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
Built an AI-powered analytics solution in Snowflake using Cortex to give business users natural-language access to trusted operational data. I created semantic models, verified queries, business rules, and curated views, then organized multiple Analysts under a single Agent so users could ask questions across different subject areas and receive governed, consistent answers.
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
A 6-month MIS dashboard tracking revenue, expenses, net profit and margin trends with an auto-updating bar chart, giving founders a one-page view of business health.
:Nikit — Local-First AI Desktop Application
Nikit is a local-first AI desktop application I designed and built around my custom ZaqX language model. The project combines a modern desktop interface with local AI inference, context handling, tool controls, and a privacy-focused architecture.
I built the application with React, TypeScript, Vite, Tauri, and CSS Modules, with a modular architecture designed for performance and maintainability. The project also includes a custom small language model and supporting AI infrastructure.
The goal was to create a practical AI workspace that feels like a real product rather than a simple chatbot, while keeping the experience fast, focused, and local-first.
AI isn’t just changing the way we build software.
It’s changing how many people are needed to build it.
A few years ago, a project might need a team of 8–10 developers, designers, testers, and other specialists.
Today, with AI coding tools and “vibe coding,” a single experienced developer can potentially handle a much larger portion of that workload.
Give that developer a powerful AI tool, a paid subscription, and the right workflow — and suddenly, work that previously required multiple people can be completed by a much smaller team.
That raises an uncomfortable question:
How many jobs will AI actually replace in the IT industry?
And the bigger question:
Are we entering an era where companies will hire fewer people, but expect each person to operate with AI at 5–10× their previous capacity?
AI is creating new opportunities too. But at the same time, some traditional roles and entry-level opportunities are clearly being reshaped.
The biggest skill may no longer be just “Can you code?”
It may become:
“Can you use AI to build, solve, debug, and deliver?”
What do you think?
Will AI create more IT jobs than it replaces — or are we already seeing the beginning of a major shift in team sizes?
Do you think leadership will actually reduce engineering headcount to cut costs, or just keep team sizes the same and drastically raise expectations on what gets delivered per quarter?