Revolutionizing Hiring with Postmark and Amazon Bedrock Nova Premier Model This is a...

This is a submission for the Postmark Challenge: Inbox Innovators. What I Built Inbox...

This is a submission for the Postmark Challenge: Inbox Innovators. ## What I Built Mail-Guide-AI is a next-gen customer service assistant that automates the chaos of corporate and personal email handling. Think of it as your email triage ninja — sorting, replying, and responding to every email like a seasoned pro. The idea? Reduce manual work, boost response speed, and give your inbox a brain of its own. Built with Python and JavaScript, Mail-Guide-AI leverages advanced machine learning and NLP to: Auto-classify incoming emails (e.g., support, feedback, sales) Craft responsible, context-aware replies Integrate smoothly with Gmail accounts for fetching + replying Handle everything through Postmark’s powerful email API Whether you're a solo founder, a startup support team, or just drowning in unread mail, this tool brings your inbox back under control. ## Demo NO DEMO HAS BEEN PROVIDED YET DUE TO TECHNICAL ISSUES. IT WOULD BE RESOLVED SOONEST. ## Code Repository To view the repository kindly Click here at Mail-Guide ## How I Built It My Tech Stack: * Backend: Python (Flask), Postmark Webhooks * Frontend: JavaScript (React) * Email Parsing & Classification: spaCy, scikit-learn, Regex * Gmail API: OAuth2 for secure access * Postmark: Email routing, delivery, and parsing * AI: OpenAI Why Postmark? Postmark's reliable infrastructure made it a no-brainer for handling real-time inbound emails. Here's how it fits into the flow: 1. - Inbound Routing: Postmark receives and forwards mail to our webhook endpoint 2. - Webhook Magic: Triggers our ML engine to analyze and classify the message 3. - Structured Parsing: Postmark handles sender, subject, body, and attachments like a champ 4. - Bulletproof Delivery: Ensures fast + reliable responses with zero lag ## Final Thoughts Mail-Guide-AI is still evolving, but it’s already saving hours of manual effort. The synergy between AI + Postmark is LIT. If you’ve ever wished your inbox came with its own support agent — this is it. **Thanks to the Postmark team for a clean and powerful API that made all this possible. 🙌 And shoutout to the community — drop a ⭐, fork it, or run your own version**. _Built with love by @Contractor-x_

✉️ StoryMail – Inbox Whispers, Powered by AI This is a submission for the Postmark...

This is a submission for the Postmark Challenge: Inbox Innovators. 💡 What I Built Have...

