Create Your First Project
Start adding your projects to your portfolio. Click on "Manage Projects" to get started
AI-Powered Resume Optimization & ATS Scoring Automation (Make)
Date
December 2025
Role
AI Automation Architect / Creative Operations Specialist
I designed the system logic, developed AI prompting strategies, and implemented the full automation workflow that integrates AI models with document generation and tracking tools.
Tools & Technologies
- Make (Integromat) — workflow orchestration
- Google Gemini (two roles):
- Resume Architect — resume adaptation
- ATS Analyst — ATS compatibility scoring
- Telegram Bot — user interface
- Google Docs — document creation
- Google Drive — PDF export
- Google Sheets — application tracker
- JSON parsing & Routers — decision logic
Goal
To build an automated system that:
- adapts a resume to a specific job description
- evaluates its ATS compatibility
- generates a ready-to-send PDF document,
- tracks applications automatically
- reduces time spent on low-probability applications
Result
Application preparation time reduced from 30–60 minutes to ~15 seconds
Each resume is evaluated with an ATS score (0–100)
Automatic generation of:
- adapted resume
- PDF file
- tracking record
- Low-match vacancies are filtered out automatically
- Fully automated end-to-end workflow
This project is an AI-driven automation pipeline for job applications.
The user sends a job description via a Telegram bot. The system then performs the following steps:
- An AI model adapts one of the base resumes to match the job requirements.
- A second AI model analyzes the adapted resume and calculates an ATS compatibility score based on hard skills, tools, technologies, and job level.
If the score is 75 or higher:
- a Google Docs file is created, the document is exported as a PDF,
- the job data (company, position, score) is logged into Google Sheets,
- and the PDF is delivered back to the user via Telegram.
If the score is below 75:
- the system stops early and returns a rejection message without generating a document, saving time and API resources.
This project demonstrates a data-driven approach to career automation, where application decisions are based on structured AI evaluation rather than intuition.