DEV Community: Sinky Priya

AI-Resume & Portfolio Tailor

Sinky Priya — Thu, 15 Oct 2026 16:49:46 +0000

What I Built

The Project: AI-Resume & Portfolio Tailor
What it does: An open-source AI agent that takes a user's master resume and a target job description, then automatically rewrites bullet points, highlights matching skills, and generates a tailored cover letter in seconds.
Who would pay for it: Job seekers, career switchers, and freelance professionals tired of manually tailoring applications.
The problem it solves: Eliminates hours of tedious copy-pasting and keyword optimization required to pass modern Applicant Tracking Systems (ATS).

Demo

Live App: https://ai-resume-tailor-demo.example.com
Video Walkthrough: Watch 2-min demo on YouTube

Code

GitHub Repository: {% github username/ai-resume-tailor %}

How I Built It

Open-Source AI / Models: Built using Llama 3 (8B) running locally via Ollama, orchestrated with LangChain, and hosted with a lightweight FastAPI backend.
Architecture & Tech Stack:
- Frontend: Next.js & Tailwind CSS for a clean, fast dashboard.
- Backend: Python / FastAPI handling document parsing (PDF/DOCX) and prompt execution.
- AI Layer: Local Llama 3 instance to ensure zero data leaks of sensitive user resume information.

Why Does Open Innovation Matter?

Using open-source weights (Llama 3) and local inference tools completely eliminated API cost barriers. For a bootstrapped side hustle targeting budget-conscious job seekers, relying on closed, per-token commercial APIs would have made a free tier or low-cost subscription model impossible to sustain. Plus, handling personal career data locally provides a massive privacy selling point that users trust.

My Agent Session

DevRelay Session: {% agent_session 9a8b7c6d %}

My First User

The User: A former colleague who is currently interviewing for Senior Frontend roles.
Their Feedback: "It took me 30 seconds to generate a custom resume version for a Netflix role that usually takes me an hour. I used it for three applications and landed two recruiter screens!"
Monetization Check: They expressed immediate willingness to pay a \$9 one-off fee or a \$5/month power-user subscription to access unlimited generations and custom template exports.

Prize Categories

Best Open-Source AI Side Hustle
Best Local Inference App

Build a Smarter Workflow: Why Open-Source AI is the Ultimate Side Hustle Stack

Sinky Priya — Thu, 15 Oct 2026 15:39:38 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built
For this challenge, I built [Project Name]—an open-source AI-powered micro-SaaS designed to solve [specific pain point, e.g., automate repetitive code reviews / generate localized marketing copy for indie founders].

Who is this for? Indie developers, bootstrapped founders, and creators who need high-leverage automation without eating into their margins with expensive, closed-source API subscriptions. It solves the core problem of [explain problem, e.g., spending hours on manual QA and formatting] by leveraging local open-weight models to handle the heavy lifting instantly.

Code
The entire project is open-source and available on GitHub. You can explore the codebase, run it locally, or contribute below:

How I Built It
To keep the tool fast, modular, and completely transparent, I built it using a modern open-source AI stack:

AI Model & Inference: Powered by [e.g., Llama 3 / Mistral / Ollama] running via [e.g., Hugging Face Transformers / LangChain / LlamaIndex].

Architecture: A lightweight agent harness that orchestrates tasks by chaining local prompts, parsing structured outputs, and executing automated checks.

Tech Stack: [e.g., Next.js, Python, FastAPI, Tailwind CSS] for a snappy frontend and robust backend processing.

Why Does Open Innovation Matter?
Open-source AI was the absolute linchpin for building this side hustle.

Zero Marginal Costs: Because the core models run locally or via open-weight hosting platforms, I don't have to worry about per-token API overhead eating into early-stage revenue.

Data Privacy & Trust: Users are trusting this tool with their sensitive code and data. Having a completely transparent, open-source codebase means users can verify that their data stays private and secure.

Customizability: Fine-tuning and adjusting system prompts to fit niche developer workflows is something closed commercial APIs simply don't allow the same level of granular control over.

My Agent Session
(Optional: If you used DevRelay to record your agent session, embed or link it here so judges can see how your AI agent was constructed!)

My First User
I tested an early version with [e.g., a fellow developer friend / indie hacker from a community], and the feedback was incredible:

"This saved me at least 3 hours of manual debugging on my latest side project launch. The fact that it runs locally and doesn't leak my codebase is a game-changer." — [User Name / Handle]

Hacktoberfest Weekend Challenge: Build for a Friend

Sinky Priya — Thu, 15 Oct 2026 15:33:24 +0000

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

What I Built
The Friend: Priya

The Problem: Priya is a busy freelancer who loves trying out new recipes, but she constantly struggles with meal planning around her fluctuating schedule, her sudden pantry cravings, and her specific dietary preferences (she loves vegetarian fusion and is trying to cut back on dairy). Manually searching for recipes and matching them to what's already in her fridge takes up way too much time.

The Solution: I built PantryChef AI, a smart, local-first recipe assistant tailored specifically for Priya. She can snap a quick photo of her fridge or type out what ingredients she has left, and the app instantly generates personalized, healthy fusion recipes with exact step-by-step instructions.

Demo
Live App: https://pantrychef-ai.example.com

Video Walkthrough: Watch the 2-minute demo on Loom (Bonus: She tested it live with leftover bell peppers and paneer, and loved the resulting Makhani tacos!)

Code
Python

Core recipe generation logic using a local open-weight model

def generate_custom_recipe(ingredients, preferences):
prompt = f"Create a quick vegetarian, low-dairy recipe for Priya using: {ingredients}."
response = local_llm.inference(prompt, temperature=0.7)
return format_recipe_card(response)
GitHub Repository: github.com/username/pantrychef-ai

How I Built It
Tech Stack: React (Frontend), Python/FastAPI (Backend)

Open-Source AI / Models: Powered locally by Gemma 2 (2B / 9B open-weights) via Ollama, ensuring zero latency and complete privacy for her grocery lists and personal preferences.

Architecture: The React frontend captures ingredient inputs and sends them to a lightweight local FastAPI backend, which prompts the Gemma model running locally to curate and stream back structured JSON recipe cards.

Why Does Open Innovation Matter?
Using open-source tools and open-weight models like Gemma made this project possible because Priya values her kitchen privacy and didn't want her personal dietary notes and fridge contents logged on a third-party commercial cloud server. Running everything locally via Ollama meant zero API costs, zero rate limits, and instant offline inference right from my laptop while testing it out in her kitchen.

My Agent Session
View my development agent session with DevRelay

Prize Categories
Best Use of Gemma

Best Use of a .tech Domain