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
MyJobs is an AI-powered job application automation platform for LinkedIn
🎯 Core Mission
Automate the entire LinkedIn job application lifecycle—allowing users to apply to dozens of relevant jobs per week with minimal effort. Target: 75% time reduction in job searching.
🏗️ Architecture Highlights
Frontend: React 18 + TypeScript + Vite (chat, dashboard, automation controls)
Backend: FastAPI + LangGraph agent orchestration + MCP servers (Jobs, Resume, Interview, Analytics)
AI/ML: Multi-LLM (Ollama local + Anthropic Claude), RAG pipeline with Qdrant vector store
Data: PostgreSQL (relational) + Qdrant (vector embeddings)
Automation: Playwright for LinkedIn interactions, VAPI for voice screening calls
💡 Key Features
Chat Interface — Natural language commands (/apply, /status, /search)
Resume Management — Upload, AI-optimize for ATS, tailor per job
LinkedIn Automation — Auto-fill applications, send follow-ups, track status
Job Profiles — Create multiple search profiles (keywords, locations, levels)
Applications Dashboard — Kanban board + table view of all applications
Interview Prep — VAPI voice agent for HR screening calls
Analytics — Insights on response rates, time-to-interview, etc.
đź“ŠÂ Data Flow
User message → WebSocket → LangGraph Agent → RAG retrieves resume/job context → LLM (Ollama/Claude) → MCP tools execute → Response streams to user
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
NetworkAI — AI-Powered Campus Network Monitoring System
A real-time network monitoring dashboard designed to help campus IT teams observe network health, monitor interfaces, and identify potential issues from a single interface.
What I built
Real-time network monitoring with live interface and system status
Network interface analytics showing traffic and connection activity
Historical monitoring data for analyzing network behavior over time
Live WebSocket communication for continuously updated monitoring data
Network controls to start and stop monitoring directly from the dashboard
Interactive charts and visualizations for easier interpretation of
network metrics
Responsive dashboard UI designed for clear monitoring rather than unnecessary complexity
FastAPI backend providing REST APIs and WebSocket communication
React frontend with a modern monitoring-focused interface
Why I built it
The goal was to create a practical campus network monitoring system that demonstrates how real-time networking data can be collected, processed, and presented through a modern web interface.
cool project bro. live data + history in one place is useful. how do you handle reconnecting when the websocket drops?
• Oct 5
BEFORE it shows your post to a single STRANGER.
And most headlines tell it nothing.
The system is called 360Brew.
Â
It doesn't just read your post.
It reads your profile, your last posts,
and the reader's history.
Â
Then it asks one question:
"Who is this person an expert for?"
Â
No clear answer?
No stranger reach.
Â
That matters more than ever.
Â
Per 2026 algorithm studies, only ~31%
of a LinkedIn feed comes from people you follow.
Â
The other ~69% is interest-based.
Strangers. Your future clients.
Â
Two more numbers worth knowing:
Â
→ 8 on-topic posts out of 10 beat 6 out of 10
by roughly 30% in reach.
Â
→ Your profile now counts as proof.
If your headline says "Helping people grow,"
the AI can't place you anywhere.
Â
So posting more won't save you.
Â
→ Rewrite your headline:
"I help [who] get [result]."
Â
→ Make your About and banner say the same thing.
Â
→ Keep 8 of every 10 posts on that one problem.
Â
(Yes, it feels boring.
Boring is how the AI learns you.)
Â
Being known for one thing
beats being liked for ten.
Â
Paste your headline in the comments.
I'll tell you what LinkedIn probably thinks you do.
Super clean work!