David Harvey
Workflows by David Harvey
AI-powered tarot readings via iMessage with GPT & Blooio
## 🔮 Mystic Tarot Bot — AI-Powered iMessage Readings This magical n8n template turns your iMessage inbox into a soulful tarot reading experience powered by Blooio and AI. Users can send in questions or photos of their tarot spreads, and the bot replies like a mystical oracle — interpreting symbols, offering gentle insights, and guiding with poetic warmth. ✨ Ideal for solo reflection, spiritual creators, or client-based guidance services — no tech knowledge needed. --- ### 🌟 Use Cases - Offer intuitive, emotionally resonant tarot readings via iMessage - Support coaching, wellness, and metaphysical businesses with AI-enhanced readings - Accept photos of real tarot card spreads or plain text questions - Great for automating daily card pulls, client responses, or onboarding into spiritual flows --- ### 🧠 Good to Know - Built using Blooio’s iMessage API — supports image attachments and conversational replies - Includes visual recognition and symbolic interpretation of real tarot card photos - Responses generated by OpenAI with a custom “Mystic Tarot Reader” persona - Onboards users if they say “Hi” or request a virtual card draw - Responds in poetic, spiritually attuned language — no markdown, no tech-speak --- ### ⚙️ How it Works **Trigger**: iMessage webhook via Blooio receives user message or image **Check**: Bot ignores self-sent messages to prevent loops **Detect**: If a photo is attached, it’s passed to AI for card recognition **Interpret**: The AI agent gives a heartfelt, symbolic interpretation **Respond**: A final, warm tarot reading is sent back through iMessage --- ### 📝 How to Use #### Set Up Blooio: 1. Sign up at [https://blooio.com](https://blooio.com) 2. Choose a **Dedicated** or **Enterprise** plan (image support required) 3. Copy your API key from **Settings → API Keys** 4. Paste it into the **Send Message** HTTP node as a Bearer token #### Customize the Experience: - Adjust the prompt for a different tone or deck style - Add journaling prompts, affirmations, or follow-ups - Use other workflows to track users, create reading logs, or offer upsells #### Try It Out: Text your Blooio-connected number with: - “Hi” → get onboarding - “Draw a card for me” → get a virtual pull - A tarot photo + question → get a full, soulful reading --- ### ✅ Requirements - Blooio Account & API Token (Dedicated plan or higher for images) - Optional: Tarot images, user questions, or both --- ### 🔧 Customizing This Workflow - Add personalized spreads (e.g. past/present/future layouts) - Send AI-generated visuals of the pulled cards - Route readings into Notion, Airtable, or Google Sheets - Expand to WhatsApp, web, or email with Blooio’s multichannel support --- 🃏 Let the cards speak. Let the messages flow.
Real-time PulsePoint emergency alerts to iMessage with AI summaries
# 🚨 Emergency Alerts Reporter to iMessage This n8n template fetches real-time emergency incident alerts from PulsePoint for a specific agency and delivers them directly to any phone number via iMessage using the Blooio API. It's designed to keep users informed with clear, AI-summarized reports of emergency activity near them—automatically and reliably. Use cases are powerful and immediate: - Get real-time fire/medical alerts for your neighborhood. - Use it for family, local safety groups, or even emergency response teams. - Convert technical dispatch data into readable updates with emojis and plain English. --- ## 🧠 Good to Know - You’ll need a **PulsePoint agency ID** (see instructions below). - iMessages are sent using [Blooio’s API](https://blooio.com) (which supports Apple’s iMessage and fallback RCS/SMS). - Messages are AI-enhanced using OpenAI's `o4-mini` model to summarize incident reports with context and urgency. - The workflow runs every hour, but this can be configured to match your needs. - Each report is sent **only once**, thanks to persistent tracking of seen incident IDs in workflow static memory. --- ## ⚙️ How it Works 1. **Trigger**: A Schedule Trigger (every hour) or manual start kicks off the flow. 2. **Get Alerts**: A `code` node fetches the latest PulsePoint incidents for a specified agency and decrypts the data. 3. **Filter New Incidents**: We store previously seen incident IDs to prevent duplicate alerts. 4. **Merge Incidents**: All new incident details are merged into a single payload. 5. **Condition Check**: If there are no new incidents, nothing is sent. 6. **AI Summary**: The incident data is passed to an AI agent for summarization with human-friendly emojis and formatting. 7. **Send Message**: The final summary is sent via Blooio’s API to your phone using iMessage. --- ## 📝 How to Use 1. **Get Your PulsePoint Agency ID**: - Visit [https://web.pulsepoint.org](https://web.pulsepoint.org). - Find your agency by location or name. - Inspect the API call or browser network log to get the `agencyid` (e.g. `19100` from a URL like `?agencyid=19100`). 2. **Set Up Blooio for Messaging**: - Sign up at [https://blooio.com](https://blooio.com). - Go to your account and retrieve your Bearer API Key. - Pricing details available on their [pricing page](https://blooio.com#pricing). - Add your key to the HTTP Request node as a **Bearer Token**. 3. **OpenAI API**: - Create or use an existing OpenAI account. - Use the `o4-mini` model for efficient, readable summaries. - Get your OpenAI API key from [https://platform.openai.com/account/api-keys](https://platform.openai.com/account/api-keys). 4. **Add Your Phone Number**: - Replace `+1111112222` with your actual number (international format). - You can also modify the message content or prepend special tags/emojis. --- ## ✅ Requirements - **PulsePoint agency ID** – See usage instructions above - **OpenAI API Key** – [Get API Key](https://platform.openai.com/account/api-keys) - **Blooio Account & Bearer Token** – [Get Started](https://blooio.com) - **Phone number** for iMessage delivery --- ## 🔧 Customizing This Workflow - **Change the schedule** to get alerts more or less frequently - **Add filters** to only get alerts for specific incident types (e.g. fires, traffic accidents) - **Send to groups**: Expand to send alerts to multiple recipients or use Slack instead of iMessage - **Use different AI prompts** to get detailed, humorous, or abbreviated alerts depending on your audience --- With just a few credentials and a phone number, you’ll have real-time incident alerts with human-friendly summaries at your fingertips. 🛠️ Stay informed. Stay safe.
