An artificial intelligence (AI) agent developed by Microsoft has been credited with helping it half the projected time it thinks it will need to develop a commercially viable quantum computer.
During the company’s annual Build 2026 software developer conference, Microsoft showcased how its Discovery agentic AI tool has enabled it to improve the quality of qubits in its next quantum chip, Majorana 2.
Using Discovery, which has been designed to speed the scientific process and accelerate collaboration, Microsoft’s quantum team said the new chip’s qubits can maintain their quantum state 1,000 times longer than its first-generation hardware, enabling more reliable computation. Majorana 2 offers a mean qubit lifetime of 20 seconds, with some instances lasting as long as one minute.
The research team has focused on developing topological qubits, which it said offer inherently low error rates, small size and digital control. The Microsoft researchers said they have improved Majorana 1’s material stack to create a more stable topological phase.
Majorana 2 replaces Majorana 1’s superconductor, aluminium, with lead, and also updates the semiconductor active region to a combination of indium arsenide and indium arsenide antimonide. According to Microsoft, this change in materials results in significant increases in performance.
The researchers said the topological gap, which protects the topological qubits from environmental noise and errors, is more than double that of the previous quantum processor.
According to Microsoft, the improvement in reliability, speed and small qubit size have put the team on a path to achieve a scalable quantum computer that is commercially viable by 2029.
With a little help from AI
The quantum team is spread across multiple countries, with specialists in areas like physics, mechanical engineering and process engineering. To support the interdisciplinary research, Microsoft’s quantum team created an AI agent for organising and analysing information, and making it easier for others to find.
“The AI is able to synthesise knowledge from all these different disciplines,” said Zulfi Alam, corporate vice-president for quantum at Microsoft, providing researchers with access to information and recommendations.
The quantum team’s scientists and engineers have been using the agentic AI capabilities in Microsoft Discovery to manage workflows, automate measurements, optimise fabrication, pinpoint previously unnoticed flaws and propose fixes.
AI is also being used to help researchers understand the vast amount of data that has been collated in quantum research. “As you run AI agents on this data, they’re able to essentially resynthesise and make correlations that we as humans cannot see because no single individual has that much vision across that much data,” said Alam.
AI’s pattern-recognition abilities are also being used to help measure the state of qubits, which, in Microsoft’s quantum chip, means detecting whether there is an even or odd number of billions of electrons on a semiconductor wire. AI agents run the process automatically and continuously, building a 3D map of the conditions that a single scientist would never be able to do in the same way, said Alam.
“Using agentic AI to automate the measurements was a game changer,” he said. “It goes through some math and starts saying, ‘Hey, where do I find the lowest point where everything sort of works?’ And it can do all these voltage adjustments in parallel, which a human cannot do. The way our minds work, we are more linear.”
The improvements being made with the help of agentic AI mean Microsoft sees a way to accelerate quantum development.
“We need to make improvements each year that will get us closer to delivering a computer that we believe will have massive commercial and societal value,” said Chetan Nayak, Microsoft technical fellow.
“We’ve got to keep marching to that roadmap to accomplish that, but where are we relative to last year? We’re 1,000 times better.”
Commenting on the use of agentic AI in quantum research, he added: “Agentic AI has permeated almost everything we do – it’s just become kind of a very natural part of our workflow.
“The agents can really accelerate things as much or as little as you want,” said Nayak. “It can be as little as pulling information together and summarising it, or it can go further down the road of synthesising it more or generating an interesting hypothesis. I think that’s extremely powerful right now.”
