under the conditions. This is where you specify the keywords that should trigger an event. You can add more keywords by clicking "Add Condition" and using the OR operator (e.g., add call, interview, or demo). Customize the Code Node This node extracts the event details from your email. The current code is a basic example using regular expressions to find a date and time. Click on the Code node. Review the code. You may need to adjust the regular expressions if your emails have a different format for dates and times. The node will output a JSON object containing the title, date, and time that will be used to create your calendar event. Configure the Google Calendar Node This is the final node that creates the event. Click on the Google Calendar node. In the Calendar ID field, enter the ID of the specific calendar you want the events to be created on. You can find this in your Google Calendar settings. Activate the Workflow Once all credentials and node configurations are complete, click "Save" at the top of the canvas. Finally, toggle the workflow to "Active". The workflow is now live and will automatically schedule events for you.
By MarthAI-powered calendar & meeting digest with Gmail and GPT-4o/Claude - daily brief
đ How It Works The Daily Calendar Brief is an automated n8n workflow designed to prep you each morning with a rich, executive-style email summary of your day. It pulls data from your calendar, email, and external contact sources to deliver a contextualized, prioritized briefing. Daily Trigger Runs every weekday morning at 7:00 AM using a schedule node. Calendar Parsing Grabs all Google Calendar events for the day and extracts details like: ⢠Event title, time, and duration ⢠Full attendee list ⢠Meeting description Attendee Intelligence Filters for external attendees and: ⢠Scrapes recent email threads with them ⢠Uses Hunter and LinkedIn to enrich attendee info with roles, bios, locations, and recent activity Brief Assembly Combines: ⢠Event metadata ⢠Attendee research ⢠Recent conversations Email Delivery Renders the Markdown as HTML and sends a polished email to your inbox with: ⢠Meeting timeline & attendees ⢠Key takeaways & extra context ⢠Conflicts & FYIs Setup Steps Prerequisites ⢠n8n instance (self-hosted or cloud) ⢠Google Calendar and Gmail OAuth credentials ⢠OpenRouter key (for GPT-4o or Claude 3.7) Configuration Authorize Credentials ⢠Connect Google Calendar and Gmail nodes with OAuth2 ⢠Set up OpenRouter credentials for AI processing Set Your Email Update the Send Email node with your preferred destination address (default is you@yourcompany.com). Set Your Domain Filter In the âIdentify External Attendeesâ node, adjust the filter value yourcompany.com to your actual domain. Customize Prompts (Optional) You can fine-tune tone, formatting, or limits in the two language model nodes: ⢠Research and Develop Brief (attendee context + email summary) ⢠Summarize Schedule (overall Markdown brief formatting) Activate Workflow Enable the workflow and test it manually once to validate your setup. Confirm that the email lands correctly.
By Nick Loui