Maggie Special Insights

The data your robots are missing lives in real homes.

Maggie Special Labs is a lab for the practical application of AI in the home, and for learning from how homes actually work. We turn a deployed, consented, allocentric system into the real-world signal robot learning teams cannot get from simulation.

Allocentric by design Consented real-home data Human-in-the-loop labeling Detroit and Accra Public Benefit Corporation
The Gap

Robots that ace the lab still fail the kitchen.

The distance between benchmark performance and real household performance is the single largest barrier to useful home robotics. It is also where the training data does not yet exist.

In simulation (RLBench)
89.4%

Task success rate for robotic manipulation systems in simulation. Tidy, repeatable, fully observed conditions.

In real households
~12%

Task success rate on real-world household tasks. Robots fail nearly nine in ten of them. This is the sim-to-real gap.

Source: Stanford HAI, 2026 AI Index Report.

Simulation rewards clean geometry, known objects, and conditions that never change. Real kitchens do not cooperate: clutter, glare, unfamiliar dishware, wet surfaces, and a thousand small variations that never appear in a synthetic scene. Models trained on staged data collapse the moment they meet a home they have not seen. The missing ingredient is not more compute. It is real-home interaction data, and labeled examples of the exact edge cases where models break.

What We Provide

Signal from occupied kitchens, not staged labs.

We operate a working system in real homes across two contrasting markets, and the humans who keep it reliable produce labeled data as a byproduct of doing their job well.

Real-Home Interaction Data

Occupied kitchens, consented and structured

Interaction data from a deployed allocentric system running in lived-in kitchens across Detroit and Accra. Not staged lab footage. Collected with consent and delivered structured for training.

Edge-Case Labeling

Human-in-the-loop, turned into training signal

Trained Domestic Technologists resolve the cases the system cannot handle on its own. Every intervention becomes a labeled example of exactly where a model failed and what the correct action was.

A Working Platform

Non-humanoid, already performing

A deployed, non-humanoid platform already executing narrow, high-value manipulation tasks in real homes. This is a running deployment generating data now, not a research promise.

Two-Market Coverage

Environmental and cultural diversity

Parallel deployment in Detroit and Accra gives your models exposure to genuinely different kitchens, dishware, layouts, and habits. Diversity that makes trained systems more robust everywhere.

From Video to Understanding

This is what real-home data looks like.

Consented capture inside occupied kitchens, from the deployed system and the Domestic Technologists who keep it reliable. A label tells a model what. A sequence teaches it why.

Sequence of a dish being washed, rinsed, scrubbed, and given a final pass in a real kitchen

Wash, rinse, scrub, final pass. The temporal grammar of a task, captured in a real home.

Hands rinsing over a basin in real light

Real materials, real light. Not rendered.

i.

Object affordances

Clay basin, plastic vessel, porcelain plate. Different materials, different grips, different physics.

ii.

Process sequences

Wash, rinse, stack, dry. The order in which a domestic task is actually completed.

iii.

Material physics

Soap suds, water displacement, surface reflection under real light. Real, not rendered.

iv.

Cultural variants

Universal tasks performed with non-Western tools and techniques. The long tail of how the world lives.

Our Stance

Consented data. Shared benefit. No extraction.

Every data point we deliver is collected with the consent of the households we serve. We do not harvest homes. People know what the system sees, and they agree to it.

The workforce that produces our labeled data shares in the benefit of it. The Domestic Technologists who resolve edge cases are trained, credentialed, and paid toward a living wage, not treated as invisible annotation labor.

As a Public Benefit Corporation, this is not a marketing posture. It is written into how we are governed. Serious partners tell us this is a reason to work with us, not a constraint. Data with a clean provenance is data you can build on.

Ways to Engage

Three ways to work together.

We shape each engagement to what you are building. Specifics, including terms, are discussed directly.

01

Data Partnership

Structured, consented real-home interaction data from our deployed system, delivered for your training pipeline.

02

Edge-Case Labeling

Targeted, human-labeled examples of the specific failure modes your models struggle with, produced by our Domestic Technologists.

03

Co-Development & Pilot Access

Deeper collaboration: shape data collection around your research questions, or run a pilot against our live deployment.

Start a partnership conversation.

Tell us what you are building. Rose responds to every serious inquiry directly.

Under NDA we can share: a deployment overview, representative data samples, our workforce model, and the roadmap.
Early conceptProduction-ready
✓ Thank you.

Your inquiry is in. We will follow up directly, and can move under NDA to share a deployment overview, data samples, our workforce model, and the roadmap.