Production deployments · 2018–present

What we've shipped — in production, not in decks.

DehazeLabs engagements result in production systems, not strategy documents. These are the anchor deployments that define our practice — the work that established our depth in data center AI, edge perception, and multimodal platforms.

T-Mobile
Data Center & Infrastructure AI
→ What was built

Real-time SIEM pipeline at telco scale — distributed, sub-second threat detection across T-Mobile's network infrastructure. DehazeLabs built the ingestion, normalization, and detection layer that processes operational event streams at carrier volume. The agentic reasoning layer interprets signals, classifies incidents, and routes escalations with full context.

"DehazeLabs' team's expertise in building, deploying, and managing AI agents revolutionized our network optimization and elevated customer service efficiency."
— Director of Technology Innovation, T-Mobile
Hayden AI
Edge & Perception AI
→ What was built

Smart-city edge ML and perception data platform for automated traffic enforcement at scale. DehazeLabs built the end-to-end stack: real-world video ingestion from edge cameras across municipal deployments, frame-level structured datasets, production inference pipelines for vehicle and violation detection, and the data architecture that makes the system operable across a city-scale deployment.

Production perception platform powering automated enforcement across multiple US cities.
SponsorUnited
Multimodal Enterprise AI Platforms
→ What was built

Multimodal AI platform built from zero — video, audio, and document intelligence at production scale. DehazeLabs designed the data architecture, built the CV detection and LLM validation pipeline, implemented hybrid RAG retrieval, and shipped the agentic workflow layer. The confidence-stratified review queue — high-confidence outputs routed to production, borderline cases to human review — drove a 90%+ reduction in manual review burden.

90%+ reduction in manual review. Platform built end-to-end, 12+ months to stable production performance.
Cargomatic
Edge & Perception AI
→ What was built

AI/ML systems for logistics routing optimization and container unloading workflows. DehazeLabs built routing models trained on historical trip data, real-time re-routing logic incorporating traffic and availability signals, and CV for dock and container operations. ML-powered optimization across hard and soft constraints — driver preferences, dwell time patterns, reload sequences — that rule-based systems fail to handle in edge cases.

ML routing and CV in production across Cargomatic's logistics network.
Current lighthouse engagements — physical economy, in production
Lighthouse pilot
Maryadha
Manufacturing Quality AI
→ What was built

AI-assisted visual inspection for leather hide quality control across Maryadha's factory network. 4-week lighthouse: standardized raking-light capture protocol, defect taxonomy (scratches, wrinkles, stains, cuts, discoloration, edge damage), 500+ images labeled via CVAT, FiftyOne dataset with class-balance analysis, baseline defect classifier, and an operator review dashboard showing grade outcomes (acceptable/rework/reject) with batch-level analytics. The first facility where none of this existed before.

First Manufacturing Quality AI deployment — queryable defect dataset and operator review queue live in 4 weeks. Results generalize to textiles, electronics, automotive, and packaging inspection.
Under NDA
Robotics client
Physical AI Data Flywheel · Edge & Perception AI
→ What was built

Physical AI Data Flywheel engagement — MCAP log ingestion, multi-signal incident detection across localization, navigation, and perception topics, Claude-assisted triage hypothesis for each flagged incident window, FiftyOne frame curation with CLIP embeddings for visual similarity search, and CVAT annotation task export. Turns raw robot failure logs into a labeled, queryable ML dataset in 90 days. Client details available under NDA.

Incident detection pipeline running on client logs. Labeled FiftyOne dataset across multiple failure types. CVAT tasks ready for the ML team — not a folder of unlabeled images.
→ Additional clients
GRIN
Loaded
Sila Money
BlueOcean
Limit Break
Accompany Health
and many more

Full case studies available under NDA for qualified prospects.

→ Technical writing & case studies
Deeper write-ups live on the blog.
Architecture decisions, production lessons, and the full story behind the deployments above.
Read the blog

Building something that belongs on this page?

We work best with teams that have a real operational problem and want a system that ships — not a roadmap document. Tell us what you're trying to build.