Solerno

Applied AI labAmsterdam, NL

Systems you can score.

Solerno builds AI systems you can evaluate: environments, agents, and machines.

LatestSudoku SFT + RL Environment2026-08

FigmaBenchSudoku SFT + RL EnvironmentLangSmith Evaluation SystemDeepTeam Red-Teaming with Local QwenAgent OntologyPi + Orca Local EnvironmentSO-101 Robot Armİnanç Tekstil Curtain StoreAgentic Due DiligenceFigmaBenchSudoku SFT + RL EnvironmentLangSmith Evaluation SystemDeepTeam Red-Teaming with Local QwenAgent OntologyPi + Orca Local EnvironmentSO-101 Robot Armİnanç Tekstil Curtain StoreAgentic Due Diligence
Live

Featured

FigmaBench

A 100-task benchmark for whether language models can design in Figma through the Plugin API. Not screenshot-to-code.

tasks
100
reward layers
6
UI categories
10

More work

Work

Named systems, not services. Each entry is something we trained, measured, or shipped.