Listing Thumbnail

    KlastroHeron Decision Intelligence: Multi-Agent AI Council

     Info
    Deployed on AWS
    KlastroHeron Decision Intelligence is a multi-agent decision support system that runs on Amazon Bedrock. Instead of a single AI agent answer, it convenes four independent AI agents that analyze the same high-stakes question from radically different perspectives, then reports where they agree, where they disagree, and why. It is a panel, not a chatbot, designed to arm human decisions with cross-checked reasoning and a full audit trail.

    Overview

    Open image

    Most AI assistants return one confident answer from a single perspective, which can hide trade-offs and blind spots on the decisions that matter most. KlastroHeron Decision Intelligence takes a different approach. It runs four structurally independent AI agents, each grounded in a distinct perspective, that review the same request and argue against one another the way a real board of advisors would. The result is not a single opinion but a measured signal: strong agreement across all four is a decision worth acting on, while disagreement points you to exactly where human judgment is needed.

    Built as a Model Context Protocol (MCP) server on Amazon Bedrock, the product uses your choice of foundation models through AWS Identity and Access Management, with no external API keys required. It accepts text, documents, and images as input, supports multilingual analysis, and returns a clear recommendation together with each perspective, the convergence result, the remaining trade-offs, and a complete record of the deliberation for governance and audit purposes. It is well suited to high-stakes review and assessment decisions such as hiring, promotions, and insurance and claims evaluation, as well as strategic and management decisions, policy and compliance questions, and complex design or engineering trade-offs.

    KlastroHeron Decision Intelligence supports human oversight rather than replacing it. It does not make the final decision for you. In regulated, high-risk decision contexts such as employment, promotion, and insurance, where frameworks like the EU AI Act call for human oversight, transparency, and record keeping, the product is designed to support these obligations by keeping a person in control and producing a documented, multi-perspective rationale for every outcome. It arms your decision with independent, cross-checked reasoning so you can act with confidence and defend your choice with a clear record. The product deploys on Amazon ECS, Amazon EKS, and ECS Anywhere, and enforces entitlement through AWS License Manager.

    Highlights

    • Four independent AI agents, not one. KlastroHeron convenes four structurally different perspectives that analyze the same question and argue against one another, so trade-offs and blind spots a single AI would miss are surfaced.
    • Built for high-stakes review decisions. Ideal for hiring, promotions, and insurance and claims assessment, plus strategy and compliance. In high-risk contexts where frameworks like the EU AI Act call for human oversight, transparency, and record keeping, it is designed to support these obligations.
    • A convergence signal with a full audit trail. Strong agreement across all four agents means act with confidence, while disagreement flags where human judgment is needed. Runs as an MCP server on Amazon Bedrock through AWS IAM with no external keys, accepts text, documents, and images, and enforces entitlement through AWS License Manager.

    Details

    Delivery method

    Supported services

    Delivery option
    Container image for Amazon ECS and Amazon EKS

    Latest version

    Operating system
    Linux

    Deployed on AWS
    New

    Introducing multi-product solutions

    You can now purchase comprehensive solutions tailored to use cases and industries.

    Multi-product solutions

    Features and programs

    Financing for AWS Marketplace purchases

    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.
    Financing for AWS Marketplace purchases

    Pricing

    KlastroHeron Decision Intelligence: Multi-Agent AI Council

     Info
    Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
    Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator  to estimate your infrastructure costs.

    12-month contract (3)

     Info
    Dimension
    Description
    Cost/12 months
    Government License
    For government agencies and public sector organizations. Supports high-stakes public decisions that require documented, multi-perspective reasoning and human oversight, such as eligibility, procurement, benefits, and policy reviews. Includes the full four-agent decision council, text, document, and image input, multilingual analysis, the convergence report with a complete audit trail, and support under commercial terms beyond the open-source AGPL edition.
    $24,000.00
    Business License
    For a commercial organization operating at a single company or site. Includes the full four-agent council for operational decisions such as hiring, promotion, insurance, and compliance reviews, all input types, multilingual analysis, the convergence report with audit trail, and priority email support.
    $18,000.00
    Enterprise License
    For large or multi-entity organizations deploying across multiple branches, sites, or subsidiaries. Includes all Business License features, company-wide deployment, support for custom decision councils, and dedicated support.
    $72,000.00

    AI Insights

     Info

    Dimensions summary

    You pick a license based on your organization type and deployment scope, all billed under a contract by units. The Government License fits public sector agencies making high-stakes public decisions with human oversight. The Business License covers a single commercial company or site for operational decisions. The Enterprise License builds on the Business License for large or multi-entity organizations deploying across multiple branches, sites, or subsidiaries, adding custom decision councils and dedicated support. Each tier changes who can use the product and how broadly you deploy, with support level rising from priority email to dedicated support.

    Top-of-mind questions for buyers

    Each license is sold by units under a contract. A unit maps to the licensed deployment scope you select. The Government and Business Licenses cover a single organization or site. The Enterprise License counts units for deployment across multiple branches, sites, or subsidiaries. Confirm exact unit counting for your scope with the vendor.
    The Enterprise License includes all Business License features, then adds company-wide deployment, support for custom decision councils, and dedicated support. The Business License covers one commercial company or site with priority email support. You pick Enterprise when you deploy across multiple branches, sites, or subsidiaries.
    All three licenses include the four-agent decision council, text, document, and image input, multilingual analysis, and a convergence report with an audit trail. The Government License adds commercial support beyond the open-source AGPL edition. This record keeps the four-perspective deliberation as a minutes-style decision record for human review.
    www.klastrovanie.com
    Helpful?

