Company Cloud

Not disclosedThe customer this was delivered for.Action CenterSave this case, request the same outcome from Tribe AI, share it, or get in touch.

Delivered ~90%+ Accurate GPR Prototype and 5-Foot Utility Detection Depth

A hardware and software development company set out to build the industry’s first commercial utility Ground Penetrating Radar (GPR) system for safely verifying underground utilities before digging. Standard site-assessment procedures still produced frequent inaccuracies, causing unplanned disruptions, delays, and financial liability for contractors. The team needed higher accuracy and portability than existing offerings and believed AI could materially improve detection performance. They also wanted the work to support patentable intellectual property. An end-to-end prototype was built to analyze scans from a custom GPR device and detect and locate underground objects. The system used AWS Elastic Kubernetes Service (EKS) for workload management, Python for machine learning, and React/Node for the application interface and backend. IMU data was integrated to correct scans and add context about ground conditions, while automated ingestion and preprocessing (e.g., de-wow, normalization, denoising, contrast enhancement, and data translation) prepared data for model inference. A tablet-based UI allowed users to run inference locally and review results as points or bounding boxes with confidence scores, with depth estimation informed by user-specified substrate type. By the end of the initial engagement, the team received a highly accurate (~90%+) prototype that could detect and locate underground infrastructure from the custom GPR scans. The handheld device concept targeted quick field adoption with an expected learning curve of about five minutes and produced a scan for a 10’ x 10’ area in about three minutes. The radar capability extended up to 5 feet deep, and a visual map was generated within about 30 seconds after scan completion. The prototype’s preprocessing and system design contributed to a successful patent application and helped attract investor interest and new funding to move the product into production.

Delivered by

Tribe AI

Not disclosedThe customer this was delivered for.Action CenterSave this case, request the same outcome from Tribe AI, share it, or get in touch.

55% Higher Audit Efficiency and 15% Higher Model Accuracy in ~2 Months

Challenge: A software leader providing end-to-end compliance and audit management had stalled on an AI-driven security product after model accuracy plateaued around 70%. The internal team needed an NLP specialist to optimize the existing model but lacked in-house expertise. The manual nature of the process limited how quickly the audit team could deliver for customers. Solution: An external team was brought in to evaluate the company’s approach, optimize the existing model, and explore alternative model strategies to improve audit efficiency. The work included reassessing the model approach (including whether Q&A would outperform STS), benchmarking different model choices (including inference time), and refining training data to reduce training time. The team also identified workflow issues in the modeling process and implemented a two-phase iterative plan to improve model accuracy while updating ML infrastructure for faster iteration and deployment. Results: In ~2 months, the engagement increased the core model’s accuracy by 15% using advanced NLP and a limited dataset. The accuracy lift increased audit team throughput, raising auditor efficiency by 55%. A foundational ML infrastructure was also put in place to support rapid ingestion of new data, retraining, and deployment at scale.

Delivered by

Tribe AI