ANALYSIS

950 Claude Agents Find CRISPR-Like Enzyme System in 21 Hours

A scientist in a blue nitrile glove pipettes an orange liquid into a small laboratory tube
Human scientists in Anthropic's new Bay Area lab ran the experiments that confirmed the enzyme system's RNA output. Source: Anthropic
Quick answer: On September 23, 2026, Anthropic said about 950 Claude agent sessions surveyed 1.9 billion protein clusters in 21.5 hours and found array-associated reverse transcriptases (ART), a new family of phage enzymes paired with CRISPR-like DNA repeat arrays. Scientists in Anthropic's new lab confirmed the arrays are transcribed into short RNAs, but the system's function is still unknown and the search missed it in 10 re-runs.
TLDR

Anthropic says a swarm of Claude agents searched 1.9 billion protein clusters and found a previously undescribed family of bacterial-virus enzymes paired with CRISPR-like DNA repeats, and the most useful part of its report is the candid account of how fragile that discovery was.

Claude agents found the ART family by reading raw DNA sequence

The campaign targeted reverse transcriptases, enzymes that copy RNA into DNA and that bacteria and their viruses repurpose for defense and gene editing. According to Anthropic's technical report, agents built profiles, searched a metagenomic database of 1.9 billion protein clusters, filtered 198,290 reverse transcriptase clusters into nine classes and ran 119 tasks, from census work to deep dives on unusual genomic neighborhoods. The public announcement describes roughly 3,500 new candidate systems cut to 20 written reports for human review.

Funnel chart showing Claude agents narrowing 1.9 billion protein clusters to 198,290 reverse transcriptase clusters, about 3,500 candidate systems, 20 reports and one new ART enzyme family
The ART search ran from 1.9 billion protein clusters to a single new enzyme family in 21.5 hours of wall-clock time. Chart: Santage. Source: Anthropic technical report, September 23, 2026.

One agent, looking at the DNA beside a known reverse transcriptase, noticed a repeating pattern that earlier surveys had passed over. It counted the repeats, measured their spacing, compared the layout with known systems and searched the literature for prior reports. The resulting family pairs a reverse transcriptase with an unusually long front section, a dedicated partner protein and an upstream array of 3 to 21 repeated units, a layout that resembles the repeat arrays at the heart of CRISPR.

“[The DNA next to the RT] is spectacular: I can see by eye a tandem repeat array … that’s a CRISPR-like … repeat array?!”

Claude agent transcript, quoted in Anthropic’s announcement, September 23, 2026

The discovery depended on the model reading at least 200 DNA letters

Anthropic's own tests show why this result came from a frontier model and would likely have been missed by a scripted pipeline. Only its most capable systems, Opus 5.5, Mythos 5.1, Mythos 5 and Opus 5, recognized ART arrays, and only when at least 200 nucleotides of contiguous sequence sat in the context window. Recognition dropped when the agents relied on tools to summarize the sequence. Using interpretability methods, the researchers also located two internal signals in Mythos 5 that respond to repeated DNA, strengthen with each successive copy and go quiet when the sequence is shuffled.

That finding changes where the value sits in these systems. Classic genome mining runs predefined detectors and hands the survivors to a human expert, whose attention does not scale. The Claude campaign put an expert-like reader at every step, which is how an anomaly outside the detector set got flagged at all. It also means the capability is tied to specific frontier models and to how much raw data the harness feeds them.

The ART campaign by the numbers
1.9BProtein clusters surveyed
949Agent sessions across 119 tasks
215.6MTokens consumed
21.5 hoursWall-clock time, 77 agent-hours
Source: Anthropic technical report, September 23, 2026.

The same campaign missed the array in 10 re-runs

The report's limitations section deserves as much attention as the headline. When Anthropic re-ran the campaign 10 times, the agents did not find the ART array again, which the authors attribute to the broad search space and the non-deterministic behavior of the harness. A discovery engine that surfaces a result once in 11 attempts is a powerful scout and an unreliable census.

ClaimStatus in Anthropic's report
ART is a distinct reverse transcriptase family with 95 membersEstablished from sequence and phylogenetic analysis
Repeat arrays are transcribed into discrete short RNAsShown by RNA sequencing; array RNAs ranked 4th most abundant 15 minutes into phage SA1 infection
The reverse transcriptase is active on those RNAsNot shown
The system cuts, copies or edits DNA like CRISPR toolsUnknown
The search reliably finds ART on repeat runsMissed in 10 of 10 re-runs

Source: Anthropic technical report, September 23, 2026.

Claude found the enzyme in a day, and the question of what it does now waits on the pace of human bench work.
Santage analysis

Anthropic now runs its own wet lab to close the verification gap

The announcement also introduced a life sciences research group and a Bay Area laboratory working at biosafety levels 1 and 2, with no human pathogens. Claude generates hypotheses and helps interpret data through Claude Science and Claude Code, and human scientists perform all of the lab work. That setup follows Anthropic's protein binder results in August, where outside labs validated Claude designs, and Novo Nordisk's move to run Claude Science across its R&D last week. Owning the bench lets Anthropic test its own leads instead of waiting on partners, and it turns discovery claims into something the company can check before publishing.

“This is an exciting example of how AI agents can contribute to biological discovery.”

Feng Zhang, Broad Institute and MIT, quoted in Anthropic’s announcement, September 23, 2026

The competitive frame is shifting from benchmark scores to verified findings, a trend visible in OpenAI's claim of 100 resolved math problems this week and the objections it drew. Biology sets a harder standard than math because no proof checker exists for a living cell. Every candidate an agent surfaces still needs cloning, expression and assays, and those steps move at human speed.

ART may prove to be a useful new molecular tool or an evolutionary curiosity, and Anthropic says plainly that it does not yet know which. The lasting result is the measurement: a frontier model can now read genomes closely enough to find what a specialist would flag, at a scale no specialist can cover, and the scarce resource in AI-driven biology has become the lab time needed to confirm what the agents find.

In short: Claude agents found ART, a new phage enzyme family with CRISPR-like repeats, by reading raw DNA across 1.9 billion protein clusters in under a day. The system's function is unknown and the search missed it in 10 re-runs, so lab verification, now done in Anthropic's own wet lab, is the real bottleneck.

Santage is committed to independent, transparent journalism. This article is produced in accordance with Santage's Editorial Standards and aims to provide accurate and timely information. Readers are encouraged to verify information independently.