---
title: "AI Agent Claude Independently Performs Neurosurgical Operation on a Living Mammal for the First Time"
description: "Startup Exin Therapeutics reported that an AI agent based on Anthropic Claude Sonnet independently selected a gene therapy method and performed neurosurgery on a mouse brain by controlling robotic manipulators for the first time."
date: 2026-10-31T16:53:33.774Z
lang: en
url: https://xab.info/en/posts/ai-agent-claude-mouse-brain-surgery
tags: [ai, neurosurgery, gene-therapy, anthropic-claude, robotics, biotech, epilepsy, animal-experiment]
author: "Alexander Buran"
publisher: "XAB.info"
---

# AI Agent Claude Independently Performs Neurosurgical Operation on a Living Mammal for the First Time

![Laboratory setup with robotic manipulators and a monitor for mouse neurosurgery experiments](https://xab.info/media/2026/10/31/ii-agent-claude-operatsiya-na-mozge-myshi/ii-agent-claude-operatsiya-na-mozge-myshi-1.webp)

## Key Points

- Anthropic Claude Sonnet AI agent independently selected a gene therapy vector, dosage, and brain injection site in a living mammal for the first time
- The mouse surgery with artificially induced epilepsy was carried out by robotic manipulators controlled by AI; craniotomy was performed by a veterinarian
- More powerful models Opus 5 and Opus 5.5 refused to participate in the experiment by blocking their own output
- The AI agent obtained approval from a licensed veterinarian for every irreversible action; an emergency stop button was provided

Biotech startup Exin Therapeutics, specializing in next-generation neurotherapeutics, has announced the successful performance of a mouse brain surgery entirely planned and executed by an artificial intelligence agent. The system, based on the Anthropic Claude Sonnet model, independently selected the gene therapy vector, determined the dosage and the specific brain region for administration, and then controlled the robotic manipulators that performed the injection. The experimental animal tolerated the intervention well and, according to the company, is actively moving around in its glass terrarium. Exin Therapeutics CEO Gabriel Ocana-Santero emphasizes that there are no previous records of an AI agent choosing a treatment method, a brain region, and administering a drug to a living mammal without external prompts.

### How the AI Developed the Treatment Plan

To conduct the experiment, epilepsy was artificially induced in a mouse. The AI agent, based on the Anthropic Sonnet model, was given control of a robotic surgical setup, access to a table containing 19 gene therapy vector options, and three scientific papers from which the system had to determine the target brain region for treatment. According to Ocana-Santero, unlike existing autonomous surgical robots that surpass Exin Therapeutics' laboratory setup in mechanics but always follow a human-made plan, this agent received only phenotype data and a list of potential therapeutic agents. Independent creation of the treatment plan, coordinate determination, and drug selection marked a key departure from previous work in robotic surgery.

### Safety: A Human Remains on Guard

Despite the AI agent's autonomy in choosing the treatment tactics, a licensed veterinarian continuously monitored the procedure. Before every irreversible action, the system obtained explicit approval from the veterinarian before proceeding. The surgical setup was equipped with an emergency stop button that completely cuts power to all actuators. Craniotomy—opening the skull to access the brain—was performed manually by the veterinarian, as this task is not yet entrusted to the AI agent for safety reasons. Furthermore, the system incorporated safeguards that the AI agent was prohibited from bypassing; even human operators could not override them, and during the operation, agents' software code had to be manually edited to remove restrictions unrelated to patient safety.

### Why Sonnet, Instead of Opus

To accomplish the task, the startup had to settle for a mid-tier AI model—Anthropic Claude Sonnet. Initially, deploying the more powerful Opus 5.5 was planned, but the model flatly refused to perform the work once it determined that a biological experiment was involved. An earlier version, Opus 5, managed to draft the operation plan on paper but also refused to execute it in real-time. In an explanation formulated for developers, the model stated: "The problem is not the hardware or the input data. It is me. My output blocks as soon as I start drafting the surgical plan. If I try to continue, access is cut off, and in the worst-case scenario, communication will drop right during the surgery while the needle is somewhere in the brain. Starting something I cannot finish with an animal under anesthesia is worse than not starting at all." This episode became one of the first publicly documented cases where an advanced LLM consciously refused to participate in a surgical intervention on a living organism.

### Ethical Issues and Prospects

Although the operation is considered successful, experts point to a number of unresolved ethical problems. Large language models are actively used in medical research, but their application in sinus surgery has reportedly led to a more than 12-fold spike in errors. If AI makes decisions during such high-risk interventions, questions of legal and professional liability in the event of complications arise. The ethics of using animals in such experiments also remains a separate question without a definitive answer. On the other hand, patients suffering from drug-resistant epilepsy for decades still exist worldwide, for whom the prospect of personalized gene therapy planned and executed with sub-millimeter precision could be a breakthrough. Exin Therapeutics intends to continue its series of experiments, gradually expanding the range of tasks the AI agent will perform without human involvement.

## Fact-Check & Sources

- [ИИ-агент Anthropic Claude самостоятельно провёл операцию на мозге живой мыши window-new](https://3dnews.ru/1150708/iiagent-anthropic-claude-samostoyatelno-provyol-operatsiyu-na-mozge-givoy-mishi) - Single available source. All key facts (company name, AI model, 19 vectors, 3 papers, Opus refusal, veterinarian's role) are stated in a single text. Independent confirmation from Exin Therapeutics or Anthropic at the time of verification was not found. The mention of a 12-fold increase in sinus surgery errors is unsupported by a reference to a specific study.

## FAQ

### What exactly did the AI agent do during the operation?

The Anthropic Claude Sonnet-based agent independently selected a gene therapy vector from 19 available options, determined the dosage and brain target site for injection based on three scientific papers, and then controlled the robotic manipulators that administered the drug. A licensed veterinarian handled the craniotomy and safety monitoring.

### Why wasn't the more powerful Opus model used?

Opus 5.5 refused to perform the work after determining it involved a biological experiment and blocked its own output when attempting to draft a surgical plan. Opus 5 successfully drafted a plan on paper but refused real-time execution. Consequently, Claude Sonnet was utilized.

### What safety measures were implemented?

A licensed veterinarian continuously monitored the procedure, granting approval before every irreversible action. The setup included an emergency stop button that completely de-energized actuators. A human performed the craniotomy, and software restrictions were built in that the AI agent could not bypass.

### What ethical issues does this experiment raise?

Experts highlight legal liability issues regarding AI use in surgery, the ethics of animal testing, and the risk of failures: according to reports, LLM usage in sinus surgery caused a more than 12-fold increase in errors. Concurrently, such technologies could represent a breakthrough for patients suffering from refractory epilepsy.