# Conduct materials experiments and characterize properties

> As of 2026-10-18, AI does this work at L2 Partial automation. 1 update bears on it. Strongest evidence: From the publisher only.

Market: [Chemistry and materials research](https://surviagi.com/markets/science-research-chemical-materials)

Held by a non-technical condition: Manual Dexterity · Physical Presence. The level above is what the evidence supports. Whether the work may be handed over is a separate question.

## How it got here

Each time the strongest evidence rose, by the date of the update or post. These are the dates the evidence carries, not when it was collected.

- Undated · Google · [Google Research grounds agents in physical lab robotics for closed-loop molecular design](https://surviagi.com/updates/ev-b7d3cfaf9dda2187c32d4c4cd2dcc3688634f2cd): L2 Partial automation

## What moved it

Every update that bears on this work, newest first.

- Undated · Google · [Google Research grounds agents in physical lab robotics for closed-loop molecular design](https://surviagi.com/updates/ev-b7d3cfaf9dda2187c32d4c4cd2dcc3688634f2cd): Claimed L3 · Accepted L2 · From the publisher only · [Source](https://x.com/GoogleResearch/status/2111159868187181399)
  Google Research describes bringing agents to the wet-lab bench, grounding them in physical lab robotics to run closed-loop molecular design cycles and discover single-digit nanomolar protein binders for cancer targets.

## More work in Chemistry and materials research

- [Design and screen molecular and material candidates](https://surviagi.com/work/science-research-chemical-materials-material-candidates): L2

---

Page: https://surviagi.com/work/science-research-chemical-materials-materials-experiments

Data generated 2026-10-18T00:16:36.466394+00:00; method activity-level-1; ontology 2.4.0.
Machine-proposed: no person has reviewed these readings, and the method is not calibrated.
Cite the page address together with the generation time.