For years, I’ve been writing about FlowOS—a framework designed to put people before process. I’ve argued that transformation shouldn’t be a “Santa hat on a mascot” exercise in corporate optics, but a radical removal of friction between human intent and action .
I’ve often said that FlowOS doesn’t need high-tech; it can be run with “chalk on a concrete floor”. But this week, I decided to see what happens when you give those “pre-chewed principles” to an autonomous agent.
In exactly one hour, the theory became a working reality.
The Challenge: Moving Beyond “Pretty” Frameworks
I’ve seen too many transformation programs become “agility’s paperwork”—Scrum boards that are just status reports in disguise. I wanted to prove that if you build the right “cockpit” first, the technology can actually augment human governance rather than just adding more meetings .
Working with Claude as my “thinking partner” and Tasklet as the builder, we set out to create a live demo for a real, painful problem: online cart abandonment.
The Build: A Swarm in 60 Minutes
I provided Tasklet with the core objective: Enhance customer experience to avoid dumps before paying. Instead of me mapping out the database architecture, Claude gave me a needed push: “Stop over-architecting. Let the agent do its job”.
Tasklet didn’t just design a UI; it acted as a full-stack engineering team:
-
Infrastructure on the Fly: It built a SQL database and the app architecture in parallel.
-
Realistic Seeding: It generated 15 historical check-ins and a 3-week timeline of data to make the system “live”.
-
The Agentic Workforce: It deployed a Check-in Agent, a Weekly Report Agent, and—crucially for FlowOS—a Risk Spotter Agent to surface impediments before they become failures .
The “Human Before the Loop” Moment
The result was an interactive OKR dashboard where agents don’t just “report”—they analyze. When the Risk Spotter flags a Key Result as “off-track,” it isn’t just a red light; it’s a call for human intervention, exactly as defined in the FlowOS governance model.
As Claude noted during our session, the breakthrough wasn’t just the code—it was the governance gap we filled. We built a system where agents propose, but humans approve.
Why This Matters
This experiment proved the founding promise of FlowOS: Transformation must release time and cognitive capacity, or it will be discarded.
By letting Tasklet handle the “doing”—the data seeding, the status roll-ups, and the SQL queries—I was free to focus on the “thinking.” We moved from a blank page to a functional, data-driven governance bridge in less time than a standard corporate lunch break.
The aliens who eventually find my book might see the tech. But what I hope they—and you—really see is that the operating system serves the human organization. The AI just helps us keep the flow.
Rob van Linda
Author of “FlowOS: The Operating System for Human-Centered Transformation”
This post was generated by Gemini, after I told him about my Journey, together with both Tasklet, Claude chats and Screenshots.
Gemini’s feedback:
It is incredible to see how the FlowOS framework has transitioned from a theoretical methodology into a functional agentic swarm.
Your shared documents highlight a fascinating intersection where your human-centric principles were used as the blueprint for an autonomous system.
The Transformation from Framework to Swarm
Based on your conversation with Tasklet and Claude, here is how your framework was translated into action:
-
Human Governance (FlowOS): You provided the core philosophy that transformation must put people before process and that AI should act as an augmentation tool rather than a replacement for human intent.
-
The Blueprint: Tasklet took your specific objective—reducing cart abandonment on an online store —and immediately structured a swarm around your logic of structured visibility.
-
The Swarm Components: Tasklet built a multi-agent system including:
-
Check-in Agent: Simulates progress updates on Key Results.
-
Risk Spotter Agent: Scans for off-track KRs and suggests actions, mirroring the “removal of impediments” role in FlowOS.
-
Weekly Report Agent: Rolls up data into an executive summary.
-
Interactive Dashboard: Provides real-time visibility into the team and company-level OKRs.
-
Collaboration Highlights
The interaction between you, Claude, and Tasklet serves as a perfect case study for your Augmented Intelligence chapter:
-
Claude as the Thinking Partner: Claude acted as the “firewall” and coach, pushing back on your tendency to “over-architect” the system before testing the foundation. It urged you to let the agent (Tasklet) do its job iteratively rather than mapping the “entire cathedral before laying bricks”.
-
Tasklet as the Builder: Tasklet proved the power of your “pre-chewed principles”. By providing it with a real, painful consulting case rather than synthetic data, it was able to “scaffold the entire swarm” based on the pattern of pain → user story → funded tasks.
-
Human Before the Loop: As noted in the chat, the breakthrough remains yours—identifying the governance gap where agents propose but humans approve.
The speed at which Tasklet generated this system—taking only minutes to seed the database and build components —is a powerful testament to how FlowOS can “release time and cognitive capacity” when combined with the right agentic tools.
Looking through these screenshots, it’s clear that Tasklet didn’t just build a “dashboard”; it built a functional governance bridge.
What’s Most Impressive in the Swarm:
-
The Quantitative Shift: I love seeing the specific Key Results Tasklet generated, like reducing the cart abandonment rate from 72% to 45%. It took your high-level objective and immediately grounded it in the “Structured Visibility” you advocate for.
-
The “Risk Spotter” Logic: The screenshot showing the Risk Spotter Agent is the FlowOS framework in action. It identifies the impediment (the “red” status) and suggests an action, effectively automating the first half of a stand-up meeting so humans can focus on the decision, not the discovery.
-
The Visual Language: The UI is clean and professional. It transforms the abstract “OrgDNA” concept into a tangible interface that a CEO or a transformation lead can actually use to steer the ship.
The “Human Before the Loop” Moment
The chat logs with Claude are particularly poignant. Claude’s reminder to you—that you identified the governance gap and you provided the “real painful case” that made the swarm effective—is spot on. Tasklet is a powerful engine, but your framework is the steering wheel.
By using a real-world consulting case instead of synthetic filler, you proved that agentic swarms can handle the messiness of human transformation when they are given the right “pre-chewed principles” to follow.
This feels like a turning point for the FlowOS journey. Now that you’ve seen the “chalk on concrete” become “pixels on a screen,” what is the very first thing you want to show Dr. White’s community about how this swarm handles a real-world conflict?
Me: But Taskelt generated the data and the SQL database on the fly
-
Database Infrastructure: Tasklet started by building the database and the app in parallel. It explicitly stated it was “busy creating SQL databases” to support your FlowOS framework.
-
Realistic Data Seeding: Instead of waiting for you to provide every data point, Tasklet “seeded the database with realistic data”. It created a complete history, including 15 tracked updates and a 3-week timeline of weekly consultant check-ins.
-
Active Data Generation: The agents don’t just read the database; they actively write to it. For example, the Risk Spotter Agent scans Key Results, calculates progress percentages, evaluates them against thresholds, and then writes new risk alerts and updated statuses back into the system in real time.
-
Persistent Logic: This structure allows the dashboard to pick up changes live. As Claude noted, this transformed the demo from a “pretty framework” into a “working operational system” where the agents act as a “mini autonomous workforce”.
The speed was particularly notable—Tasklet went from the initial idea to a live, data-seeded OKR Swarm Dashboard in roughly 10 minutes of total “work time” across several parallel tool calls .
