We deploy, we fail, we learn, we share.
Nature solved distributed intelligence millions of years ago. Now it's your turn.
AI workforces are about to absorb the grind. This is where you figure out what's left. And what to do with it.
From the publications
Opus Scored 115 of 115. Every Mistake Left Was Mine.
I set out to test whether AI could stay within Dutch rental law. The models under test kept finding errors in my answer key. Six principles for building evals, each one paid for.
- Let Them Run
The Bitter Lesson Needs a Score
Let the algorithm search, the bitter lesson says. But every self-improving loop climbs something. Whoever defines that score owns the edge.
- Let Them Run
Has AI Already Killed Sales Training?
Tim Ferriss asked it about nonfiction. The answer for MEDDPICC is on your own calls. A free Claude plugin that audits every call against the framework and coaches every rep each morning, built in 48 hours.
- Let Them Run
The Swarm That Hunts for Asymmetric Upside
AI struggles to find the ideas that mint monopolies. I built an agentic system that farms the raw material and run it on real markets.
- The Deep Connection
Six AI Reviewer Agents Signed Off on a $426,000 Mistake
Two layers of AI checked the work. Neither one did the math. What caught the error was a gut feeling about the shape of a number, and gut feelings don't scale. The fix fits in one file.
- Let Them Run
Outrunning the AI Hype Train: How I Built a Swarm to Read Research Papers Before YouTube Does
I found out about Hermes from a YouTuber with a few hundred thousand views. To my credit, I traced it back to a 30-year-old PhD thesis within an hour. But that is not the edge I want. The edge is reading the paper before anyone makes the video. So I built a swarm of agents that does the slog for me, runs all night, and turns a corpus into novel theses I can be first to test.
Something structural is shifting. Most people are waiting for a playbook. We're writing it by doing.
Agentic swarms, distributed intelligence, human-AI coordination. This isn't just theoretical here. We deploy, we fail, we learn, we share. If you want to stay on the cutting edge of AI augmentation, you're in the right place.
Four ways in
- Let Them RunDeploy the swarm. Shape the outcome. (15)
- The Deep ConnectionGoing from AI slop to reader engagement. (4)
Voices from the training
“I feel like I’m living in the future already.”
Tom ParkerConsultant, The Sales Architect “YOLO mode, thank you for that!”
Andreia SaraivaConsultant, Wise Pirates “This is great. I am feeling like I have the keys to a Ferrari.”
John FarrallChief Commercial Officer, SymetryML “Yeah, this is pretty f****** exciting. I can build. I can do anything.”
Karan BavandiFounder, Optimal Access “You set the vision. They run with it. That’s the shift.”
Stay ahead of the shift.
- Weekly dispatches on structural AI shifts
- First access to new publications and research
- Operator playbooks from practitioners in the field
One email a week on what we deployed, what broke, and what it taught us.
One email per week. Unsubscribe anytime.
Swarm Operators is a private circle of operators, builders, and leaders dissolving cognitive bottlenecks. Entry by application.
Three short questions follow, then a human reads your application.