Use Case Intelligence RSS Search use cases Search
AWS Software / SaaS United Kingdom

Unitary

Security and Compliance

Founded in 2019, Unitary specializes in multimodal ML models for identifying harmful text, images, and videos amid seas of digital content.

Read the original story Explore all use cases
"Even running at peak traffic, using over 1,000 nodes to process more than 20 million videos daily, our entire team spent 5 days abroad without needing to manage or interact with...
Also, Unitary has reduced container boot times on its ML inference workloads by up to 80 percent.
Key Outcomes reduction in overall costs over 18 months 50%–70% reduction in container boot times for fast response 80% million users served effortlessly across digital platforms...
On AWS, Unitary helps platforms with over 100 million combined users combat toxic content while minimizing the impact on human moderators.

Reported impact

Business outcome

On AWS, Unitary helps platforms with over 100 million combined users combat toxic content while minimizing the impact on human moderators. As the company continues to grow, Amazon EKS and Karpenter will continue to be a key part of its infrastructure.

  • Cost Reduction
  • Risk Reduction
  • Scalability

Solution

Software startup Unitary exists to make the internet safer, helping improve lives and create a fairer world. Built on Amazon Web Services (AWS), the company uses artificial intelligence (AI), specifically machine learning (ML), to help its customers with online content moderation. Given the daily surge of content, processing millions of images and videos, Unitary needed a scalable solution to manage growing demand. On AWS, Unitary helps platforms with over 100 million combined users combat toxic content while minimizing the impact on human moderators. To meet this scale, Unitary chose to run its ML inference workloads on Amazon Elastic Kubernetes Service (Amazon EKS), a managed service for running Kubernetes on AWS.

Data flow

Unitary uses an API to ingest up to 26 million videos daily, which represent several billion frames of content and tens of millions of hours of audio. When Unitary receives a video to be analyzed, multiple microservices that run on Amazon EKS split the video into frames, extract the audio, and then classify the video's content using ML. Afterward, the extracted parts of the videos are stored.

Solution architecture

3 components · 2 layers
  1. Compute
    • Amazon EKS Runs containerized services that deliver the security analysis and compliance workflows.
    • Amazon EC2 Provides scalable compute capacity for the security analysis and compliance workflows.
  2. Serving
    • Amazon SNS Distributes notifications generated by the security analysis and compliance workflows.

Architecture clues

  • For example, Karpenter gracefully handles the necessary Kubernetes node disruptions for security updates and pod scheduling without interrupting system throughput and stability.
  • In fact, Unitary estimates that using Spot Instances for GPU inference infrastructure has reduced costs by 50–70 percent over 18 months.
  • Thanks to the speed at which Karpenter can provision new Kubernetes nodes, Unitary now has the responsiveness required to achieve these results.
  • Then, Unitary runs a series of AI and ML models—some of which can be trained using a customer's safety policies—to detect toxic or unsafe content in the combined multimodal context of visuals, audio,...
  • Unitary uses an API to ingest up to 26 million videos daily, which represent several billion frames of content and tens of millions of hours of audio.

Evidence from the source

"We provide a blended solution that catches harmful content in less time, with more accuracy, and at a lower cost." The first version of Unitary's product was originally built on Amazon Elastic Compute Cloud (Amazon EC2), which offers...
Built on Amazon Web Services (AWS), the company uses artificial intelligence (AI), specifically machine learning (ML), to help its customers with online content moderation.
Given the daily surge of content, processing millions of images and videos, Unitary needed a scalable solution to manage growing demand.
On AWS, Unitary helps platforms with over 100 million combined users combat toxic content while minimizing the impact on human moderators.
Software startup Unitary exists to make the internet safer, helping improve lives and create a fairer world.
To meet this scale, Unitary chose to run its ML inference workloads on Amazon Elastic Kubernetes Service (Amazon EKS), a managed service for running Kubernetes on AWS.
Transparency Evidence & methodology 91/100 reference value · 87% 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 value91/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity16/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    6 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence87%
  • 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
    6 direct source quotes retained.
  • Date provenance8/10
    The publication date comes from publisher-controlled metadata.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    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. AWS

    Unitary customer story

    First-party
    https://aws.amazon.com/solutions/case-studies/unitary-eks-case-study/
    Source type
    Vendor-published customer story
    Published
    Jan 1, 2024
    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

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
AWS Archived · Jun 16, 2026 WithSecure Software / SaaS Europe WithSecure's solutions make cybersecurity accessible for mid-market companies that might not have specialized knowledge or security operation centers. The Security Awareness Assistant analyzes complex data tables to provide a 7-day overview of the organization's… Security and Compliance Amazon Bedrock · Amazon Neptune AWS Jul 25, 2024 Elastic Software / SaaS Global Elastic aims to help customers find information faster while running their applications smoothly and protecting against cyberthreats. Operating from the premise that search functionality is fundamental to critical… Enterprise Knowledge SearchSecurity and Compliance Amazon Bedrock AWS Apr 22, 2024 VIVOTEK Software / SaaS global VIVOTEK needed to launch a secure, scalable cloud surveillance platform quickly without spending time building custom camera-to-cloud infrastructure or diverting engineering effort away from new AI-powered features. 12 months Security and Compliance AWS IoT Core · Amazon DynamoDB · Amazon EC2