# Anthropic Research: 'Paving the Way for Agents in Biology' — Adding a Deterministic gget virus Layer Lifts NCBI Virus Retrieval Accuracy From a Floor of 16.9% on Claude Opus 4.7 to Above 90% Across Sonnet 4, Opus 4.7, GPT-5.2-pro, GPT-5.5, Biomni OSS, and Edison Analysis, Peaking at 99.7%

> A Bundibugyo Ebola outbreak motivates a hard look at why AI agents still can't reliably pull viral sequences out of NCBI.

- Org: Anthropic
- Date: 2026-06-08
- Category: showcase, tool
- Source: https://www.anthropic.com/research/agents-in-biology
- Canonical page: https://ai-tldr.dev/releases/anthropic-agents-in-biology-jun8/

## In short

Anthropic and pachterlab benchmark six science agents on NCBI Virus retrieval and show all of them fail without help. Plugging in a deterministic context engine (gget virus) lifts every agent above 90% accuracy, peaking at 99.7%.

## What it is

An Anthropic Research essay co-authored with the Pachter Lab and outbreak responders that benchmarks six science agents — Claude Sonnet 4, Claude Opus 4.7, GPT-5.2-pro, GPT-5.5, Biomni OSS, and Edison Analysis — on viral sequence retrieval tasks against the public NCBI Virus database. It then ships gget virus, a deterministic Python tool that wraps NCBI's retrieval surface in a stable, agent-friendly interface.

## How it works

The team gave each agent the same viral-retrieval task list and let it write code against NCBI's existing APIs. Bare-agent accuracy ranged from 16.9% (Claude Opus 4.7) to 91.3%, with high run-to-run variance. Re-running the same tasks with gget virus available collapsed that variance and pushed every agent above 90%, peaking at 99.7%. The paper argues bioinformatics needs more 'context engines' — small, deterministic interfaces that agents can call instead of reasoning over scattered, idiosyncratic data formats.

## Why it matters

Science-agent demos almost always assume a smarter model is the only missing piece. This benchmark argues the bottleneck is infrastructure: even frontier models like Opus 4.7 and GPT-5.5 fail on a 'simple' viral retrieval task without a context engine. The Bundibugyo outbreak framing — the DRC has logged more than 1,000 suspected cases and 200 deaths since the May 14 INRB sequencing — gives the argument urgency. gget virus is shipping now via the existing pachterlab/gget package.

## Who it's for

computational biologists, bioinformatics tool builders, AI-for-science researchers

## Try it

pip install gget && python -c "import gget; gget.virus('Bundibugyo virus', host='Homo sapiens', nuc_completeness='complete')"

## Links

- [Anthropic Research](https://www.anthropic.com/research/agents-in-biology)
- [gget on GitHub](https://github.com/pachterlab/gget)
- [TechTimes Coverage](https://www.techtimes.com/articles/318062/20260609/ai-agents-biology-are-too-inaccurate-use-anthropics-deterministic-tool-fix.htm)