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
Your resume might be ready. But is the job opportunity worth applying for?
I’ve been building ResumeIQ AI to help job seekers look beyond the usual ATS score.
Two features I recently implemented focus on problems that are easy to overlook:
🔎 Job Posting Health
Analyzes job descriptions for potential warning signs, including registration fees, suspicious urgency, and mandatory equipment purchases.
📊 Resume Freshness
Highlights skills that lack recent evidence in your resume, helping you identify where recent projects, experience, or learning could strengthen your application.
The idea is simple: evaluate the opportunity and understand how well your resume demonstrates relevant, current skills.
I'm now making ResumeIQ AI available as a source-code product for developers who want to explore, customize, or build on the application.
Looking for something tailored to your workflow? I’m also open to discussing customizations and AI-powered features for existing applications.
Interested in the source code or a tailored implementation? Send me a message here on Contra.
#AI #Java #SpringBoot #ProductDevelopment
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 don't know if I'm making the right move or not. 😅
I've moved from Upwork to Contra, hoping for better opportunities.
Will it work out? Honestly, I don't know yet.
But I'm keeping my expectations high and giving it a shot.
So, say hi! I'm new here.
And if you're already on Contra, I'd love a few tips:
How did you land your first client?
What should a beginner focus on?
Any mistakes I should avoid?
Let's connect and help each other grow!
Hi Hun!
I've been on Contra for years now (i suspect since the early days) and have had a lot of work from it over the years, including long-term clients.
I landed my first clients fairly early (within a couple of months, I'd say) into using it but here are some tips if...
CRAG — Self-Correcting Research Assistant
Overview
A research-assistant project exploring how AI applications can retrieve information and improve the quality of their responses through a self-correction workflow.
Project focus
Python-based AI application development.
Retrieval and research workflow design.
Improving answer reliability through evaluation and correction.
Technologies: Python, AI, retrieval-augmented generation.
Self-correcting retrieval is the upgrade RAG has needed, Daniel. Most systems stop at the first retrieval and hope for the best, so building evaluation and correction into the workflow is a real reliability win. The live telemetry dashboard makes it feel production-ready.
My AI assistant runs all day. The expensive model only does the thinking.
Most requests need no AI at all. "Call me in 30 minutes" is handled by plain code. Reminders, schedules and limits are code too.
Short tasks like sorting and scoring go to fast models on a free tier.
The big model only gets planning and long conversations, where it actually has to think.
If it hits a limit, a backup model answers instead of the app going silent.
If your AI app's bill keeps growing, check what really needs the big model.
What does your app send to the most expensive model?
Same pattern holds in outbound tooling. Filtering, dedupe and enrichment lookups are plain code. The model only writes the first line once the row is already verified. Cuts cost and the weird outputs.