How an AI measures in 10 seconds what takes you 3 hours

The AI stack

PlotonIQ uses specialised models for each task rather than one model for everything.

Language: Language AI + Fast Inference Provider

Language AI handles all text tasks: quoting, price justification, business chat, briefing. Strong at structured output (JSON), numerical reasoning, and industry-specific instructions.

Fast Inference Provider serves as fallback. If Language AI is unavailable, a fast-inference model with open-weight models takes over automatically. Slightly lower quality, but availability rises to 99.9%+.

Vision: Object Detection + AI Model + Cloud Vision Cascade

For AI measurement, a multi-model cascade:

AI Vision — object detection, bounding boxes.

AI Model — text-prompt localisation ("find all glass surfaces").

AI Model — context analysis (window type, glazing).

Cloud Vision Cascade — pixel-accurate polygon segmentation. Not rectangles — true contours. 5–15 seconds per photo.

Audio: Speech Recognition

AI speech recognition — speech-to-text, 95%+ accuracy, all 17 languages. PlotonIQ extracts materials, dimensions, customer names and scheduling from the transcript automatically.

Production: Physics, not AI

Production scheduling deliberately uses deterministic algorithms. Machine throughput rates, setup times, deadline prioritisation — physics and logic, not pattern recognition. No API costs, no latency, predictable results.