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
AI-Powered Job Application Agent for MQL5 / MetaTrader Freelancers
I built an automated agent that monitors freelance job boards in real time, filters postings by budget and competition, and writes tailored, client-specific proposals — then submits them within a safe, human-like time window.
What it does:
Watches new job postings continuously (60-second polling)
Filters out low-budget or oversaturated jobs automatically
Uses AI to read each job description and match it against relevant skills
Calculates fair pricing and delivery timelines per job
Writes a short, specific proposal (not a copy-pasted template)
Applies with human-like delays to stay within platform limits
Built with: Python, Playwright, Gemini AI, SQLite
I use a version of this system for my own MQL5 / MetaTrader / algo-trading work — Expert Advisors, quant strategies, and automated trading tools. The same architecture can be adapted to any freelance niche where fast, relevant proposals matter more than mass-applying.
If you need:
A custom Expert Advisor or trading bot (MQL4/MQL5, MetaTrader 4/5)
Backtesting and strategy optimization
Automation tooling for your own workflow (job monitoring, proposal generation, lead qualification)
I build production-ready systems, not prototypes. Message me with your requirements and I'll scope it out.
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
An experimental AI-agent application for researching business opportunities using web search, webpage extraction, evidence collection and structured analysis.
The evidence collection step is where I would look first. When two pages disagree, do you keep both source links so someone can see why the analysis chose one?
"Businesses lose time and money to invoice errors that go unnoticed until it's too late. I built an automated pipeline that extracts invoice data, cross-checks it against vendor history, and flags anomalies with clear AI-generated reasoning — all visualized in a real-time dashboard. Stack: LangChain, Groq, n8n, FastAPI, Next.js."
Most agent bugs are invisible: the agent loops, drops context or calls a tool it shouldn't, and all you see is a wrong answer. I wrote an agent harness from scratch in Python — loop control, context compaction, permissioned tools, sub-agents — and Harness Studio, a web app that replays every run: one lane per agent, each event explained, and the exact context each agent held when it stopped.
