PersonalWindfield Intelligence Series · Article 11

Coloring Outside the Lines: Why Having a Co-Founder Is So Important

A late-night text exchange with my former co-founder made the compound reliability math obvious. You cannot build an autonomous system without surrender. The biggest companies in the world are not scoring because they are not relinquishing control.

T
Tommy Saunders
Senior Sales & Marketing Technology Strategist
Apr 16, 2026· 9 min read
5.4%
End-to-end at 85%/step
99.7%
Per-step needed
18
Pipeline steps
1 day
Windfield test cycle

I have been watching Y Combinator videos on YouTube for years. It is one of the best channels for finding up-and-coming ideas and innovations. The biggest companies in the world went through YC. Great cast of founders, investors, and operators. And one of their common threads — a thread so consistent it might as well be a law of physics — is that every company needs a co-founder. They will not even accept solo founders into most batches. I always understood that intellectually. I did not understand it viscerally until a late-night text exchange.

01The Late-Night Text Exchange

I was texting back and forth with Ben Niehues IV — my former co-founder from FEWDM — about what I have been building with Intelligent Operations. Ben is a UX Design and Strategy Leader at CommunityAmerica Credit Union now, but we built a fitness tech startup together years ago. I was deep into the problems. The kind of problems that only surface when you are actually trying to make an agentic system work in production, not when you are reading about agentic systems working in demos.

I was texting him about the gaps. The places where AI gets you 80% of the way there. Sometimes 90%. On a good day, maybe 99%. But it never gets you all the way there. There is always a gap between what the model produces and what production requires.

The Problems Every AI Builder Knows

Model outputs that are 95% correct — but the 5% corrupts everything downstream.

Agents that work perfectly in testing — then fail on the first real input that deviates from the test data.

Pipelines that complete successfully — but produce output no human would actually trust.

Automations that save 3 hours — then cost 4 hours to fix when they break.

Context windows that lose the plot — the agent forgets what it was doing by step 12.

Confident wrong answers — the model does not know what it does not know.

02“I Just Color Inside the Lines”

His reply was so simple it stopped me. “Yeah, of course,” he texted back. “But I just color inside the lines.” That is it. That is the whole answer. He does not fight the model. He works within the boundaries of what actually works, measures the results, and expands the boundaries only when the evidence says the boundary is ready to move.

This is why you need a co-founder. Yin and yang. I am the person who sees 18 agents coordinating a full property intelligence loop and thinks: yes, let us build that. Ben is the person who says: great, but which one of those 18 agents have you actually tested in production?

“Yeah, of course. But I just color inside the lines.”

Ben Niehues IV · Former Co-Founder, FEWDM · UX Design & Strategy Leader, CommunityAmerica Credit Union

03And Then I Did the Math

That text exchange made me do the math. And when I did, it was obvious. You cannot build an autonomous or agentic system without surrender. Without relinquishing full control. The biggest models in the world are not scoring production-grade reliability across long pipelines because the biggest companies in the world are not relinquishing control.

The Surrender Math

0.8518 = 0.054 — Five percent end-to-end success at 85% per step.

0.9918 = 0.834 — Even 99% per step only gets you 83% across 18 steps.

To reach 95% end-to-end across 18 steps, you need 99.7% per step.

Nobody gets to 99.7% per step without running the agent in production, measuring failures, fixing them, and running again. That requires organizational surrender. Large firms cannot do this. Small firms can.

“You cannot build an autonomous system without surrender. Without relinquishing full control. The biggest companies in the world are not scoring because they are not letting go.”

Tommy Saunders · Intelligent Operations AI

04Why Small Firms Get There First

This is exactly why Windfield Real Estate was able to build what we built. We are smaller. We do not have the red tape. Our ability to test agentic loops is fundamentally faster than larger firms. Because we can pivot and move in an instant across all of our areas of operation.

We can build a small loop — one agent, one property type, one task — and test it in a day. A large firm takes three months to get approval. By the time they have approved the test, we have run it forty times, fixed twelve edge cases, and earned autonomy for that segment.

05The Y Combinator Pattern

YC figured this out decades ago. The reason they require co-founders is not just about workload distribution. It is about the tension between vision and discipline. The founder who sees the future and the co-founder who grounds it in what works today.

06The Lesson for Builders

Find your co-founder. Not for fundraising. Not for the pitch deck. For the tension. For the person who asks the questions you do not want to hear.

Surrender control in small segments. You cannot earn production reliability without production data. You cannot get production data without letting agents run in production.

Be small enough to move fast. The compound reliability problem is solvable. But it is not solved by the people who color outside the lines alone. And it is not solved by the people who color inside the lines alone. It is solved by the two of them arguing about where the lines should be.

Frequently Asked Questions

5
Building agentic AI requires two opposing mindsets: the visionary who pushes boundaries and the operator who enforces discipline. AI gets you 80–90% of the way there but never 100%. A technical co-founder who “colors inside the lines” provides the systematic rigor needed to close that gap.
Autonomous agentic systems require relinquishing control — letting agents run, fail, learn, and earn trust through measured performance. Large firms cannot do this because every failure requires committee review, legal sign-off, and risk assessment. Small firms can build small loops, test immediately, and pivot in an instant.
Coloring inside the lines means operating within defined boundaries — testing agents in constrained segments, measuring results against specific thresholds, and only expanding autonomy where the data supports it. Production-grade agentic AI requires both mindsets: vision to see what is possible and discipline to build it safely.
At 85% reliability per step, an 18-step pipeline has only 5.4% end-to-end success (0.85^18 = 0.054). Even at 99% per step, 18 steps produce only 83%. The biggest AI companies are not reaching production-grade reliability because they are not running enough real production loops to earn it.
Windfield can pivot and move instantly across all areas of operation. No red tape, no committee approvals, no six-month procurement cycles. Small agentic loops can be built, tested, and iterated in days rather than quarters.
T
Tommy Saunders
Senior Sales & Marketing Technology Strategist, Windfield Real Estate

Former co-founder of FEWDM with Ben Niehues IV. Building the IO Agentic Operating System — production-grade agent infrastructure for commercial real estate. 18 agents. 78 properties. One system.