The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Full-stack system for supervising crude oil trunk and sub-trunk lines. Offline-capable PWA with GPS route logging, native Android app, and JWT multi-user authentication with supervisor and inspector roles. Includes GPX export for route analysis. Designed for field conditions with intermittent connectivity.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
:I’m an AI & Full-Stack Developer who builds modern web applications and practical AI-powered solutions from frontend to backend. My projects include Lump Chat, a communication-focused web application; Smart Attendance, an AI-based attendance system powered by face recognition; and Local Store, a modern e-commerce platform. I work with React.js, Node.js, Python, FastAPI, MongoDB, PostgreSQL, JavaScript, OpenCV, REST APIs, and modern web technologies. My focus is on building responsive interfaces, robust backend architecture, database-driven systems, and intelligent features that solve real-world problems.
Built a LangChain-based agentic application that turns a learning goal into a structured, personalised learning plan.
The application supports two execution modes:
⚡ ReAct Agent Mode
A tool-using agent dynamically selects custom tools for course lookup, completion-time calculation, and learning-plan generation.
🔍 Explain Mode — LCEL
A deterministic LCEL pipeline executes the planning workflow step-by-step, making the process more transparent, predictable, and easier to debug.
The project also uses Pydantic structured outputs, Groq, Python, Streamlit, and custom LangChain tools, with deterministic logic kept outside the LLM wherever possible.
This project was built to explore the practical engineering side of AI agents — tool calling, agent orchestration, structured outputs, deterministic workflows, and explainability.
The project is not currently deployed, but the complete source code and implementation are available on GitHub.
Tech: Python · LangChain · ReAct · LCEL · Groq · Pydantic · Streamlit
turning a learning goal into an actual plan is such a useful agent use case 🔥
MessyAPI is a production-ready developer infrastructure platform I built to eliminate repetitive data utility work. It gives developers one API to clean, validate, match, transform, protect, and analyze messy data instead of rebuilding those capabilities for every application.
I designed the platform around real production requirements, including API-key authentication, tenant isolation, usage metering, rate limiting, idempotency, asynchronous jobs, retries, webhooks, observability, and secure data handling.
MessyAPI also includes JavaScript and Python SDKs, OpenAPI, MCP support, CLI tooling, RapidAPI integration, interactive testing, and composable workflows for chaining multiple data operations together.
The goal was simple: turn common data infrastructure developers repeatedly build themselves into one reliable API.
one API for messy data instead of rebuilding it every project is a big win