koichi nagino
Templates by koichi nagino
Daily AI outfit recommendations based on weather forecast to Slack
Description Start your day with the perfect outfit suggestion tailored to the local weather. This workflow runs automatically every morning, fetches the current weather forecast for your city, and uses an AI stylist to generate a practical, gender-neutral outfit recommendation. It then designs a clean, vertical image card with all the details—date, temperature, weather conditions, and the complete outfit advice—and posts it directly to your Slack channel. It’s like having a personal stylist and weather reporter deliver a daily briefing right where your team communicates. Who’s it for Teams working in a shared office location who want a fun, daily update. Individuals looking to automate their morning routine and take the guesswork out of getting dressed. Community managers wanting to add engaging, automated content to their Slack workspace. Anyone interested in a practical example of combining weather data, AI, and dynamic image generation. How it works / What it does Triggers Daily: The workflow automatically runs every day at 6 AM. Fetches Weather: It gets the current weather forecast for a specified city (default is Tokyo) using the OpenWeatherMap node. Consults AI Stylist: The weather data is sent to an AI model, which acts as a stylist and returns a practical, gender-neutral outfit suggestion. Designs an Image Card: It dynamically creates a vertical image and writes the date, detailed weather info, and the AI's full recommendation onto it. Posts to Slack: Finally, it uploads the completed image card to your designated Slack channel with a friendly morning greeting. Requirements An n8n instance. An OpenWeatherMap API Key. An OpenRouter API Key (or credentials for another compatible AI model). A Slack workspace and the necessary permissions to connect an app. How to set up Set Weather Location: In the Get Weather Data node, add your OpenWeatherMap API Key and change the city name if you wish. Configure AI Model: In the OpenRouter Chat Model node, add your API Key. Configure Slack: In the Upload a file node, add your Slack credentials and, most importantly, select the channel where you want the forecast to be posted. Adjust Schedule (Optional): You can change the trigger time in the Daily 6AM Trigger node. How to customize the workflow Change the AI's Personality: Edit the system message in the Generate Outfit Advice node. You could ask the AI to be a pirate, a 90s fashion icon, or a formal stylist. Customize the Image: In the Create Image Card node, you can change the background color, font sizes, colors, and the layout of the text. Use a Different Platform: Swap the Slack node for a Discord, Telegram, or Email node to send the forecast to your preferred platform.
By koichi naginoGPT-4.1-mini Powered Invoice Processing from Gmail to Google Sheets with Slack
AI-Powered Invoice Processing from Gmail to Google Sheets with Slack Approval This workflow completely automates your invoice processing pipeline. It triggers when a new invoice email arrives in Gmail, uses AI to extract key data from the PDF attachment, logs it in a Google Sheet, and sends a request to Slack with simple links for one-click approval or rejection. Who's it for? This template is perfect for small business owners, finance teams, freelancers, and anyone looking to eliminate the manual work of processing invoices. It saves hours of data entry, reduces human error, and streamlines the approval process. How it works Trigger: The workflow starts when an email with a specific subject (e.g., "Invoice") arrives in Gmail. Extraction: It automatically downloads the first PDF attachment from the email and extracts all its text content. AI Processing: The extracted text is sent to an AI model, which intelligently identifies and pulls out key details: invoice number, issue date, company name, total amount, and due date. Logging: This structured data is appended as a new row in your Google Sheet. The status is automatically set to "pending". The full, raw text from the PDF is also saved for easy verification. Approval Request: A formatted message is sent to a designated Slack channel. This message includes the key invoice details and two unique links: one to approve and one to reject the invoice. Handle Response: When a user clicks either the "Approve" or "Reject" link, the corresponding Webhook in the workflow is triggered. Update Sheet: The workflow finds the correct row in the Google Sheet using the invoice number and updates its status to "approved" or "rejected". Confirmation: A final confirmation message is sent to the Slack channel, closing the loop and informing the team of the action taken. How to set up Credentials: Add your credentials for Gmail, OpenAI, Google Sheets, and Slack in the designated nodes. Gmail Trigger: In the "1. New Invoice Email Received" node, change the search query q from "incoice" to the keyword you use for invoice emails (e.g., "invoice"). Google Sheets: In the three Google Sheets nodes ("6. Log Invoice...", "9a. Update Status to Approved", and "9b. Update Status to Rejected"), enter your Google Sheet ID and the name of the sheet. Slack: In the three Slack nodes ("7. Send Approval Request...", "10a. Send Approval Confirmation", and "10b. Send Rejection Confirmation"), enter your Slack Channel ID. Webhook URLs: First, activate the workflow using the toggle in the top-right corner. Open the "Webhook (Approve)" node, go to the Production URL tab, and copy the URL. Paste this URL into the "7. Send Approval Request to Slack" node, replacing the https://YOURWEBHOOKBASE_URL/webhook/approval part of the approval link. Repeat this process for the "Webhook (Reject)" node and the rejection link. Activate Workflow: Ensure the workflow is active for the Webhooks to work continuously. How to customize AI Prompt: You can modify the prompt in the "5. Extract Invoice Data with AI" node to extract different or additional fields to match your specific invoice formats. Slack Messages: Feel free to customize the text in all three Slack nodes to better fit your team's tone and communication style.
By koichi naginoTrack and visualize daily moods with GPT-4o, Wolfram Alpha, Sheets, and Slack
Overview This workflow, "Mood Graph Studio," offers a comprehensive solution to track and visualize your emotional well-being. By simply inputting a single sentence about your mood, this template uses AI to perform a sentiment analysis, generates a visual graph via Wolfram Alpha, provides personalized feedback, and logs everything to Google Sheets. It is designed for anyone interested in mindfulness, self-reflection, or quantified self-tracking. How It Works The workflow is divided into two main API functionalities and a manual trigger for easy testing. Analyze a Single Mood (/mood endpoint) An AI Agent (OpenAI) quantifies your mood text into valence (positivity) and energy (activity). A query is sent to Wolfram Alpha to generate a simple linear graph based on the score. A second AI Agent provides short, encouraging advice in Japanese. The complete entry is logged as a new row in Google Sheets. Returns a JSON response containing the full analysis and the graph image. Generate Mood History Graph (/history endpoint) Retrieves historical mood data for a specified user from Google Sheets. A Code node formats the data into a time-series plot query. Wolfram Alpha generates a line graph visualizing the mood trend over time. The resulting graph is automatically posted to Slack. How to Set Up Credentials You must add your own credentials for the following services in the respective nodes: OpenAI: Used in both Chat Model nodes. Google Sheets: Used in the "Log Mood" and "Get History" nodes. Slack: Used in the "Send History" node. Wolfram Alpha App ID This workflow uses the HTTP Request node to call the Wolfram Alpha API. Get a free App ID from the Wolfram|Alpha Developer Portal. Paste your App ID into the appid parameter value in both Generate...Graph nodes. Google Sheet Configuration Create a new Google Sheet. Paste the Sheet ID into the Document ID field in both Google Sheets nodes. Crucially, ensure the first row has the following headers exactly (case-sensitive): userId, moodText, valence, energy, createdAt, wolframQuery, feedback How to Use For Testing: Use the Manual Trigger. Modify the sample text in the "Set Test Data" node and click "Execute Workflow" on the canvas. For Production: Activate the workflow. Send POST requests to the Production URL of the Webhook nodes.
By koichi nagino