Quote · The MongoDB Podcast
From Data to Decisions: Powering gen/Agentic AI with Capgemini & MongoDB
Where this was said
Case Study: Predictive Maintenance for Oil & Gas with MongoDB, Capgemini & AWS
At 19:28 · chapter starts 17:10
The episode's centrepiece is a detailed walkthrough of a tri-party reference architecture built by MongoDB, Capgemini, and AWS for critical equipment predictive maintenance in the oil and gas industry. Farid sets the commercial stakes with a Baker Hughes study: 80% of oil and gas companies face at least one unexpected critical equipment failure per year, [1] — Farid Mohammad "Unexpected equipment failure in oil and gas costs $250,000 per hour, and 80% of companies face at least one such failure per year according…" 17:10 and when it happens, the cost is $250,000 per hour. The previous approach was entirely reactive — time-based, usage-based, or rule-based maintenance — with no ability to anticipate failure across a complex production pipeline involving third-party equipment from companies like Halliburton. The new architecture changes all of that. Sensors stream real-time telemetry to MongoDB. Historical failure records, maintenance notes, and semi-structured PDF equipment manuals are all vectorized and stored in MongoDB alongside live data. [2] — Farid Mohammad "Sensors stream telemetry into MongoDB. Historical failure data and equipment manuals are vectorized and stored in the same platform. When a…" 20:30 When an anomaly is detected in the telemetry, vector similarity search scans the historical failure corpus to find resonant past cases and surfaces a recommended repair approach. Finally, an AI agent automatically creates a service ticket and assigns it to a field engineer — proactively, before failure occurs. Vinay then describes how the solution matured: starting from basic RAG and workflow automation, it evolved to include digital twins, AI/ML hybrid models, IoT streaming, and ultimately the ability to predict faults even before anomalous data appears in the stream.
Unexpected equipment failure in oil and gas costs $250,000 per hour, and 80% of companies face at least one such failure per year according to Baker Hughes. A tri-party reference architecture using MongoDB's vector search, AWS Bedrock, and Capgemini's domain knowledge now predicts failures before they happen.
A Baker Hughes study found that 80% of oil and gas companies experience at least one unexpected critical equipment failure within a year.
Unexpected critical equipment failure in oil and gas results in $250,000 per hour of business impact, according to a Baker Hughes study.
Sensors stream telemetry into MongoDB. Historical failure data and equipment manuals are vectorized and stored in the same platform. When an anomaly is detected, vector similarity search finds past failures and recommends repairs. An agent automatically creates a service ticket and assigns it to a field engineer — all before failure occurs.
The oil and gas predictive maintenance solution evolved from rule-based reactive maintenance to AI-powered anomaly detection that identifies faults before failures occur.
The oil and gas solution started as a basic RAG and vector search implementation. It then evolved to include workflow automation, digital twins, AI/ML hybrid models, and real-time IoT streaming. The final phase: predicting faults before equipment even starts streaming anomalous data.
