Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
GenM - Enterprise AI Analytics and Orchestration Platform
GenM transforms how organizations interact with their data by replacing complex SQL queries and manual reporting with conversational AI. Business users, analysts, and decision-makers can ask questions in plain English and receive accurate, sourced answers drawn from databases, data warehouses, documents, and files, with all data remaining securely within your own AWS environment.
Show the rest of the publisher’s description (15 more lines)
Multi-Agent Orchestration
GenM runs 10+ specialized AI agents in parallel: a RAG agent for document Q&A, a Data Lake agent for structured file analysis (Excel, CSV), a Timbr-powered SQL agent for enterprise data warehouses, a Web Search agent, a Doc/PDF agent, and an LLM Judge agent for automated quality evaluation. A Master agent and intelligent Router agent coordinate these in real time, merging results into unified, coherent responses. Administrators can also create custom user-defined agents with dedicated knowledge bases and tool bindings.
Enterprise-Ready AWS Integration
GenM is built natively for AWS. It deploys via Terraform to Amazon ECS or EKS (Helm charts included), uses Amazon RDS Aurora (PostgreSQL + pgvector) for structured data and vector search, AWS S3 for document storage, AWS SQS for async worker queues, and AWS Bedrock for multi-model LLM access (Anthropic Claude, Meta Llama, Mistral, and more). ALB with OIDC authentication actions is supported out of the box.
Broad Data Source Connectivity
Connect to 20+ enterprise data sources including Snowflake, BigQuery, AWS Athena, Redshift, Databricks SQL, PostgreSQL, MySQL, SQL Server, Oracle, and MongoDB via the Timbr semantic layer for governed, business-friendly SQL generation. Native file support covers multi-sheet Excel workbooks, PDFs, and CSV files.
Flexible LLM Provider Support
GenM works with OpenAI (GPT-4, o-series), Azure OpenAI, AWS Bedrock, Anthropic Claude, and any OpenAI-compatible endpoint (Ollama, vLLM, LM Studio). Models are configurable via the admin dashboard with no redeployment required to add or switch providers.
Enterprise Security and Identity
Supports JWT/OIDC with Microsoft Entra ID, Okta, Auth0, and Keycloak. Role-based access control (Admin, Editor, Viewer), space-scoped data isolation for multi-tenancy, domain-level access policies, API key management, and full audit logging for compliance requirements.
Observability and Quality Assurance
GenM includes full OpenTelemetry support with integration to standard OTel-compatible backends including Prometheus, Grafana, CloudWatch, and Jaeger for distributed tracing. A built-in LLM Judge system evaluates response quality automatically, and a user feedback loop enables continuous improvement over time.
Extensible Without Redeployment
Model Context Protocol (MCP) support allows GenM to act as an MCP server for tools like Cursor and Claude Desktop. REST API tool bindings, Git-synced instruction management, and custom agent creation mean new capabilities can be added without touching the codebase.
Ideal For: Enterprises with complex, multi-source data environments; financial institutions requiring audit logging and strict data governance; organizations standardizing on AWS (Bedrock, RDS, SQS, S3); and teams looking to move from manual BI reporting to AI-powered self-service analytics.
Highlights
Highlighted by the publisher on AWS Marketplace.
Multi-LLM orchestration with dynamic model routing to optimize cost, performance, and security
Unified access to structured and unstructured enterprise data through RAG and Text-to-SQL
Enterprise-grade governance including RBAC, audit logs, budget control, and secure data ownership
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.
Plans and pricing as listed
6 listed- Units
- Units
- Units
- Units
- Units
- Units
Refund terms
As stated by the publisher on AWS Marketplace.
All fees are non-refundable unless otherwise specified in a separate written agreement. For purchases made via AWS Marketplace Private Offers, any refund terms will be governed by the applicable private offer agreement between the buyer and seller.
Sources
Linked 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.