McKinsey’s new LegacyX platform, developed by QuantumBlack, McKinsey’s AI arm, applies these cutting-edge agentic AI capabilities to the problem of software modernization, refreshing enterprise systems at a fraction of the time and cost that would have been required just a few years ago.
Recently, McKinsey partnered with a multinational bank that was manually converting a fragmented landscape of more than 100 legacy risk models from SAS to Python, a modern and versatile programming language that could offer greater flexibility, scalability, and integration capabilities for the bank.
The team deployed LegacyX, which developed and ran five multi-agent squads, each comprising of at least 25 agents, programmed to accelerate code documentation and modernization. The agents reviewed the legacy code, documented the business logic in plain English, validated the revised target state, and then modernized the models into Python with a 90% rate of accuracy. The project timeline was accelerated by 80% while keeping human developers in the loop.
The guiding ambition for LegacyX is to solve the problem of tech modernization by applying agentic AI to specific challenges and training clients to manage the modernization process going forward. In a recent example, business analysts with no technical experience were able to create squads of agents to synthesize interviews and test different hypotheses. “This is really exciting for businesses because agentic AI can be accessible to everyone—not just technical teams—allowing organizations to fully leverage its potential,” says Dante Gabrielli, global product manager for LegacyX.
With LegacyX, legacy applications are no longer a barrier to progress. By harnessing the power of agentic AI, businesses can significantly enhance productivity and stay ahead of the curve in an ever-evolving tech landscape.
Note: This article was created by McKinsey & Company.
How AI is reshaping legacy tech systems
At the heart of virtually every large organization lies a legacy tech system slowing it down. In fact, about 70% of the software that powers Fortune 500 companies was developed at least 20 years ago. Upgrading these legacy systems is essential, but the process can be daunting—a typical mainframe modernization project, depending on the amount of code, can require more than 200 engineers, take multiple years, cost millions of dollars, and even be outdated before it is completed.
Advances in generative AI are making it possible to modernize enterprise technology without all the traditional hurdles.
One of the most promising use cases for gen AI has been in updating software code. With large language models trained in software development, organizations can now easily and affordably tackle modernizations that were once too difficult and costly. The emergence of agentic AI, a powerful new capability, has further revolutionized this process. Agentic AI allows developers to create entire teams of AI agents in different roles (e.g., data engineer, coder, tester) and instruct them to assess, update, and build new technology infrastructures that meet current and future business demands.
Dan Collins, Associate Partner, and Dante Gabrielle, Global Product Manager, LegacyX, at McKinsey & Company
McKinsey & Company’s LegacyX is revolutionizing the modernization of legacy tech systems with AI.
i
i
McKinsey’s new LegacyX platform, developed by QuantumBlack, McKinsey’s AI arm, applies these cutting-edge agentic AI capabilities to the problem of software modernization, refreshing enterprise systems at a fraction of the time and cost that would have been required just a few years ago.
Recently, McKinsey partnered with a multinational bank that was manually converting a fragmented landscape of more than 100 legacy risk models from SAS to Python, a modern and versatile programming language that could offer greater flexibility, scalability, and integration capabilities for the bank.
The team deployed LegacyX, which developed and ran five multi-agent squads, each comprising of at least 25 agents, programmed to accelerate code documentation and modernization. The agents reviewed the legacy code, documented the business logic in plain English, validated the revised target state, and then modernized the models into Python with a 90% rate of accuracy. The project timeline was accelerated by 80% while keeping human developers in the loop.
The guiding ambition for LegacyX is to solve the problem of tech modernization by applying agentic AI to specific challenges and training clients to manage the modernization process going forward. In a recent example, business analysts with no technical experience were able to create squads of agents to synthesize interviews and test different hypotheses. “This is really exciting for businesses because agentic AI can be accessible to everyone—not just technical teams—allowing organizations to fully leverage its potential,” says Dante Gabrielli, global product manager for LegacyX.
With LegacyX, legacy applications are no longer a barrier to progress. By harnessing the power of agentic AI, businesses can significantly enhance productivity and stay ahead of the curve in an ever-evolving tech landscape.
Note: This article was created by McKinsey & Company.
At the heart of virtually every large organization lies a legacy tech system slowing it down. In fact, about 70% of the software that powers Fortune 500 companies was developed at least 20 years ago. Upgrading these legacy systems is essential, but the process can be daunting—a typical mainframe modernization project, depending on the amount of code, can require more than 200 engineers, take multiple years, cost millions of dollars, and even be outdated before it is completed.
Advances in generative AI are making it possible to modernize enterprise technology without all the traditional hurdles.
One of the most promising use cases for gen AI has been in updating software code. “With the unprecedented power of large language models, trained on software development, it has suddenly become feasible and economically viable for organizations to attempt these kinds of modernizations that were previously too difficult and too expensive,” said Dan Collins, associate partner at McKinsey. The emergence of agentic AI, a powerful new capability, has further revolutionized this process. Agentic AI allows developers to create entire teams of AI agents in different roles (e.g., data engineer, coder, tester) and instruct them to assess, update, and build new technology infrastructures that meet current and future business demands.
The team deployed LegacyX, which developed and ran five multi-agent squads, each comprising of at least 25 agents, programmed to accelerate code documentation and modernization. The agents reviewed the legacy code, documented the business logic in plain English, validated the revised target state, and then modernized the models into Python with a 90% rate of accuracy. The project timeline was accelerated by 80% while keeping human developers in the loop.
The guiding ambition for LegacyX is to solve the problem of tech modernization by applying agentic AI to specific challenges and training clients to manage the modernization process going forward. In a recent example, business analysts with no technical experience were able to create squads of agents to synthesize interviews and test different hypotheses. “This is really exciting for businesses because agentic AI can be accessible to everyone—not just technical teams—allowing organizations to fully leverage its potential,” says Dante Gabrielli, global product manager for LegacyX.
With LegacyX, legacy applications are no longer a barrier to progress. By harnessing the power of agentic AI, businesses can significantly enhance productivity and stay ahead of the curve in an ever-evolving tech landscape.
Note: This article was created by McKinsey & Company.
The team deployed LegacyX, which developed and ran five multi-agent squads, each comprising of at least 25 agents, programmed to accelerate code documentation and modernization. The agents reviewed the legacy code, documented the business logic in plain English, validated the revised target state, and then modernized the models into Python with a 90% rate of accuracy. The project timeline was accelerated by 80% while keeping human developers in the loop.
The guiding ambition for LegacyX is to solve the problem of tech modernization by applying agentic AI to specific challenges and training clients to manage the modernization process going forward. In a recent example, business analysts with no technical experience were able to create squads of agents to synthesize interviews and test different hypotheses. “This is really exciting for businesses because agentic AI can be accessible to everyone—not just technical teams—allowing organizations to fully leverage its potential,” says Dante Gabrielli, global product manager for LegacyX.