An AI agent chose a gene therapy and guided the needle into a live mouse's brain

Overview

Updated 1 hour ago

On October 28, Gabriel Ocana-Santero, chief executive of the San Francisco startup Exin Therapeutics, posted an account of an experiment his team ran. An AI agent chose one of 19 gene-therapy candidates, picked the lateral entorhinal cortex as its target, derived injection coordinates from three published papers, and drove a needle 250 nanoliters into a live mouse's brain. A veterinarian opened the skull and held an emergency stop button the whole time.

Autonomous surgical robots already exist. What is new here is that a human did not decide the operation. The agent selected the treatment and the target, then executed the delivery on a living animal. Exin's seizure results do not exist yet, the account comes only from the company, and a calibration error forced the run to stop mid-procedure.

Why it matters

If a model can pick a drug and steer a needle into a living brain, the scarce resource in animal research becomes oversight, not hands.

Questions about this story

Free account needed to ask — your question is kept and asked for you right after sign-up. Answers are public.

No questions yet — be the first to ask.

Key Indicators

Therapies the agent chose from

The agent picked one candidate from a spreadsheet of 19 options.

250 nL

Volume injected

Delivered over five minutes, with the agent setting its own motor speeds and wait times.

Live animals injected by the agent

The company reports the mouse recovered; no seizure data has been released.

~60 min

Procedure time

Against roughly 45 minutes for the same surgery done by hand.

34 mm

Errant Y-axis target

Computed on a rig with 30 millimeters of travel; the agent flagged it and refused to retry.

Voices

Curated perspectives — historical figures and your fellow readers.

People Involved

Gabriel Ocana-Santero

Chief executive and cofounder, Exin Therapeutics

Running follow-up tests on other AI models

Organizations Involved

Exin Therapeutics

Biotechnology startup

Ran the experiment; results not yet published

A San Francisco startup using AI to analyze brain activity and develop drugs for epilepsy and neurodegenerative disease.

Anthropic

AI model developer

Did not respond to a request for comment

Maker of the Claude models Exin used, one of which declined to guide the needle into the mouse's brain.

Timeline

October 2026 November 2026

3 events Latest: Today

November 2026
WIRED reports the run; accounts differ on the code fix
Today Coverage

WIRED says a second agent silently patched the calibration code; Exin's thread says Ocana-Santero did it by hand.
Today
October 2026
Company posts account of the agent-run injection
Statement

Ocana-Santero describes the agent picking a therapy, a brain region and coordinates, then driving the rig.
4 days ago
Exin posts CircuitATLAS preprint
Research

A knowledge graph of 3.83 million nodes, plus an agent that nominated a target for humans to test in live animals.
October 7th, 2026

Scenarios

Exin reports that the injected therapy reduced seizures

Uncertain Resolves by Q2 2027

Discussed by: Exin Therapeutics; the company has said it is waiting for the therapy to take effect

The chosen vector raises inhibitory GABA signaling in GABAergic neurons, delivered to the lateral entorhinal cortex where this mouse model's seizures are reported to start. If treated animals show fewer tonic-clonic seizures than controls, the demonstration becomes a result. Exin has promised a technical report; none has appeared yet.

Therapy fails; the run stands as a capability demonstration only

Possible Resolves by Q2 2027

Discussed by: Startup Fortune and The Rundown AI, both noting the outcome remains unknown

Gene therapies often fail in animal models. If the treated mouse's seizures do not fall, Exin still has a notable demonstration: an agent chose a treatment and a brain target and delivered it. The scientific value shifts from the drug to the workflow, and the company's next milestone becomes repeatability across more animals and models.

Exin lets an agent perform the craniotomy on a live animal

Unlikely Resolves by End of 2027

Discussed by: Ocana-Santero, who says the company is experimenting with agent-controlled craniotomies

Opening the skull is the step Exin currently reserves for a surgeon, calling a mistake there capable of seriously harming the animal. The company says it wants to be sure of safety before moving to live surgeries. A successful supervised run would extend the agent's role from injection to the irreversible step itself.

Historical Context

3 moments from history that rhyme with this story — and how they unfolded.

January 2022

STAR robot sutures live pig intestine (2022)

A Johns Hopkins team led by Axel Krieger reported in Science Robotics that its STAR robot had sewn together sections of intestine in live pigs, working laparoscopically, with the animals followed for a week.

Then

The surgeries succeeded, and the pigs recovered.

Now

The system let an operator pick among autonomously generated surgical plans. The machine executed; the human chose the operation.

Why this matters now

This is the line Exin says it crossed. The robot's precision was not the new part; the agent deciding what operation to perform was.

July 2025

SRT-H removes gallbladders outside a body (2025)

Krieger's lab and collaborators presented SRT-H in Science Robotics. It performed steps of a gallbladder removal on eight gallbladders, described as fully autonomous with a 100% success rate.

Then

The demonstrations worked on organs that were not inside a living body.

Now

Autonomy claims in surgery became routine enough that the meaningful question moved to what the machine decides, not whether it can move.

Why this matters now

Exin's run differs on two counts: a living animal, and an agent choosing the treatment and target rather than executing a human's plan.

December 2023

Coscientist runs chemistry experiments (2023)

Carnegie Mellon researchers described an AI agent, Coscientist, that planned chemical reactions and carried them out on robotic lab hardware, including work on palladium-catalyzed cross-coupling.

Then

The agent completed reactions on commercial cloud-lab equipment.

Now

It established a template: models connected to instruments, with humans setting the boundaries of what they may do.

Why this matters now

Exin applies the same pattern to animal surgery, where the boundaries are veterinary oversight and a physical kill switch rather than a fume hood.