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
Just shipped OpsAgent. An AI workflow builder for back-office teams that replaces a tangle of Zapier flows with one runtime that actually understands your data.
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 think every business needs an AI agent.
That's probably not the popular opinion these days, but it's the one I've come to after building automation workflows.
A lot of the conversations I have start with the same request:
"We want an AI agent."
So I ask a different question.
"What's slowing your team down today?"
The answers are rarely about AI.
It's usually someone copying information between tools.
Someone sending the same emails every week.
Someone updating spreadsheets by hand.
Or someone chasing people for updates.
Those are workflow problems.
Sometimes a simple automation fixes them.
Sometimes AI is the right next step.
The trick isn't choosing the newest technology.
It's choosing the one that actually solves the problem.
That's why I spend more time understanding the process than deciding which AI model to use.
The technology is important.
The workflow is what people actually live with every day.
What's your view on this?
Do you start with AI, or do you start by fixing the process?
I ran a session with my team on how to build a team of AI agents, and how to treat them so they actually deliver.
What we've seen running this setup on client work:
→ Agents running 24/7
→ 3B+ tokens in 6 days
→ A 2-week milestone done in 3 days
The 5 things I taught the team:
Treat agents like teammates, not software.
Give them a clear goal, the right context and tools they're comfortable with.
Tell them the goal, never the solution.
Let the agents propose the options. You make the call.
Talk to one agent, not ten.
A central PM agent takes the goal and coordinates the rest.
Solve today's problem.
Don't build the perfect agent on day one. Start small and let the team grow with the work.
Don't be the bottleneck.
Review at milestones, not every task.
For clients, this changes the pace. My job is understanding the problem and making the decisions. The agents handle the execution.
Highlights from the session 🎥
Building something and want to move faster with an AI-first team? Let's talk.
AI Workflow Architect is now live in the ChatGPT Plugin Directory. 🎉
A lot of businesses know they want to automate more — but the harder question is usually:
What should actually be automated, what needs fixing first, and what should stay human?
That’s what I built AI Workflow Architect to help with.
You can give it a real workflow — client onboarding, approvals, handoffs, internal operations — and it helps identify:
• the main bottleneck
• automation readiness
• missing information
• human responsibilities
• controls and safeguards
• the most important next step
The goal isn’t to automate everything.
It’s to make better decisions about where automation will actually help.
The plugin has now been reviewed and approved and is available publicly in ChatGPT.
If you want to go beyond the initial assessment, I also offer the Complete Automation Blueprint, where I turn the workflow into a structured future-state architecture with ownership, controls, exception paths and an implementation sequence.
AI Workflow Architect — Find what to automate.
“What should stay human” is the right wedge for a ChatGPT plugin — most teams automate the wrong step first. Public directory listing is a nice proof point.