Microsoft Software / SaaS United States

OriGen

Real-time Analytics

Like most businesses these days, energy companies are striving to do more with less. Historically, the energy industry has been slow to adopt new digital technologies, but the need to realize greater returns with lower outlay is driving the development of exciting new solutions. That’s where OriGen comes in.

As a major oil and gas provider in Colombia with an energy transport business as well, Ecopetrol partnered with OriGen in 2021 to see how it might take groundbreaking AI technologies into the energy industry to maximize
By running thousands of simulations that factored data alongside geological plausibility, OriGen successfully created a model that matched 85 percent of the wells in the oilfield of study.
In the case of reservoir simulation predictions, traditional CPU-based solutions consistently require thousands of simulations—with long processing times for each—to achieve an accurate prediction.
It chose the NVIDIA GPU-enabled virtual machines rather than CPU specifically because of the demanding need to run neural networks with billions of parameters.

Reported impact

Business outcome

With that enhanced accuracy and insight, Ecopetrol now makes more informed decisions about how to glean the highest yields and best manage its reservoir. This means more efficient work with higher yields more quickly attained. Villasmil states, “The biggest benefit of Azure AI infrastructure is faster time to market.

  • Customer Experience
  • Productivity Improvement
  • Scalability
  • Speed to Market

Solution

OriGen built this solution on Azure AI, Azure Kubernetes Service, Azure. Like most businesses these days, energy companies are striving to do more with less. Azure AI provides managed AI services used to automate classification, recommendations, or decision support. Azure Kubernetes Service orchestrates containerized workloads at scale. Azure provides the core cloud infrastructure, security boundary, and managed services underpinning the solution. New York City–based software developer OriGen is revolutionizing the energy industry with proprietary AI models supported by Microsoft Azure AI infrastructure. OriGen’s AI solutions focus on three key areas—energy reservoir simulations, geological modeling, and operational optimization—to deliver extremely high speed and accuracy and empower better decision-making for energy in.

Solution architecture

3 components · 2 layers
  1. Compute
    • Azure AI Provides managed AI services used to automate classification, recommendations, or decision support.
    • Azure Provides the core cloud infrastructure, security boundary, and managed services underpinning the solution.
  2. Orchestration
    • Azure Kubernetes Service Orchestrates containerized workloads at scale.

Architecture clues

  • Containerized workloads are part of the runtime architecture.

Evidence from the source

In the case of reservoir simulation predictions, traditional CPU-based solutions consistently require thousands of simulations—with long processing times for each—to achieve an accurate prediction.
Like most businesses these days, energy companies are striving to do more with less.
New York City–based software developer OriGen is revolutionizing the energy industry with proprietary AI models supported by Microsoft Azure AI infrastructure.
The company started in 2018 to focus the power of AI on solving energy industry challenges, such as accelerating reservoir simulations, using Azure AI infrastructure
With that enhanced accuracy and insight, Ecopetrol now makes more informed decisions about how to glean the highest yields and best manage its reservoir.
Transparency Evidence & methodology 65/100 reference value · 85% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value65/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth15/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence85%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity6/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Microsoft

    OriGen customer story

    First-party
    https://www.microsoft.com/en/customers/story/1665511423001946809-origen-partner-professional-services-azure
    Source type
    Vendor-published customer story
    Published
    Aug 17, 2023
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Aug 17, 2023 · Microsoft · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.