How to Build an AI-Powered Email Subscription Summarizer

GenAI 30 Project Challenge - 3

Published: March 7, 2025 URL: https://buildtolaunch.ai/p/genai-30-project-challenge-3 Engagement: 21 likes, 4 comments, 3 restacks Word count: 1078

---

If you're like me, your email is probably overflowing with newsletters and notifications from all the subscriptions you've signed up for. It feels like a constant battle to catch up with all the "useful" insights that fill your inbox.

This got me thinking: What if I used GenAI to create a Subscription Summarizer?

A tool that could sift through my inbox, extract the key information, and give me concise, actionable insights.

---

Project Goals

For this project, I set out to build a program that could:

1. Connect to my Gmail account to retrieve all unread subscription emails.
2. Parse the emails to extract recommended article links.
3. Use AI to read those articles and generate summaries for me.

---

Choice of Model and Tools

• Model: Hugging Face's BART, a transformer model well-suited for text summarization tasks.
• Programming Language: Barebones Python, keeping it lightweight and straightforward.
• Frameworks: Hugging Face Transformers library for NLP, and Gmail API for email access.

---

Help from Cursor (As Always)

Cursor played a pivotal role in getting the basics up and running. It:

1. Generated boilerplate code to connect with the Gmail API and fetch unread emails.
2. Helped parse email content, extract links, and handle authentication securely.
3. Integrated BART from Hugging Face, generating a simple pipeline for summarizing the articles.

---

Rounds of Adjustments

1. Extracting Correct Links: Medium emails are riddled with links — often more than one for the same article. It took 20+ iterations to get the filtering right, but eventually I was extracting clean article URLs.

2. Improving Summary Length: The initial summaries generated by BART were too short — just a couple of sentences. After tweaking the parameters (max_length and min_length), I got summaries that were concise yet informative.

3. From Summarizer to Recommender: Even with improved summaries, I found it overwhelming to read through all of them. That's when I decided to level up: turning the summarizer into a recommender system.

---

From Summarizer to Recommender

To prioritize the best articles, I built a scoring system based on four metrics:

1. Content Quality: Assesses how coherent and informative the content is, using BART to compare the summary with the original.
2. Readability: Evaluates the article's ease of reading using metrics like Flesch Reading Ease.
3. Relevance: Checks how well the content matches the title.
4. Length Score: Scores articles based on their length to balance short, actionable reads with in-depth insights.

weights = {
    'content_quality': 0.4,
    'readability': 0.3,
    'relevance': 0.2,
    'length_score': 0.1
}

Now, instead of skimming through every summary, I can sort articles by their overall score and focus on the top ones.

---

Problems and Improvements

• Email Parsing Complexity: Subscription emails have inconsistent structures. There's room to automate filtering further.
• Summarization Quality: Could be improved by fine-tuning BART on a dataset of Medium articles or experimenting with newer models like T5 or GPT-3.5.
• Relevance Scoring: The relevance metric is currently based on simple keyword matching. Incorporating a semantic similarity model could make this more robust.
• Scalability: As the volume grows, performance might degrade. Optimizing the pipeline and adding caching could help.

---

Final Thoughts

What started as a simple summarizer evolved into a powerful recommender system that prioritizes high-quality content. Not only does it save me time, but it also ensures I don't miss out on the most valuable insights.

Working with BART and Hugging Face was a great learning experience, and Cursor made the process of writing and refining code much smoother.

On to the next GenAI challenge soon!