TailorMail: Cold Mail Generator

Automate personalized cold email generation for client outreach by leveraging AI-driven insights from job postings, skill-based portfolio matching, and tailored messaging—all in real-time.

Comment 1

TailorMail: Cold Email Generator

Problem Statement

The software services industry, including companies like TCS and Infosys, faces fierce competition in acquiring clients. These companies often use cold emailing as a key marketing strategy to propose contract-based services. This involves identifying client requirements through job postings on their career pages and crafting personalized emails highlighting the company's relevant expertise and portfolios.

However, this process is:

  • Manual: Sales teams manually analyze job postings and draft emails.
  • Time-Consuming: Creating tailored emails for each potential client requires significant effort.
  • Prone to Errors: Relevancy and personalization can be inconsistent.

The Cold Email Generator addresses these challenges by automating the process of:

  1. Scraping job postings for skill requirements.
  2. Mapping relevant portfolios from a database.
  3. Generating professional, tailored emails using advanced AI tools.

Screenshot of Application

Technical Architecture

High-Level Workflow

  1. Input:
    • A user provides a URL to a job posting.
  2. Processing:
    • The system extracts job-related data, matches it with stored portfolios, and generates a personalized email.
  3. Output:
    • A well-crafted, relevant cold email ready for client outreach.

Technical Architecture Image

Detailed Architecture

1. Frontend

  • Framework: Streamlit
  • Functionality:
    • User-friendly interface to input job posting URLs.
    • Displays the generated email for review and further customization.
  • Features:
    • Interactive preview.
    • Option to download the email or copy it directly.

2. Backend Services

a. Web Scraping
  • Tool: LangChain
  • Process:
    • Scrape the job posting webpage using the provided URL.
    • Extract raw text including job role, required skills, and job description.
  • Output:
    • Structured data containing job details.
b. Information Parsing
  • Tool: Llama 3.1 (Hosted on SambaNova Cloud).
  • Process:
    • Analyze the raw text extracted from the job posting.
    • Extract key information like:
    • Job Role
    • Required Skills
    • Job Description
    • Format the information into a structured JSON object.
  • Output:
    • Example JSON:
      json { "job_role": "AI/ML Engineer", "skills": ["Python", "Machine Learning", "DevOps"], "description": "Looking for an AI/ML Engineer with expertise in Python and DevOps." }
c. Portfolio Matching
  • Tool: ChromaDB (Vector Database).
  • Process:
    • Query the database using extracted skills.
    • Retrieve portfolio links and relevant examples of past work.
    • Example:
      json { "Python": "www.company.com/python_portfolio", "DevOps": "www.company.com/devops_portfolio" }
  • Output:
    • Relevant portfolio links for each skill.
d. Cold Email Generation
  • Tool: Llama 3.1 (SambaNova Cloud).
  • Process:
    • Combine job details and portfolio links into a professionally crafted cold email.
    • Ensure personalization and clarity in the email content.

  • Output:

    • Example email:
      ``` Subject: Expertise in AI/ML for Your Team

    Dear [Client Name],

    I noticed your recent job posting for an AI/ML Engineer requiring expertise in Python and DevOps.
    At [Company Name], we have a proven track record in delivering exceptional results in these areas.
    Here’s a portfolio of our past work:

    We’d love to discuss how we can help meet your needs efficiently and cost-effectively.

    Best regards,
    [Your Name]

Integration and Hosting

  1. Model Hosting

    • Platform: SambaNova Cloud
    • Features:
      • Fast inference (100+ tokens/sec).
      • OpenAI-compatible APIs for seamless integration.
      • Support for Llama 3.1 and other advanced models.
    • Benefits:
      • Real-time response for email generation.
      • Scalable and easy to deploy.

  2. Backend Integration

    • Use SambaNova’s OpenAI-compatible APIs to connect the components, ensuring smooth data flow between scraping, processing, database queries, and email generation.

Advantages of the Architecture

  • Scalable: Handles multiple simultaneous requests with ease.
  • Efficient: Automates repetitive tasks, saving significant time for sales teams.
  • Cost-Effective: Reduces the need for manual effort while maintaining high accuracy.
  • Customizable: Generated emails can be easily reviewed and edited for final touch-ups.

This technical architecture ensures that the Cold Email Generator is fast, reliable, and effective in helping software services companies improve their client outreach process.

Built With

  • chromadb
  • langchain
  • openai
  • python
  • sambanova.ai
  • streamlit
Share this project:

Updates