Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
# Key Features:
- AgentSearch offers unified semantic search capabilities across structured, semi-structured, and unstructured enterprise data.
- Its graph-enhanced RAG architecture powered by Bedrock ensures accurate, explainable responses by combining language models with graph context.
- The platform enables fast and parallel indexing of large datasets using Kubernetes workers, which significantly reduces processing time.
- Security and auditing are built-in, leveraging AWS IAM for access control, VPC for network isolation, and CloudWatch for monitoring.
- Additionally, AgentSearch includes observability and automatic performance scaling features through Kubernetes and Horizontal Pod Autoscaler (HPA).
Show the rest of the publisher’s description (28 more lines)
# Use Cases:
- AgentSearch supports a wide range of enterprise applications.
- It powers Enterprise Knowledge Discovery, enabling employees to extract relevant information quickly across departments.
- In the Legal and Compliance domain, it facilitates deep search across regulatory and policy documents. It is ideal for Policy and Risk Q&A in highly regulated sectors like BFSI and Healthcare, helping teams make informed decisions. In E-commerce, it enhances catalog intelligence, allowing businesses to gain richer insights from product data.
# Target Users:
- AgentSearch is designed for a range of enterprise users.
- Business Analysts can use it to extract strategic insights quickly.
- Legal and Compliance Teams benefit from its precise document discovery capabilities.
- Data Engineers can leverage the platform for building robust data search pipelines.
- Knowledge Workers in regulated industries such as finance and healthcare can rely on it for fast, explainable, and secure information retrieval.
# Technical Requirements:
- To deploy AgentSearch, organizations need an AWS Account with Amazon EKS, IAM, and VPC properly configured. Enterprise data should be available across
Amazon S3, Neptune, RDS, and OpenSearch. Additionally, access to Amazon Bedrock APIs is necessary to power the generative AI layer.
- Operational knowledge of Kubernetes is also required for managing the microservice-based architecture and deployment.
# Technical Requirements:
- To deploy AgentSearch, organizations need an AWS Account with Amazon EKS, IAM, and VPC properly configured. Enterprise data should be available across Amazon S3, Neptune, RDS, and OpenSearch.
- Additionally, access to Amazon Bedrock APIs is necessary to power the generative AI layer.
- Operational knowledge of Kubernetes is also required for managing the microservice-based architecture and deployment.
# Deployment Architecture:
- The solution is deployed using a microservice architecture on Amazon EKS.
- It includes a GraphRAG API server alongside indexing workers that process and serve data efficiently.
- Secure access to data sources such as S3, RDS, Neptune, and OpenSearch is enforced using AWS IAM.
- All data transfers are encrypted via TLS, and data at rest is secured using SSE-S3 encryption. Observability is handled via Amazon CloudWatch, while APIs are exposed through API Gateway and Ingress controllers for managed access.
# Benefits:
- AgentSearch delivers graph-aware, explainable AI responses across data silos, helping organizations improve search reliability.
- It significantly reduces research time, thereby enhancing the productivity of teams across functions.
- The platform enables traceable and auditable AI-driven search, a critical requirement for compliance in regulated sectors.
- It is also designed with scalability, performance, and security in mind, making it suitable for large-scale enterprise deployments.
Highlights
Highlighted by the publisher on AWS Marketplace.
Modular agentic framework enabling intelligent task automation across workflows.
Seamless integration with leading LLMs for context-aware reasoning and responses.
Enterprise-grade scalability with built-in privacy, observability, and secure deployment.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment · as of 2026-08-29
Sources
Publisher resources
2 linksLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.