Artificial Genius Orthix version 2 is a Non-Hallucinatory Agentic Unstructured Data Workflow Platform. It is designed to be easy to use for every department, to design their own workflows, that accurately deliver the right information to the right people at the right time, when it can make a commercial difference, producing ROI.
The Artificial Genius Orthix Unstructured Data Workflow Platform applies breakthrough proprietary non hallucinatory language model technology to provide enterprises with ROI on the unstructured data. Enterprises have a lot of valuable unstructured data which, if the accurate and relevant information hidden in it could be delivered to the right person at the right time, would create significant opportunities for sales, revenue, and other measurable commercial returns.
Version 2 of the platform adds sophisticated capabilities to transform the data during the execution of the workflow, without the need for a separate scripting language. Instead, by adding eager semantics to special Markdown links, the Orthix Markdown itself serves as a fully declarative functional language, with transparent if-then-else, recursion, and looping logic.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
This product uses a single usage-based dimension: Per User Per Hour. You are billed for each hour a user actively runs a workflow on the platform. Idle time — a container or session that is up but not running a workflow — does not accrue charges. Your bill scales with how many users run workflows and how long those workflows run. There are no tiers, instance sizes, or add-ons to choose from. The platform captures value from unstructured enterprise data, and cost tracks active workflow usage.
Top-of-mind questions for buyers
What am I billed for under the Per User Per Hour dimension?
You are billed per user for each hour that user actively runs a workflow. Two users running workflows for one hour bill the same as one user running workflows for two hours. The count reflects active workflow time, not how many containers or sessions you keep open.
Am I charged when a container is idle and not running a workflow?
No. You are charged only while a container is actively running a workflow. Idle containers — up but not processing a workflow — accrue no usage charges. Billing meters active workflow time, so charges stop when workflows stop and resume when they run again.
What work does the platform charge user-hours on?
The platform runs workflows that capture value from unstructured enterprise data. Charges apply only during active workflow runs, under the single Per User Per Hour dimension. Time when no workflow runs does not add to your bill.
www.artificialgenius.ai
Helpful?
Vendor refund policy
Customers can request a refund of up to 5 business days of usage if the product does not meet their business requirements.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Adds ability to call non-hallucinatory SageMaker models, in addition to Bedrock models, including the Orthix-50000 multimodal model, which can be used for cybersecurity and other coding tasks.
Additional details
Usage instructions
Running a Workflow
Once provisioned in ECS, users can run any number of workflows by invoking the standard container endpoint for Bedrock AgentCore agents, /invocations on port 8080. The POST input for this endpoint is a JSON object with a 'prompt' field that contains the PRD in Markdown format. The POST output is also a JSON object with a 'response' field that contains a log of successes and failures of the workflow items, also in Markdown format.
Configure the Network
In the VPC console, create a VPC consistent with where your resources are located, and create a Security Group that is attached to the VPC above, and configure its Inbound and Outbound Rules to enable network access for the following resources and ports:
AWS Marketplace Product Registration: TCP port 443
Bedrock Runtime Agent: TCP port 8080
S3: TCP ports 80, 443
HTTP: TCP ports 80, 443
All ICMP - IPv4
In the VPC console, create corresponding Endpoints, with Private DNS Names, using the above Security Group:
com.amazonaws.region.s3 (Gateway, if access to S3 desired).
Configure Permissions
In the IAM console, create an IAM Role for the Orthix container, for example, 'OrthixRole'.
The Permission Policies attached to OrthixRole should include:
AmazonEC2ContainerServiceforEC2Role
AWSMarketplaceMeteringRegisterUsage
AWSMarketplaceMeteringFullAccess
AmazonECSTaskExecutionRolePolicy
AmazonBedrockReadOnly
BedrockAgentCoreFullAccess (see manual).
The Trust Relationships of the role should follow the template: https://agipub.s3.us-east-1.amazonaws.com/artificial-genius-orthix-trust-relationships.json. Modify the template so that the Statement Id 'AllowRoleToAssumeItself' allows OrthixRole to assume itself. This is necessary because various derived versions of the role may be automatically generated that need to be normalized back to the original role.
Create the ECS Cluster
In ECS console, create a new cluster, give it a name, say 'orthix-cluster'.
Select Network Settings to point to your above VPC and Security Group.
Create the ECS Service
In ECS console, create a Task according to the template Task Definition https://agipub.s3.us-east-1.amazonaws.com/artificial-genius-orthix-ecs-task.json. Replace the wildcards '*' in this template with your specifics, including the container URI provided to you when you subscribed to the Orthix product, and the OrthixRole above. Select the requiresCompatibilities field to conform to the Infrastructure Capacity type of your cluster. Then, register it as a Task Definition under a name, say 'orthix-task'. Then Deploy the Task Definition as a Service.
Select Cluster as orthix-cluster.
Select the Networking to be consistent with the VPC and Security Group above.
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Agentic platform that uses non-hallucinatory language processing to turn unstructured data into accurate, timely workflows any department can build without coding.