AWS Partner Network (APN) Blog
Liveline Technologies: Artificial Intelligence Innovation in Manufacturing with AWS SaaS Factory Support
By Babak Parvizi, Sr. Partner Solutions Architect – AWS SaaS Factory
By Clay Brehm, Sr. Enterprise Solutions Architect – AWS
By Koyel De, Business Architect – AWS SaaS Factory
 |
| Liveline |
 |
Artificial intelligence (AI) is impacting almost every sector and manufacturing is no exception. As per the IDC Worldwide Artificial Intelligence Spending Guide, when it comes to investments in AI, the manufacturing industry is one of the largest industries.
Common use cases for AI in manufacturing include predictive maintenance, virtual tests, and supply chain management. However, AI is not widely applied to real-time process control.
Examples of AI directly controlling factory systems are almost nonexistent, despite the potential for AI-based controllers to improve operating outcomes in complex and dynamic production environments, and to do so for a fraction of the cost to implement traditional control systems.
Liveline Technologies is an AWS Partner and provides factory-scale automation for manufacturers of all sizes. It uses advanced artificial intelligence to quickly generate AI-based controllers that adjust equipment parameters in real-time for an entire production line or cell.
Liveline Technologies’ customers enjoy less scrap, waste, and energy usage; better product quality; less unplanned downtime; and higher productivity. Its solutions help supplement technical talent that is difficult to find.
Liveline Technologies’ approach makes advanced process control (APC) practical for nearly all manufacturers. Legacy APC solutions have been limited to refining, petrochemicals, and other sectors with mega-sized facilities. This is due primarily to cost and the difficulty of implementation, but Liveline Technologies is leveraging AI to make APC affordable for all.
Liveline Technologies has partnered with the AWS SaaS Factory team to launch its product as a software-as-a-service (SaaS) solution built on Amazon Web Services (AWS). In this post, we’ll take a close look at the major challenges they encountered, examine how AWS SaaS Factory provided support in overcoming those challenges, and discuss how other organizations can leverage the SaaS delivery model to drive AI innovation.
Q&A with Liveline Technologies
The AWS team had a Q&A discussion with Joseph Hernandez, David Wade, and Christopher Couch from Liveline Technologies.
AWS SaaS Factory: Can you tell us about yourself and role at Liveline Technologies?
Joseph Hernandez: I am the Co-Founder and Vice President of Engineering at Liveline Technologies. I have a deep background in advanced technology development for manufacturing.
David Wade: I am the Principal Solutions Architect at Liveline Technologies. I am 7x AWS Certified and the lead expert responsible for integration of IT systems with operational technology (OT) systems in manufacturing.
Christopher Couch: I am the Co-Founder and CEO of Liveline Technologies and SVP of Engineering/CTO of Cooper Standard, a global Tier 1 automotive supplier and the parent company of Liveline Technologies.
AWS SaaS Factory: Can you describe which products and solutions Liveline Technologies has built on AWS?
Joseph Hernandez / David Wade: Liveline Technologies created a digital platform that collects, stores, publishes, and consumes data from the plant environment while maintaining a state in AWS. The Liveline Digital Controls Platform (LDCP) consists of microservices for digitizing manufacturing equipment, enabling advanced AI-based controls and process visualization.
Our SaaS solution relies on AWS services such as Amazon Relational Database Service (Amazon RDS), Amazon Elastic Compute Cloud (Amazon EC2), Amazon Elastic Container Service (Amazon ECS), Amazon Simple Storage Service (Amazon S3), AWS Lambda, Amazon API Gateway, and Amazon Cognito.
With AWS, the LDCP gains data redundancy both at the manufacturing plant and through AWS that enables cloud-first visualization and process control. Customers realize operational improvements like scrap savings, material waste reductions, and reduced dependency on tribal process knowledge.
AWS SaaS Factory: Who are your customers and what are some key customer benefits?
Christopher Couch: We are targeting process manufacturing companies that are in various stages of their digitization journey. Process manufacturing refers to continuous flow operations such as extrusion, calendarization, chemical processing, food processing, and the like. Our solution implements a new AI-based approach to APC through modern SaaS and democratizes access to advanced AI. This provides cost-effective automation where traditional APC has been too complex or expensive.
AWS SaaS Factory: What were the primary business motivations to deliver the SaaS and democratize this AI solution?
Christopher Couch: In my other life as CTO of a mid-sized manufacturer, I was unable to purchase automation solutions that made sense for our types of processes or our relatively small scale. Design criteria for the solution included low cost, speed to implement, and scalability within and across factory sites.
Our intellectual property promotes data efficiency in AI, minimizing the amount of data and time it takes to train controllers, as well as the compute required for real-time inference. Once we developed a viable solution, we thought it would be relevant to manufacturing companies across multiple industries. That’s when we established Liveline Technologies.
