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
Freelancer OS Agent - Type a brief, get a full Notion workspace in seconds
Every time I landed a new client, I spent 30-45 minutes doing the same admin - creating project pages, setting up task boards, drafting invoices, building kickoff checklists. Same steps. Every single time.
So I built Freelancer OS Agent.
You type one sentence describing the client and project. The agent does everything else - automatically building your entire Notion workspace across 4 connected databases simultaneously.
→ Client record (name, budget, dates, project type)
→ Deliverables board (Kanban, linked to client)
→ Draft invoice (correct amount, correct dates)
→ Kickoff checklist (categorised action items)
Zero forms. Zero dropdowns. Just plain English.
Built with Notion Custom Agent API + GPT-4o + Python.
Demo video: https://youtu.be/ksc0dP3YIS0
GitHub: https://github.com/adetonayusuf/Freelancer-OS-Agent
Built by Adetona Yusuf Olalekan - Lagos, Nigeria.
"I built the tool I wish I had when I started freelancing."
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
Been freelancing on Contra and building a tool for freelancers at the same time lol.
It's called ProposalForge. You give it a client brief and your rate and it drafts the proposal, and I use it on my own drafts too.
It's live now and free to try (3 proposals, no card). The video shows a free checker I made along the way that marks the phrases that make a proposal sound like ChatGPT. No sign-in: proposalforge.site/check
I'm trying to see where people actually get stuck. What part of writing a proposal takes you the longest? The opening, scoping and pricing, or just getting started?
Why AI Agent Demos Break in Production
An AI agent demo only has to work once, on a clean input, with you watching. In production it runs again and again on messy real inputs, and nobody's watching.
I've built AI into real products, from a repricing engine that runs 24/7 for a US Amazon seller to a voice automation platform for a company in Germany. These are the three things I put in place before any agent goes live:
1. Scoped tools, not open access
Give the agent a short list of actions it's allowed to take, each with its own limits, instead of raw access to your database or APIs. Anything that touches money, customers or deleting data needs a human to approve it.
2. A plan for when the model fails
Model calls are slow, they time out, and sometimes they return something that makes no sense. Run agent work in background jobs with timeouts and retries, check the output before acting on it, and hand the task to a person when it still can't be trusted.
3. A log of every decision
Store every input, tool call and output. When the agent does something strange (and at some point it will), you can see exactly why and fix it instead of guessing.
None of this shows up in a demo. All of it decides whether the agent is still running a month later.
Planning an AI agent for your product? I offer a free build audit: calendly.com/roshaanali-business
"Works once with you watching" is the best way I've heard it put. Timeouts and a human fallback are the parts most demos skip.
AI is booming nowadays, but so is the creativity of the minds who are behind it.
This one was a big challenge-constructing almost everything through AI generation, just enough to not make it look AI-generated. Hundreds of prompts at work, thousands of hours invested, and don't know how many nights were passed awake, with only one thought in mind...
"Can I make AI keep up with the creative intelligence that I, a human with limitless potential like every other human, possess?"
