Coscientist: a GPT-4 agent plans and runs real chemistry experiments from plain-English prompts
Gabe Gomes's group (Nature, Dec 2023) built Coscientist, a GPT-4-based agent that searches documentation, writes code and drives lab automation. Across six tasks it included successfully planning and optimising palladium-catalysed cross-coupling reactions (Suzuki and Sonogashira) from a single prompt.
Key facts
- GPT-4 with web search, documentation search, code execution and robotic liquid-handler control
- Successfully executed and optimised Suzuki and Sonogashira couplings
- Capability demonstration rather than a new chemical discovery
Science result
- Field
- chemistry / autonomous experimentation
- Problem
- Can an LLM agent autonomously design and execute wet-lab chemistry?
- Result
- LLM agent planned and executed real cross-coupling experiments via cloud-lab automation.
- AI system
- Coscientist (GPT-4)
- Human role
- Autonomous within a supervised lab setup
- Verification
- Peer-reviewed in Nature
- Status
- confirmed
What happened
An LLM was connected to laboratory tools and asked in natural language to carry out reactions, which it planned, coded and ran.
Why it matters
It was the first peer-reviewed LLM agent operating a physical lab, a precursor of 2026's AI-run labs.
Changelog
- 2026-09-29: created
Related events
- Liverpool's mobile robot chemist runs 688 experiments in 8 days and finds a 6× better photocatalyst ★★★
- GPT-5 autonomously runs 36,000 experiments in Ginkgo's cloud lab, cutting protein-synthesis cost 40% ★★★
Sources (2)
- paperAutonomous chemical research with large language models (Nature)
- pressChemistry World: first GPT-4-powered AI lab assistant
id: 2023-12-20-coscientist-autonomous-chemistry · updated 2026-09-29 · open in the interactive timeline