    Vendor refund policy

    All contract purchases are generally considered final. If you are not satisfied with the product, please contact Klastrovanie Co., Ltd. at contact@klastrovanie.com  within 30 days of your purchase and describe the issue. We will review each request individually and, where a refund is warranted, work with you and AWS Marketplace to process it. Refunds for AWS Marketplace transactions are issued through AWS in accordance with AWS Marketplace terms.

    How can we make this page better?

    Tell us how we can improve this page, or report an issue with this product.
    Tell us how we can improve this page, or report an issue with this product.

    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.

    Usage information

     Info

    Delivery details

    Container image for Amazon ECS and Amazon EKS

    Supported services: Learn more 
    • Amazon ECS
    • Amazon EKS
    Container image

    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

    Version 3.0.1 is the recommended release of KlastroHeron Decision Intelligence, Cloud and MCP Edition, on AWS Marketplace. It is a major re-architecture of the 2.x on-premise edition, rebuilt as a Model Context Protocol (MCP) server that runs on Amazon Bedrock.

    Highlights of this release:

    • Four independent AI agents deliberate on each request and return a recommendation, each perspective, a convergence result, remaining trade-offs, and a full audit record.
    • Runs on Amazon Bedrock using your choice of foundation models through AWS Identity and Access Management. No external API keys are required.
    • Accepts text, documents, and images as input, and supports multilingual analysis.
    • Exposed as an MCP server over streamable HTTP, with a health endpoint and file upload endpoints.
    • Entitlement is enforced through AWS License Manager.
    • Deploys on Amazon ECS and Amazon EKS.

    Configuration notes:

    • Set BEDROCK_MODELS to a comma separated list of Amazon Bedrock model IDs, and make sure model access is enabled for those models in your account.
    • Optionally set BEDROCK_JUDGE_MODEL and BEDROCK_REGION.
    • See the product usage instructions for required IAM permissions and deployment steps.

    Additional details

    Usage instructions

    Overview KlastroHeron Decision Intelligence runs as a Model Context Protocol (MCP) server on Amazon Bedrock. It listens on port 8000 and exposes an MCP endpoint at /mcp, a health check at /health, and file upload endpoints under /uploads.

    1. Enable Amazon Bedrock model access In the Amazon Bedrock console, request access to the foundation models you plan to use, in the AWS Region you will run in (default us-east-1).

    2. IAM permissions Grant the task or pod role permission to invoke Amazon Bedrock and to call AWS License Manager. Bedrock actions: bedrock:InvokeModel, bedrock:InvokeModelWithResponseStream, bedrock:Converse, bedrock:ConverseStream. License Manager actions: license-manager:CheckoutLicense, license-manager:CheckInLicense, license-manager:ExtendLicenseConsumption, license-manager:GetLicense, license-manager:ListReceivedLicenses.

    3. Environment variables BEDROCK_MODELS: comma separated Amazon Bedrock model IDs for the four agents, for example us.amazon.nova-lite-v1:0,us.amazon.nova-micro-v1:0. BEDROCK_JUDGE_MODEL: model ID used by the judge. BEDROCK_REGION: AWS Region for Bedrock (default us-east-1). CM_LICENSE_ENABLED: true in production (default true). CM_LICENSE_REGION: AWS Region for License Manager (default us-east-1).

    4. Deploy Run the container on Amazon ECS or Amazon EKS. Map container port 8000. Attach the IAM role from step 2 and set the environment variables from step 3.

    5. Verify Call GET /health. A healthy response returns status ok with the number of configured models and the license state. If the license state is not valid, confirm the contract has been accepted and that the role can reach AWS License Manager.

    6. Use the product Connect an MCP client to /mcp over streamable HTTP. To include files, upload them with POST /uploads and pass the returned session id to the run_council tool. run_council accepts a question and returns a recommendation, each of the four perspectives, the convergence result, remaining trade-offs, and an audit record. Input can be text, documents, or images, and analysis is multilingual.

    Support Contact contact@klastrovanie.com .

    See the product manual for full details.

    Resources

    Support

    Vendor support

    Support is provided by Klastrovanie Co., Ltd. by email at contact@klastrovanie.com .

    Buyers receive email support during standard business hours, Monday through Friday. We aim to acknowledge new requests within one business day and to provide a resolution or a clear next step as quickly as possible.

    Support covers deployment on Amazon ECS, Amazon EKS, and ECS Anywhere, licensing and entitlement through AWS License Manager, configuration of Amazon Bedrock models and IAM permissions, product usage questions, and bug reports. When contacting support, please include your AWS account ID, the product version, your deployment environment, and a description of the issue with any relevant logs so we can assist you efficiently.

    Support is available in English and Korean.

    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.

    Similar products

    Customer reviews

    Ratings and reviews

     Info
    0 ratings
    5 star
    4 star
    3 star
    2 star
    1 star
    0%
    0%
    0%
    0%
    0%
    0 reviews
    No customer reviews yet
    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.