This is a submission for the Postmark Challenge: Inbox Innovators. ## What I Built As a father of three with a busy calendar, this is something I’ve wanted for quite some time – this challenge pushed me to build it ☺️ It's a personal assistant that sends me a daily briefing email with what’s on today, what’s important, what I should already have on my radar for tomorrow or later in the week. Working title: **Daily Brief**. You log in once, connect your Google Calendar, add a bit of personal context (routines, who people are, etc.), and from then on you get a daily email. It shows you what matters today, plus a bit of what’s coming. Thanks to Postmark's inbound email parsing you can also forward emails to a personal inbox to consider them for the briefing. The idea is: one setup, then it just works. You don’t have to open an app every day. The whole thing runs through email. You can even reply to your briefing to adjust things or add context. Since I got the first working version online, I have been using it together with my wife to organize our busy family schedule. It’s been super useful, the process to build this was so fun,I learned a lot and I'm actually thinking about releasing this publicly, so maybe others can get that little bit of calm when starting their day :) ## Demo 👉 https://dailybriefing.verygooddesignstudio.com You can test it in two ways: * **Login with GitHub** → You’ll get dummy calendar data * **Login with Google** → Use your real calendar (currently in Google verification, so there’s a warning). Your calendar data is only used to generate the briefing. Nothing gets stored on my end. You can also try forwarding any email to your inbox address or replying to the briefing. That’s live and working. ## Code Repository ## tomreinert / dailybriefing ### # Daily Briefing App A personalized daily briefing service that combines your calendar events, custom notes, and email content into AI-generated summaries delivered on your schedule. ## Features * **Calendar Integration** : Connect your Google Calendar to include upcoming events * **Custom Notes** : Add and manage personal notes, talking points, and task lists * **Email Parsing** : Receive and process emails at your unique inbound address * **AI-Generated Briefings** : Combine all sources into personalized daily summaries * **Scheduled Delivery** : Automated email delivery at your preferred time * **Test Mode** : Preview briefings in the UI before scheduling ## Quick Start 1. **Setup Environment** cp .env.example .env.local Update `.env.local` with your API keys: * **Supabase** : Project URL and anon key from your project settings * **OpenAI** : API key from OpenAI platform * **Postmark** : Server token from your Postmark account * **Google OAuth** : Client ID and secret from Google Cloud Console * **Supabase Service Role** : Service role key for… View on GitHub ## How I Built It I’m a designer, but I’ve always had a thing for code – mostly frontend stuff. This was the first time I’ve really been able to ship something end-to-end, thanks to AI support (I used Cursor with Claude a lot). The stack: * Next.js * Supabase (auth + storage) * Vercel AI SDK * Google Calendar API * Github Actions * Postmark (inbound + outbound email) * shadcn/ui for the interface ### Implementation Timeline & Learnings This was one of those projects where I learned a ton by just doing. Here’s what stood out along the way: * **Started with a personal starter project** Already had Next.js with Supabase auth and the Vercel AI SDK set up. That saved a lot of setup time. * **Added Google sign-in + calendar integration** Getting OAuth working was okay, but pulling calendar events with the right scopes and tokens took some figuring out. * **Set up Postmark inbound processing** Hooked up the webhook, tested locally with ngrok. Worked immediately and gave me clean data to work with. * **Added personal notes input** This small feature made a big difference. Gave the assistant the context it needs to feel relevant. * **Dug into calendar data structure** Had to learn how recurring events and multi-day entries work so the briefings are actually useful and clear. * **Had to get the app verified by Google** It’s a pretty verbose process with a bunch of steps. Still pending, but a good learning. * **Built a mock mode with GitHub login** Added a test path with fake calendar data. Super helpful for trying things quickly and demoing without setup. * **Introduced user email settings** Let users choose when they want their briefing. Timezone handling was surprisingly tricky. * **Switched from Vercel Cron to GitHub Actions for scheduling** Vercel only allows one run per day on the free plan, which made testing hard. GitHub Actions was easy to set up and gives full control over timing—has worked reliably since. * **First real briefing arrived** A cool moment—everything stitched together and worked as intended. * **Iterated on the prompt + AI model** Tested a few different prompt setups and model configs to get the tone and structure of the briefing right. * **Refined UX and UI** Made a few passes to reduce friction. Setup should feel simple and invisible once it's done. ### Postmark Postmark was a key part of this. The inbound parsing made a huge difference, it just worked. I had it set up in no time and it was way easier than expected. Outbound emails are also super fast and easy to manage. One thing that helped a lot was StrippedTextReply. When someone replies to a briefing, I only want the new message, not the full quoted email thread. Postmark gives you just the reply content, no extra cleanup needed. Made the reply-to-context feature feel seamless. Honestly, one of the smoothest parts of the whole project. Thank you for this challenge which pushed me to build and learn!

