HomeCompaniesWell Principled
Well Principled

The neural engine for autonomous robots

We aren’t building AI to replace "knowledge work” that requires neither, but to bolster the working human intellect which has never failed to discover new paths to prosperity. For all their success, mainstream approaches to AI have fundamental limitations preventing them from solving critical classes of problems. We are building a new AI architecture from first principles to break from these limitations. The status quo has ossified around the supervised, brute-force pretraining paradigm. These systems do not, and cannot, handle the essential skills of continual learning, goal discovery, novel planning, and the creation of new knowledge. These limitations are not trivial. Our national prosperity depends directly on overcoming these limitations, because the essential skills underlie the skilled trades. From electricians to machinists to nurses, apprentice tradespeople in all of these fields learn “skilled improvisation” where every solution is novel, and even the goal must be discovered. Prosperity demands the precise capabilities where status quo AI is structurally weak. Worse, these limitations will not be overcome with more compute or training data. They are inescapable consequences of the underlying technologies of supervised learning, neural networks, transformers, backprop, and gradient descent. Progress requires independence from them. We are building a new AI architecture by reverse-engineering the system that got us this far: the human brain. By triangulating between neuroscience, cognitive science, and the evolutionary elaboration of brains, we have identified the brain’s algorithms to (a) continually learn a causal world model (b) select goals to both achieve and learn to achieve more (c) plan to reach novel goals, and (d) creatively produce new knowledge. Join us in building intelligence with ingenuity to bolster the skilled trades.
Active Founders
Ryan Richt
Ryan Richt
Founder
Ryan has galvanized teams with bold vision and disruptive, patented innovations since 2003. Ryan transformed distributed analytics across an academic lab, his first bootstrap startup and computational biology and cloud teams at Monsanto. He grew VC-backed CiBO from 7 to 70 engineers and data scientists. Ryan holds an MBA and BA prob/stats from Olin and WashU.
Christopher Shafer
Christopher Shafer
Founder
Chronically the first customer-facing engineer, Chris has delighted customers with deep-data applications from corn germplasm catalogs to global satellite data and environment simulations. Marshalling his broad expertise from cloud architecture to data visualization, Chris delivers outcomes customers love and leads solutions teams to productize them.
Joseph Wingbermuehle
Joseph Wingbermuehle
Founder
Joe has spent 15 years building foundational platforms, from middleware at AT&T, to startups across FPGA-accelerated high-frequency trading, accelerated ETL, machine learning based network security (acquired by Cisco) and hybrid AI/physical models of global-scale crop simulation. Joe holds a BS in Applied Math and a PhD in Computer Science from WashU.
Company Launches
BODYSIM: Gain muscle and shed fat with a digital twin of your body
See original launch post

uploaded image

We're excited to announce a complete overhaul of BODYSIM from a tracking and modeling tool for your metabolism into an end-to-end fitness forecasting system. After launching our initial beta last fall, we discovered something crucial: our users didn't just need another tracking tool with cool graphs, they needed a complete solution that bridges the gap between goals and real results.

The Challenge of Getting Results is Still Valid

If you've ever tried to build muscle and lose fat, you know the frustration:

  • Conflicting advice from countless "experts" and unreliable information
  • Scattered data across different apps and devices, each telling a different story
  • The exhausting task of turning abstract targets into actual meals and workouts

The (new) BODYSIM Solution: Building Your Digital Twin

At BODYSIM's core is our advanced "digital twin" technology, combining sensor fusion with the science of metabolism and physiology to help you understand your true potential, using:

  • DEXA scans
  • BIA weigh-ins
  • 3D body scans
  • Fitness tracker data
  • Resistance training
  • Macro-tracking
  • Blood panel biomarkers

This comprehensive data integration unlocks hidden insights about your metabolism, including your Basal Metabolic Rate (BMR), Total Daily Energy Expenditure (TDEE), hormone balance, and body composition changes.

What's New: Tools are Not Enough - Get Our Users Outcomes

1. Prescriptive Meal Plans: Chef-Created Meal Plans & Virtual Meal Kits

  • Library of high-protein, low-fat recipes with step-by-step instructions to make eating for transformation easy
  • Customizable weekly meal plans based on your preferences and goals
  • Direct integration with Walmart and Amazon delivery: order your entire meal plan with a few clicks
  • Simplified food logging with grouping, automated recipe creation, and easy to repeat meals

uploaded image

2. Prescriptive Workouts: Comprehensive Workout System

  • 2,200+ exercises with detailed videos and instructions
  • Intelligent weekly split recommendations
  • Progressive overload tracking to optimize muscle gain
  • 3D scan integration to track individual muscle group progress

uploaded image

3. Fitness Forecasting: Advanced Integration Features

  • Scenario planning to understand how to achieve goals faster
  • Muscle group modeling that maps exercises to specific body measurements
  • Blood marker sub-models that connect nutrition choices to health outcomes with quantitative recommendations to make a change
  • Overtraining Syndrome (OTS) risk monitoring

uploaded image



Why Trust Us

This is what we do; our core tech distills messy academic literature into simulations. We've deployed science-based models of consumer behavior and battery electrochemistry to enterprise. We built BODYSIM to guide our own fitness journeys. It worked. I put on 45 lbs of muscle, and my co-founder put on 25 lbs of muscle while losing 50 lbs of fat.

And it worked in our alpha test (ages 29-69, 50% female). 8 alpha testers lost an average of 12.6 pounds in 3 months, and 4 alpha testers with a maintain goal changed <1.4 pounds in 3 months.

We then had some beta amazing beta tester results: one lost 40 lbs, another gained 12 lbs of muscle, a female user gained 8 lbs muscle, a co-founder gained 10 lbs of muscle, and more.

uploaded image

uploaded image

The Complete Package

Your BODYSIM subscription includes:

  • Quarterly DEXA scans
  • Withings Body Scan scale
  • Monthly at-home blood tests
  • Escali food scale for precise tracking
  • Daily body composition updates
  • Live signals like Resistance Training Intensity to adaptively steer to your goals
  • Personalized exercise and nutrition recommendations

Join Us

Join us in revolutionizing how people transform their bodies. With BODYSIM, you're not just getting another fitness app - you're getting a science-based, personalized system that guides you from where you are to where you want to be.

Ready to transform your body with confidence? Visit bodysim.com today.

YC Photos
YC Summer 2019 Demo Day Video
Well Principled
Founded:2018
Batch:Summer 2019
Team Size:3
Status:
Active
Location:St. Louis, MO