Anthropic’s Claude begins autonomously running science experiments

Scientific research often depends on complex laboratory equipment that only specialists know how to use. But Anthropic is now rolling out a system that allows AI agents to control lab devices and autonomously carry out experiments in Robo-Labs.

Laboratory automation technology has been around for decades but getting different bits of equipment to talk to each other has traditionally been a major headache. Most instruments use their own proprietary interfaces, so connecting a microscope to a robotic arm or a liquid handler typically requires bespoke software that takes specialists weeks or even months to build.

Anthropic says its new Model Hardware Standard can reduce this process to minutes by giving devices a common language. It relies on a standardised “driver” that lets any programmable device describe itself to an AI agent, allowing the AI to handle the integration. The company announced its opening the system up as a research preview to an initial group of labs and manufacturers.

“Our hope is that the standard can be of use to researchers, engineers, and other practitioners in speeding up the process of discovery and experimentation in any domain that uses devices with a programmable interface,” Anthropic said in a press release.

The standard is similar to Anthropic’s Model Context Protocol, which makes it easier for AI to interact with third-party software, but the new system is aimed at hardware instead. The driver at its heart is essentially a piece of software that sits between a computer and a piece of hardware, translating instructions from one into signals the other can act on.

The Future and Deep Future of AI 2040, a keynote by futurist Matthew Griffin

Most laboratory instruments already run some form of driver, but each has traditionally spoken its own dialect, which is why connecting them has required custom code that can translate between devices. Anthropic’s new driver standardises that dialect using deliberately simple commands such as “read” or “write,” which can refer to anything from checking a temperature to setting the length of an operation.

Because every device speaks in these same basic terms, machines can find each other on a network and exchange data without a custom program to translate between them. The driver also makes it easier for the company’s Claude agents to learn how to use a device they’ve never seen before.

The standard lets users encode key details, like the weight of a robotic arm, using natural language. They can either write out their hardware setup themselves or have an agent interview them about it. The system then turns that information into a reference file covering what a device can measure, what can be adjusted, and what safety limits apply.

Anthropic says this lets its agents orchestrate complex experimental processes across multiple instruments in often highly complicated and interactive ways.

“We’ve found that Claude interacts with experiments and hardware in an exploratory manner, much as a scientist would,” the company writes. “We observed Claude make an adjustment to a laser, observe the results through a camera to assess how its adjustment moved the laser beam, and repeat the process, seeking to understand the sequence of events.”

Speaking to the Financial Times, Anthropic scientist Alek Kemeny described watching Claude locate a specific, unfamiliar structure in a live brain tissue sample during a neuroscience experiment by manipulating a microscope’s mirrors and lasers on its own.

“The neuroscientist sitting there said: ‘Yep, that’s right,’” said Kemeny.

The new standard could be key to the company’s ambition to move beyond its key markets of software development and knowledge work and allow its AI to start having an impact in the physical world. But allowing AI, which is still not immune to hallucinations, to control real-world hardware carries considerable risks.

“It is an impressive proof of concept, but how do we ensure safety in the physical world? Because small errors can matter here," Kaoutar El Maghraoui, principal research scientist at IBM, said on the company’s Mixture of Experts podcast.

That’s probably why Anthropic is only releasing the standard to a small number of partners initially, and it has committed to working with them to build safety evaluations for AI systems that are operating physical hardware. If the early launch goes well though, AI agents could soon make an impact in far greater swathes of the economy.

First published on Fanatical Futurist on 27 August 2026.

311 Intelligence

What this means

Analysis by the 311 Strategic Intelligence Unit

The big shift is AI moving from screens into the physical world of the lab. Anthropic's Model Hardware Standard gives lab devices a common driver, so Claude agents can find instruments, learn to use them and run experiments across several at once, with integration work cut from weeks or months to minutes. Our Starburst data shows where this leads: we track Self-Driving Laboratories, labs where AI plans experiments and robots carry them out, and we expect them to reach wide use by 2038. We also rate AI Agent Communication Protocols, shared rules such as Model Context Protocol, an Act now technology.

What it means by sector.

• Life sciences and research: Claude located an unfamiliar structure in live brain tissue by adjusting a microscope on its own. Faster set-up of experiments is the main gain Anthropic is aiming for.
• Manufacturers of lab equipment: Anthropic is opening the standard to an initial group of labs and manufacturers. Devices that describe themselves in a common format will be easier for AI agents to use.
• Every organisation with programmable hardware: Anthropic says the standard can help in any domain that uses devices with a programmable interface. We track Physical AI, AI that sees, understands and moves in the real world, with wide use expected by 2037, and General Purpose Technologies, AI spreading across every industry like electricity and the internet, as an Act now trend.

What to do now.

• List the programmable instruments and machines you run and which ones have open, documented interfaces.
• Set clear safety limits for any AI agent that can change physical settings, and keep a person able to stop it.
• Start with low-risk, reversible tasks, as Anthropic is doing with its small partner group.

The Starburst technologies behind this story

From the 311 Technology Starburst (first product, expected wide use and readiness):

Technology	Category	First product	Wide use	Action	TRL
Self-Driving Laboratories	Advanced Manufacturing	2020	2038	Watch	6
AI Agent Communication Protocols	Intelligence	2024	2027	Act now	8
Physical AI	Intelligence	2025	2037	Watch	7
Agentic Artificial Intelligence	Intelligence	2024	2028	Prepare	8

And the trends they feed, from the 311 Trends Starburst:

Trend	Wide use	Action
General Purpose Technologies	2023	Act now
Robotics	2030	Prepare

How this moves the trend

AI has been edging into the lab for years. In 2019 researchers used AI to build a self-driving lab, and in 2024 scientists created the first autonomous AI scientist. Later that year Anthropic proposed a new way to connect data to AI, and in March 2026 OpenAI's GPT-5 began designing scientific experiments. Anthropic's standard extends that work from software to the instruments themselves.

Go deeper with 311

• The 311 Starburst Centre: every technology and trend above, with timelines and readiness.
• 311 Vantage: ask what AI-run experiments mean for your organisation and get a plain English executive brief.
• The Exponential Technology Codex and the Annual Trends Codex: the technologies and trends reshaping every industry.
• Book a briefing or keynote on the future of AI and science for your board or leadership team.