iMessage food photo nutritional analysis with GPT-4 Vision & Memory Storage
# iMessage AI-Powered Smart Calorie Tracker > 📌 **What it looks like in use:**  > This image shows a visual of the workflow in action. Use it for reference when replicating or customizing the template. This n8n template transforms a user-submitted food photo into a detailed, friendly, AI-generated nutritional report — sent back seamlessly as a chat message. It combines OpenAI's visual reasoning, Postgres-based memory, and real-time messaging with Blooio to create a hands-free calorie and nutrition tracker. --- ## 🧠 Use Cases - Auto-analyze meals based on user-uploaded images. - Daily/weekly/monthly diet summaries with no manual input. - Virtual food journaling integrated into messaging apps. - Nutrition companion for healthcare, fitness, and wellness apps. --- ## 📌 Good to Know - ⚠️ This uses GPT-4 with image capabilities, which may incur higher usage costs depending on your OpenAI pricing tier. Review [OpenAI’s pricing](https://openai.com/pricing). - The model uses visual reasoning and estimation to determine nutritional info — results are estimates and should not replace medical advice. - [Blooio](https://blooio.com) is used for sending/receiving messages. You will need a valid API key and project set up with webhook delivery. - A Postgres database is required for long-term memory (optional but recommended). You can use any memory node with it. --- ## ⚙️ How It Works 1. **Webhook Trigger** The workflow begins when a message is received via Blooio. This webhook listens for user-submitted content, including any image attachments. 2. **Image Validation and Extraction** A conditional check verifies the presence of attachments. If images are found, their URLs are extracted using a Code node and prepared for processing. 3. **Image Analysis via AI Agent** Images are passed to an OpenAI-based agent using a custom system prompt that: - Identifies the meal, - Estimates portion sizes, - Calculates calories, macros, fiber, sugar, and sodium, - Scores the meal with a health and confidence rating, - Responds in a chatty, human-like summary format. 4. **Memory Integration** A Postgres memory node stores user interactions for recall and contextual continuity, allowing day/week/month reports to be generated based on cumulative messages. 5. **Response Aggregation & Summary** Messages are aggregated and summarized by a second AI agent into a single concise message to be sent back to the user via Blooio. 6. **Message Dispatch** The final message is posted back to the originating conversation using the Blooio Send Message API. --- ## 🚀 How to Use - The included webhook can be triggered manually or programmatically by linking Blooio to a frontend chat UI. - You can test the flow using a manual POST request containing mock Blooio payloads. - Want to use a different messages app? Replace the Blooio nodes with your preferred messaging API (e.g., Twilio, Slack, Telegram). --- ## ✅ Requirements - OpenAI API access with GPT-4 Vision or equivalent multimodal support. - Blooio account with access to incoming and outgoing message APIs. - Optional: Postgres DB (e.g., via [Neon](https://neon.com)) for tracking message context over time. --- ## 🛠️ Customising This Workflow - **Prompt Tuning** Tailor the system prompt in the AI Agent node to fit specific diets (e.g., keto, diabetic), age groups, or regionally-specific foods. - **Analytics Dashboards** Hook up your Postgres memory to a data visualization tool for nutritional trends over time. - **Multilingual Support** Adjust the response prompt to translate messages into other languages or regional dialects. - **Image Preprocessing** Insert a preprocessing node before sending images to the model to resize, crop, or enhance clarity for better results.