Neurosymbolic AI verification platform that transforms policies into enforceable logic to validate LLM outputs with full auditability and compliance traceability.
Jaxon DSAIL transforms natural language policies into structured, enforceable logic for validating LLM outputs.
Instead of trusting model output, DSAIL validates it against structured rules derived from your internal doctrine and regulatory requirements.
Supports multi-step validation workflows, enabling complex chains of rule evaluation that catch violations, ensure compliance, and produce fully-auditable reasoning traces for every output.
Built for Regulated Industries
Designed for mission-critical deployments in defense, financial services, healthcare, and other regulated industries.
Addresses the core risks of enterprise AI adoption: hallucinations, policy drift, and opaque decision-making.
Every evaluation is traceable and explainable, providing the transparency required for regulatory compliance and audit readiness.
Predictable Usage-Based Pricing
Usage is measured in Jaxon Verified Units (JVUs).
One JVU represents one rule applied to one text unit of up to 1,000 characters.
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.
You pay based on usage, measured in Jaxon Verified Units (JVUs). One JVU covers a single rule that checks up to 5 claims against up to 1,000 characters of text. Your cost scales with how much you verify. Longer text or more claims per check consume more JVUs. There are no tiers or fixed seats. You are billed only for the verification work you run, so your total tracks directly with the volume of rules and text you process.
Top-of-mind questions for buyers
How is one Jaxon Verified Unit counted when my text or claims exceed the limits?
One JVU covers a single rule checking up to 5 claims against up to 1,000 characters. Longer text or more claims consume additional JVUs. A rule checking 2,000 characters counts as more than one JVU. Your total scales with the size and number of checks you run.
How does DSAIL scale as my verification volume grows?
DSAIL uses a parallel processing model where each document is validated independently. As demand rises, capacity scales by adding compute, with no reconfiguration. Because billing is per JVU, your cost tracks directly with the number of rules and characters you process, growing only as your usage grows.
Am I charged when a document fails verification or returns an unknown result?
Billing meters the verification work performed, measured in JVUs, not the verdict. Every rule produces a discrete outcome: pass, fail, or insufficient information. Each evaluated rule against up to 1,000 characters consumes JVUs regardless of whether the result is pass, fail, or unknown.
jaxon.ai
Helpful?
Vendor refund policy
Jaxon AI offers a 48-hour refund on software usage charges for the DSAIL Platform. To request a refund, email support@jaxon.ai with your AWS Account ID and the affected usage period. After 48 hours, refunds are evaluated case-by-case for platform defects or metering errors that resulted in incorrect JVU charges. AWS infrastructure costs (EC2, EBS, KMS, data transfer) are billed by AWS and not covered. For metering errors, AWS may also issue refunds directly per AWS Marketplace policy.
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.
This CloudFormation template deploys the Jaxon DSAIL Platform as a self-contained single-instance architecture on an EC2 instance. All platform services - including the Platform API, Temporal workflow engine, PostgreSQL database,
object storage, Authentik identity provider, HashiCorp Vault secrets manager, LLM proxy, and NGINX edge proxy - run as Docker containers on a single machine using a pre-baked AMI.
IAM role with policies for SSM Session Manager access, Vault KMS operations, and AWS Marketplace metering
Security group allowing HTTPS (443) and HTTP (80, redirects to HTTPS) ingress from all sources
Configuration Options:
Instance type: choose from r8i, r6i, m6i, or m7i families based on workload and region availability
OpenAI API key: required for LLM-powered rule extraction and verification workflows
External URL: set a custom domain or leave empty to auto-detect from the instance public IP
SSL/TLS: provide your own Base64-encoded certificate and private key, or let the platform generate a self-signed certificate on first boot
SSH access: disabled by default; when enabled, requires a key pair name and source CIDR block. SSM Session Manager is always available as an alternative
EBS encryption: enabled by default using the aws/ebs key; optionally specify a custom KMS key ID
First Boot Process:
On launch, the instance runs an automated first-boot script that generates unique passwords, initializes HashiCorp Vault with KMS auto-unseal, configures mTLS certificates for all internal services, and starts the full platform stack. Login credentials are written to /opt/jaxon/dsail/.credentials on the instance. The first-boot process takes approximately 5-10 minutes to complete. Platform availability can be verified by accessing the HTTPS URL shown in
the stack outputs.
Management:
The platform includes management scripts at /opt/jaxon/dsail/ for starting (jaxon-start.sh), stopping (jaxon-stop.sh), and checking status (jaxon-status.sh) of all services. Connect to the instance via SSM Session Manager from the AWS Console or using the AWS CLI command provided in the stack outputs.
CloudFormation Template (CFT)
AWS CloudFormation templates are JSON or YAML-formatted text files that simplify provisioning and management on AWS. The templates describe the service or application architecture you want to deploy, and AWS CloudFormation uses those templates to provision and configure the required services (such as Amazon EC2 instances or Amazon RDS DB instances). The deployed application and associated resources are called a "stack."
Version release notes
Initial release of the Jaxon DSAIL Platform for AWS Marketplace.
Deterministic verification of LLM outputs against structured rules derived from policy documents
Policy-to-rules pipeline: automated extraction of compliance rules from regulatory and internal policy documents using LLM-assisted analysis
mTLS encryption for all internal service communication
Pre-configured for OpenAI LLM integration
SSM Session Manager access (no SSH required)
Usage-based metering via AWS Marketplace (Jaxon Verification Units)
Email: support@jaxon.ai
Phone: (877) 209-7055
Support Availability Commitment. Jaxon will provide email- and phone-based support (support@jaxon.ai, 877-209-7055) during normal business hours, which currently are Monday through Friday (excluding holidays) from 9:00 a.m. through 5:00 p.m. Eastern time. Jaxon will respond to any emails sent to support@jaxon.ai or voicemails left at (877) 209-7055 within 1 business day. Jaxon reserves the right to change its normal business hours and will notify users of any such changes.
AWS infrastructure support
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.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.