T-Minus 4 Weeks: Rapid Prototype for Spatial Object Tracking Product
- Jun 6, 2022
- 2 min read
The Situation:
An AI startup needed to secure a large commercial contract with a Fortune 100 consumer company. To do so, they had four weeks to demonstrate accurate, near real-time tracking of people moving through a physical environment. Measured in milliseconds, not seconds.
This was not a science project. The demo needed to work reliably, under executive scrutiny, with no room for hand-waving.
We had three things working in our favor which shaped every technical decision that followed:
a clearly defined success criterion
a non-negotiable timeline
a small, focused team with explicit ownership
The Approach:
Rather than over-optimizing models or chasing edge cases, we designed the prototype around a simple question:
What is the minimum system that proves this can work in production?
The system needed to:
Capture positional data from physical sensors
Identify people in the environment
Translate noisy sensor data into stable trajectories
Visualize movement in near real time
Each step was chosen to de-risk the next.
Key Technical Decisions:
Physical environment & instrumentation: We converted an office space into a controlled mock retail environment and instrumented it with video sensors. This allowed us to test realistic movement patterns while keeping variables manageable.
Spatial alignment: We anchored sensor output to a shared coordinate system using physical reference markers, projecting all detections onto a unified 2-D plane. This made downstream reasoning and visualization tractable.
Person detection: We integrated a person-detection model directly into the sensor pipeline, mapping detections to approximate real-world positions in near real time.
Noise handling: Real-world sensor data is messy. Raw output caused erratic trajectories. People appeared to jitter and teleport across the space. Instead of smoothing after the fact, we applied a Kalman filter to model both motion and noise explicitly. This preserved responsiveness while producing stable, believable movement. That was what earned executive trust in the demo.
Visualization: We streamed the processed data into a live visualization, making latency and positional accuracy immediately legible. A parallel front-end effort delivered a custom UI that overlaid movement on a floor plan and tracked session-level metrics.
Outcome:
This was a prototype, not a full product. We deferred some production features, like robust re-identification, on purpose.
What mattered was that, within four weeks, the system could:
Detect people moving through a physical space
Estimate and smooth their trajectories
Stream accurate positional data to a live dashboard in near real time
The demo landed. The executive team approved the engagement, resulting in the largest commercial contract in the company's history. The prototype became the foundation for a production system used across multiple clients.
Why this matters:
Many AI demos fail not because the models are weak, but because the system design collapses under real-world constraints. This project succeeded because we treated the prototype like the first slice of a production system, not a throwaway proof-of-concept.
Designing for reality under time pressure is what I bring to every engagement.
________________________________________________
If you're building an AI prototype that needs to survive contact with real users, messy data, and hard deadlines, I'm happy to talk.