Bringing Coordinated AI to the Mainframe

Why It Matters

Coordinated AI enables mainframe operators to automate complex tasks safely, preserving uptime while accelerating digital transformation and protecting against costly vendor lock‑in.

Key Takeaways

• Coordinated AI shifts from isolated to team-wide mainframe workflows.
• BMC AMI introduces agentic orchestration for governance and auditability.
• Standardized protocols (MCP, MCPS) enable cross‑vendor mainframe integration.
• AI agents automate capacity planning, reducing cost and SLA risks.
• Federated orchestration balances centralized control with distributed team responsibilities.

Summary

The discussion centers on BMC’s Automated Mainframe Intelligence (AMI) portfolio, which is evolving from siloed generative AI tools toward a coordinated, agent‑driven intelligence layer that spans development, operations, and governance across mainframe environments. By embedding AI assistants and autonomous agents directly into the mainframe stack, BMC aims to turn isolated code‑explanation features into collaborative workflows that multiple developers, testers, and offshore teams can share, audit, and repeat. Key insights include the need for a central orchestration plane that enforces policies, role‑based access, and audit trails while allowing agents to act across subsystems such as databases, security modules, and capacity planners. The panel highlighted how AI‑augmented capacity planning can balance performance improvements against cost trade‑offs, and how emerging interaction standards like MCP and MCPS will replace ad‑hoc APIs to ensure reliable, vendor‑agnostic communication. Notable examples cited were the AMI assistant’s code‑explanation capability, the agentic pipeline that can commit code from a generative model directly into a mainframe, and the distinction between simple data‑sharing APIs and MCP servers that execute actions on behalf of users. Priya emphasized risk avoidance in mission‑critical mainframes, while Matt stressed a federated orchestration model that mirrors existing team responsibilities. The broader implication is that enterprises can modernize legacy mainframes in place—leveraging AI to boost efficiency, reduce manual errors, and maintain compliance—without falling into vendor lock‑in. Standardized protocols and a governance‑first approach are essential for scaling these capabilities across heterogeneous environments.

Original Description

Part two of an ongoing mainframe and AI conversation on TechStrong TV. Priya Doty, VP Solutions Marketing for BMC AMI Solutions, and Matt Whitbourne, VP Product Management and Design for the BMC AMI portfolio, return with Alan Shimel to go deep on what it actually takes to move from isolated generative AI use cases to coordinated, agentic intelligence inside real mainframe shops. They explain why every install is unique, why introducing change always introduces risk on revenue-producing systems, and how BMC is aligning with emerging interaction protocols like MCP and Agent2Agent (A2A) — the new APIs of the agentic era. Priya and Matt walk through where coordinated intelligence lives, why orchestration plus governance is the new central plane, and how a federated model lets operations, security, data, and platform teams keep their authority while agents stitch their workflows together. They also share real-world scenarios — from BMC AMI Assistant code explanation to agentic capacity planning — that show how mainframe customers can modernize in place without ripping out the systems running mission-critical transactions.

In this conversation, Priya and Alan cover:

• Part 2 of the BMC AMI conversation — from isolated to coordinated intelligence

• Why agents need orchestration plus governance — and why it must be federated

• MCP and A2A as the new APIs of the agentic era

• Why modernize-in-place beats rip-and-replace on revenue-producing systems

• Real-world scenarios from BMC AMI Assistant and agentic capacity planning

• How auditable, repeatable agent workflows keep enterprise compliance intact

Chapters:

00:00 Welcome back — Part 2 with BMC AMI

01:00 Meet Priya Doty and Matt Whitbourne

01:25 What AMI stands for — Automated Mainframe Intelligence

01:45 From isolated GenAI to coordinated agentic intelligence

02:44 Real-world example — BMC AMI Assistant code explanation

04:12 Where coordinated intelligence lives in the product portfolio

06:17 Coordinating across coders, DevOps, SREs, security, and data teams

07:14 Orchestration plus governance — the new central plane

08:00 A federated model for agentic responsibilities

09:05 Why standardized communication matters now

10:29 Risk, modernize-in-place, and unique customer stacks

11:30 MCP and A2A as the new APIs of the agentic era

Guest: Priya Doty and Matt Whitbourne, VP Solutions Marketing (Priya) and VP Product Management & Design (Matt), BMC AMI — https://www.bmc.com/it-solutions/bmc-ami.html

Host: Alan Shimel, TechStrong Group

Subscribe to TechStrong TV for more interviews with the leaders shaping enterprise tech.

#BMCAMI #MainframeAI #AgenticAI #MCP #TechStrongTV