This is a submission for the Postmark Challenge: Inbox Innovators. ## What I Built I built **CouponAI** , a server-side application that automates the extraction of promotional offers, deals, and coupons from your inbox using **Postmark’s inbound email parsing** feature. Many of us receive dozens of marketing and promotional emails every day from services like Swiggy, Zomato, Uber, Ola, e-commerce brands, and more. While these emails often contain valuable discounts and promo codes, they’re easy to miss or forget when we actually need them. **CouponAI** solves this problem by allowing users to automatically forward promotional emails to a custom inbound server **email address for parsing (powered by Postmark)**. From there, the parsed emails are processed with the help of a local LLM (Large Language Model) to extract structured information like: * The company or brand * Offer * Offer description * Expiry date * Category (e.g., food, travel, shopping) This data is then stored in a MongoDB database and can be retrieved via a simple frontend interface, helping users quickly check which discounts are available to them before making purchases or placing orders. _You can now retrieve all usable offers from a single endpoint and never miss a discount again!!_ ## Demo You can watch CouponAI demo here As this project depends on a locally hosted Large Language Model (LLM) to process parsed email data — which would be costly to deploy in the cloud — it is currently not live. However, you can run and test it on your local machine by following a few simple steps outlined below: ### How to Run and Test Locally You can try this project on your local machine by following these steps: 1. **Clone the Repository and Install dependencies** git clone https://github.com/Utkarsh212/CouponAI.git cd CouponAI npm install 2. **Install and Run Ollama** * You can download it from here * I have used `gemma3:4b` you can choose any suitable model as per your needs. ollama run <YOUR_MODEL_NAME> 3. **Configure Environment Variables** Update `config.env` with the following variables: PORT=5000 MODEL=YOUR_MODEL_NAME // Add your model name here HOSTED_MODEL_URL=http://127.0.0.1:11434/api/chat DB_CONNECTION_URL=YOUR_DB_CONNECTION_STRING // Add your MongoDB connection string here 4. **Expose the App with ngrok** * You can download Ngrok from here * Run your Express app (e.g., on port 5000) * Start ngrok to expose it: ngrok http 5000 5. **Configure Ngrok URL over Postmark** * Add ngrok URL to your server’s inbound webhook URL field on Postmark portal. 6. **Forward a Test Email** * From any email account, forward promotional email to the Postmark inbound server email address. * Postmark will parse it and send the content to your server’s inbound webhook URL. 7. **See Results** * Open the `index.html` file to view the results. * You'll see a list of all promotional emails along with their details. * Alternatively, you can access the Ngrok URL directly to view all the extracted offers in JOSN. ### Results Here are example of an email that were forwarded to the inbound server: ### Corresponding Output from LLM: The parsed and structured JSON results: { "company": "Zomato", "offer": "Up to 50% off on your favourite treats", "details": "Just code ZOMATO while ordering online.", "expiry": null, "category": "Food" } ## Code Repository GitHub: github.com/Utkarsh212/CouponAI ## How I Built It The application is powered by a Node.js + Express backend, a locally running LLM model via Ollama, and **Postmark’s inbound email parsing** feature to automate the extraction of useful promotional data from email content. ### Tech Stack * **Backend** : Node.js + Express * **LLM** : `gemma3:4b` model running locally via Ollama * **Database** : MongoDB * **Email Parsing** : Postmark Inbound Stream * **Development Tools** : Ngrok (for exposing localhost), dotenv, axios ### Architecture Overview Below is the architecture diagram that illustrates the complete flow — from the moment a email is forwarded, to how it gets parsed, processed by an LLM, and stored in the database. ### Flow & Architecture 1. **Inbound Email Forwarding** : Users set up forwarding from their personal email accounts to a Postmark-provided inbound email address. 2. **Postmark Webhook Integration** : Postmark parses the email and sends structured email data (subject, text body, HTML body, etc.) to a webhook on my Express server. 3. **Email Parsing & LLM Processing**: The server cleans the raw email content and generates a prompt, which is then sent to a locally running LLM (gemma3:4b). The LLM returns result which is then parsed into a JSON object with the following fields: - `company`: Brand or service name - `offer`: Promo description - `details`: Additional details about the offer - `expiry`: Validity date if mentioned - `category`: Context (e.g., food, shopping) 1. **Storage & Retrieval**: The structured offer data is saved in a MongoDB collection and can be retrieved via a public API route. 2. **Frontend (Optional)** : For simplicity, I created a minimal HTML page that displays the available coupons pulled from the backend API. ### Experience with Postmark This was my first time working with Postmark’s inbound email stream feature — and it was a smooth experience. Setting up the inbound stream, getting the parsing to work, and configuring the webhook was very straightforward. I was especially impressed with how detailed and clean the parsed JSON format is out-of-the-box.

This is a submission for the Postmark Challenge: Inbox Innovators. What I Built I built...

This is a submission for the Postmark Challenge: Inbox Innovators. Postmark x Dev.to...

We are thrilled to partner with Postmark to bring the community a brand new DEV challenge. Running...