AWS SaaS Factory: Can you walk us through how AWS SaaS Factory supported the adoption of your SaaS model?
David Wade: The AWS SaaS Factory team reviewed our architecture, providing resources and best practices guidance from the AWS Well-Architected SaaS Lens framework. They helped us transition to a SaaS model and shifted our mentality from a siloed, single customer approach to a multi-tenant SaaS application in a well-architected environment. SaaS Factory provided reference solutions for our complex integrations while keeping our security posture intact.
AWS SaaS Factory: What were some of the technical challenges you ran into when democratizing this AI solution through a SaaS delivery model?
Joseph Hernandez: Manufacturers require robust, onsite systems to maintain constant production even with a network outage. Our biggest challenge was developing a technology stack that provides reliable, on-premises performance while utilizing modern, cloud-based resources. We architected a robust, manufacturing-first solution that fits within the modern microservices-first paradigm.
Our platform utilizes on-premises deployment of AI models for edge inference and doesn’t fit within a traditional cloud-based machine learning (ML) deployment method. Liveline Technologies crafted an MLOps pipeline utilizing multiple AWS services to train, test, and publish securely to on-premises devices.
AWS SaaS Factory: Can you share how AWS SaaS Factory helped you address these technical challenges?
David Wade: AWS SaaS Factory guided our team through a series of advanced topics, including:
- Identity management and SaaS identities.
- Multi-tenant data isolation patterns: dynamic policy generation, attribute-based access control (ABAC).
- Deployment models: pooled, bridge, and silo.
- Frictionless onboarding patterns using tier-based deployments with AWS CloudFormation.
- Publishing tenant-aware logs and metrics to analyze tenant usage and consumption trends.
- Cost optimization techniques aligning tenant usage with consumption metrics and correlating consumption with cost.
AWS SaaS Factory: Can you share how SaaS architecture and key AWS services were used?
David Wade: Our architecture uses AWS services to power our systems. The CI/CD process relies on AWS CodePipeline and build/deployment mechanisms with images created and stored in Amazon Elastic Container Registry (Amazon ECR). Compute is comprised of Amazon EC2 and Amazon ECS, while MLOps require a combination of graphics processing unit (GPU) and CPU using AWS Fargate and Amazon ECS with Amazon EC2.
The customer portal utilizes a single-page application hosted on Amazon CloudFront for global availability. We apply authorization and authentication processes using Amazon Cognito.
AWS SaaS Factory: Tell us why you chose this unique architectural approach.
Joseph Hernandez: Liveline Technologies had to solve two specific architecture challenges: securing and isolating customer data, while limiting production downtime caused by wide-area network (WAN) outages. A bridge SaaS model offers a global customer portal and maintains dedicated resources for storage and compute. With this approach, customer data is siloed and secure. Additionally, our architecture can sustain multiple days of WAN downtime while running stored models. Data is available onsite for local visualization, production charts, and e-Andon boards.
AWS SaaS Factory: Can you walk us through how AWS SaaS Factory supported your business efforts?
Christopher Couch: The AWS SaaS Factory team helped us to align our target ideal customer profile (ICP) and brought diverse perspectives about our go-to-market (GTM) strategy. In business workshops, they shared information on current trends, technology, and business approaches, and we consider our solution architecture to develop a value-based pricing and packaging strategy.
AWS SaaS Factory: What advice would you share with other organizations as they bring AI innovation through SaaS?
Joseph Hernandez: AI/ML are generic terms used to describe a vast array of data science techniques. A “solve everything approach” detracts from the company’s niche value-add. Focus on creating technology that will deliver AI solutions to meet your customer’s objectives. For Liveline Technologies, the underlying AI/ML solution is a robust automation platform for bridging the gap between advanced controls and manufacturing processes.
About AWS SaaS Factory
AWS SaaS Factory helps organizations at any stage of the SaaS journey. Whether looking to build new products, migrate existing applications, or optimize SaaS solutions on AWS, we can help. Visit the AWS SaaS Factory Insights Hub to discover more technical and business content and best practices.
SaaS builders are encouraged to reach out to their account representative to inquire about engagement models and to work with the AWS SaaS Factory team.
Explore today resources for any stage of your SaaS journey from design and build, to launch and optimization.
Liveline Technologies – AWS Partner Spotlight
Liveline Technologies is an AWS Partner whose product suite enables rapid and cost-effective automation at the factory system level. This means controlling an entire production line or cell consisting of multiple processing stages. Its proprietary AI is not an add-on to help manage legacy Advanced Process Control (APC), but rather a unique approach that’s purely AI-based from the ground up.