Is your CV truly job-ready? I built an AI Senior Strategist with Gemini to find out

Diego Martinez L. — Tue, 03 Mar 2026 05:52:02 +0000

This is a submission for the Built with Google Gemini: Writing Challenge

What I Built with Google Gemini

I developed CV Advisor PRO, a senior career auditor designed to move beyond simple spell-checking and into high-level career coaching. Many talented professionals miss out on opportunities because they lack the "language of leadership." This tool democratizes access to the kind of feedback usually reserved for expensive executive consultants.

Google Gemini serves as the brain of the operation. Leveraging the Gemini 3 Flash Preview model via Google AI Studio, the app performs deep-tissue scans of professional documents. It uses Gemini’s massive context window and multimodal capabilities to:

Analyze PDF structures and extract complex work histories.
Apply the STAR method (Situation, Task, Action, Result) to transform passive duties into high-impact achievements.
Generate an Employability Score.

Demo

Here is my video demo.

What I Learned

Building this tool taught me that career coaching is a delicate balance of data science and psychology.

Technical Growth: I mastered prompt engineering to ensure the model maintained a "Senior Career Strategist" persona, providing "tough love" without being discouraging.
Product Philosophy: I realized that users don't just want a better document; they want the confidence that comes from knowing their worth. I applied to my CV and it was very helpful.
System Design: Using Cloud Run and TypeScript alongside Gemini showed me how quickly a high-speed, scalable AI microservice can be deployed.

Google Gemini Feedback

The experience with Gemini 3 Flash was a game-changer for this specific use case:

The Wins: The model's responses are consistent and useful. I applied several improvements to my own CV. Also the speed is incredible. For a real-time conversational coach, latency is the enemy, and Flash handled complex reasoning almost instantly. Its ability to "understand" the nuance between a responsibility and an achievement was far superior to previous models I've tested.
The Friction: Fine-tuning the "AI Carrer Coaching" aspect required several iterations. Initially, the model tended to be too polite (the model praised everything, even irrelevant details). Another point of friction was that it types the response much faster than it can read. That's why I limited interaction after the AI finishes speaking.
Future Support: I’d love to see even deeper integration for real-time web-scraping within the AI Studio environment to facilitate the "Live Job Comparison" feature I have planned next.

"Google Me": Transforming my Career into a Google Search Experience

Diego Martinez L. — Sat, 31 Jan 2026 09:36:10 +0000

This is a submission for the New Year, New You Portfolio Challenge Presented by Google AI

About Me

I am Diego Martinez, a Systems Engineer and Google Product Expert with a passion for blending high-level engineering with intuitive user experiences. This portfolio is more than just a CV; it is a showcase of my identity as a "Google-native" professional and a bold statement of my career-long dream: to officially join the ranks as a Googler. My goal was to transform the familiar, minimalist interface of Google search engine into a narrative tool that guides recruiters through my education, experience, and technical skills in a way that feels both nostalgic and creative.

Portfolio

Try Out here

I added the label: --labels dev-tutorial=devnewyear2026

How I Built It

My tech stack was chosen to mirror the speed and reliability of Google’s own tools:

AI Development with Google AI Studio: I leveraged Google AI Studio to prototype, prompt-engineer, and refine the core intelligence of the portfolio. This allowed me to fine-tune the model's behavior and ensure high-quality responses before integration.
AI Integration: I integrated Gemini 3 Flash Preview to power the "AI Mode" button. This feature acts as a virtual career assistant, answering specific questions about my background using RAG over my professional career.
Deployment: Hosted on Google Cloud Run, ensuring global scalability and performance.
Design Decisions: 1) Constrained Search UX: To prevent users from mistaking it for a general web search, the box search was implemented focused strictly on my professional data. When a user types anything, it directs them to my professional career path, thus avoiding distractions and focusing them on the relevant aspects of my portfolio. 2) Available in only 3 languages: English, Spanish and Portuguese.

What I'm Most Proud Of

I'm really proud of the "AI Mode" button. It's not just a gimmick; it represents the transition from static portfolios to interactive experiences. When activated, the interface transforms from a classic search results page into a space for spoken/written interaction with generative AI. Furthermore, in my opinion, the "I'll contact you" button (a playful nod to Google's "I'm feeling lucky") adds a touch of personality that aims to spark positive conversations with hiring managers.

I really enjoyed creating this portfolio; I'll probably add easter eggs like askew, gravity, or "do a barrel roll" to it at some point just for fun.

DEV Community: Diego Martinez L.