Product overview

BMC AMI Platform provides a framework for integrating generative AI capabilities into a cloud-native environment for mainframe operations. It is designed to support modernization efforts by enabling AI-assisted workflows and containerized deployment models.

Version 2.0.00 introduces several key enhancements:

• User Management: Authentication using z/OSMF mainframe credentials for secure access.
• Observability: Advanced monitoring and diagnostic tools for improved system visibility.
• Deployment Orchestration: Kubernetes-based orchestration for streamlined deployment and scalability.
• AI Integration: Includes the BMC AMI Assistant chat interface and AI-driven services to assist with operational tasks.

These features aim to provide a more automated and integrated mainframe ecosystem without altering existing core functionality.

Core capabilities

• BMC AMI Assistant (GenAI-powered chat): An AI-powered assistant that enables users to retrieve technical knowledge and assist with routine operational tasks using natural language. It leverages ingested BMC public documentation and BMC SME-contributed tribal knowledge to help users find information faster, often reducing the need to search manuals or open support tickets. By accelerating access to critical answers, teams save time and operate more efficiently.
• LLM management: The BMC AMI Platform includes an LLM Management layer that provides organizations the flexibility to choose from a curated LLM Library or bring their own LLM (BYOLLM) to power GenAI experiences. This provides enterprises with more control over data privacy, model performance, and AI governance.
• Integrated product experiences: The BMC AMI Platform supports integration with key BMC AMI solutions. This version supports the integration of BMC AMI Assistant chat with BMC AMI Ops User Interface, BMC AMI Ops Insights, and BMC AMI DevX zAdviser Enterprise on-premises, delivering a unified experience across tools. BMC AMI Platform also enables advanced AI capabilities across integrated BMC products - such as Code Explain and Code Conversion in BMC AMI DevX Code Insights, Root Cause Explain and recommendations in BMC AMI Ops Insights, helping users better understand code, troubleshoot faster, and streamline daily operations.
• Role-based access and enterprise authentication: Built with enterprise-grade access controls, supporting multiple authentication methods and granular role-based permissions.
• Platform health and observability: Includes monitoring capabilities for core platform services and integrations, helping administrators ensure system uptime and availability. The BMC AMI Platform is purpose-built to help organizations modernize mainframe operations with intelligence, speed, and flexibility. As we continue to evolve, our goal remains clear - To simplify complex environments and empower teams through AI-driven innovation.

BMC AMI Platform components

This section provides a detailed description of BMC AMI Platform components.

BMC AMI AI Services

The BMC AMI AI Services provide a common framework for delivering Generative AI (GenAI) solutions. It offers an integration service framework that streamlines the development process for all AI use cases. The BMC AMI AI Manager enables service health checks, Large Language Model (LLM) configuration, and feature provisioning, while its containerized architecture ensures flexible deployment options. The platform also includes an evaluation framework to validate LLM outputs during development and is designed with the flexibility to incorporate future advances in GenAI technologies. 

Service descriptions

The following table describes the services offered by the BMC AMI AI Services:

Service	Description
Gateway	The Gateway Service is the entry point to the BMC AMI AI Services. As a proxy, it routes incoming requests to the appropriate feature-specific integration services. This service also hosts the BMC AMI AI Manager, which enables the provisioning of features.
Discovery	The Discovery Service monitors the status of all services within BMC AMI AI Services. Each service sends periodic heartbeats, allowing the Discovery Service to track its availability and current operational status (whether it's up or down). When a microservice needs to communicate with another service, it retrieves the corresponding service address from the Discovery Service.
Security	The Security Service acts as a protective layer for the BMC AMI AI Services. It prevents prompt injection attacks and filters out denylisted words. With an allowlist filter in place, only a specified range of unified characters is allowed, safeguarding against embedded or unwanted characters. You can input and output anomaly detectors to the security layer to identify abnormal behaviors. This service also includes a provision for enabling a rate limiter to manage traffic efficiently.
LLM	The LLM Service is the AI engine of BMC AMI Platform. It is responsible for configuring and managing the LLM used within the platform.
Integration	The Integration Service is responsible for handling the core business logic. It performs use-case-specific tasks, including managing large inputs, employing task-specific prompts, and executing data pre- and post-processing. It intercommunicates with the security and LLM services to prepare responses to user queries.
Expert	The Expert Service is responsible for handling the core business logic. It performs use-case-specific tasks, including managing large inputs, employing task-specific prompts, and executing data pre- and post-processing. It intercommunicates with the security and LLM services to prepare responses to user queries.

BMC AMI Platform core services

The Core Services form the foundation of the BMC AMI Platform, delivering essential capabilities that ensure security, connectivity, communication, and visibility across the ecosystem. These include API Gateway and Security Services for robust authentication and user management; the z/OSMF Connector, which enables seamless mainframe-based user authentication; the Notification Service, providing configurable email alerts for key platform activities; and Observability Services, which integrate tools like Kibana, Uptrace, and Jaeger to monitor logs, metrics, and traces for comprehensive platform health insights. Together, these core components enable a secure, integrated, and transparent platform experience.

Service descriptions

The following table describes the services offered by the BMC Core Services:

Service	Description
Observability	The AMI Platform uses OpenTelemetry to collect logs, metrics, and traces across core services. These signals are routed via the OpenTelemetry Collector to specialized backends: Prometheus for metrics (viewed in Uptrace), Elasticsearch for logs (viewed in Kibana), and Jaeger for traces. This architecture provides full visibility and correlation across services, enabling efficient debugging and performance monitoring.
z/OSMF Connector	The platform integrates mainframe user authentication by managing credentials and session states across configured z/OSMF hosts. It ensures that host connections are actively maintained and validated, allowing users to securely log in using their mainframe credentials. Upon successful authentication, the Security Service automatically provisions the user as an MF-type account within the platform. This account can then be assigned appropriate roles and groups, enabling seamless access control and alignment with platform-wide identity management policies.
Security services	This service acts as the centralized authority for user identity and access management. It handles authentication, authorization, JWT token generation and validation, and enforces role-based access control. All user-related operations with the PostgreSQL database are securely routed through this service. API access is strictly restricted to requests originating from the API Gateway.
API Gateway	The API Gateway acts as the centralized entry point for all external API requests to the platform, facilitating secure and efficient communication between clients and internal microservices. It is responsible for key functions such as request routing, authentication, JWT token validation, load balancing, and security filtering. Serving as the unified interface for the Security Service, the gateway exclusively exposes user management APIs through this layer. Access to these APIs is strictly limited to authorized clients, specifically the Platform Core UI and CES, ensuring tight control over all user-related operations.
Notification services	The Notification Service manages all email communications within the platform, enabling seamless interaction between system components and users. It supports automated notifications, alerts, and transactional messaging workflows, ensuring reliable and consistent delivery of critical information.
Database services	The Database Service functions as the platform’s core data layer, integrating multiple storage and indexing technologies to support a wide range of data operations. It leverages PostgreSQL for structured relational data, Milvus for high-performance vector similarity search, and Elasticsearch for full-text search and analytics. Through a unified access layer, this service enables efficient querying, indexing, and storage across structured and unstructured datasets.