design-research-experiments#
The study-design and orchestration layer for reproducible design research.
What This Library Does#
design-research-experiments defines study structure: hypotheses, factors,
blocking, admissible conditions, replications, and artifact flows. It
coordinates how agents, problems, and downstream analysis are connected in a
controlled experimental pipeline.
This library is the methodological control layer of the ecosystem. It is not just another execution utility. It encodes experimental method in software and is where design choices about rigor, admissibility, and reproducibility are made.
Highlights#
Study schemas for hypotheses, factors, blocking, admissible conditions, and replications
Artifact contracts that connect runs, events, and evaluation outputs
Reproducible condition materialization and execution helpers
Runnable examples and recipes for study-definition workflows
Integration points that wire agents, problems, and downstream analysis together
Typical Workflow#
Define hypotheses, factors, blocking, and admissible conditions.
Materialize concrete study conditions and replication plans.
Execute runs across agents and problems while preserving artifact contracts.
Export standardized artifacts for downstream analysis and reporting.
Reuse examples and recipes to benchmark or extend the protocol.
Note
Start with Quickstart to define a first study, materialize a concrete condition set, and get into a reproducible local loop before branching into examples, recipes, and reference material.
Guides#
Learn the study-modeling concepts, setup flow, and orchestration patterns that shape a stable experimental pipeline.
Examples#
Browse runnable examples that show the public API in action across the major study-definition and execution surfaces.
Reference#
Look up the stable import surface, CLI behavior, reference pages, and optional development extras.
Integration With The Ecosystem#
The Design Research Collective maintains a modular ecosystem of libraries for studying human and AI design behavior.
design-research-agents implements AI participants, workflows, and tool-using reasoning patterns.
design-research-problems provides benchmark design tasks, prompts, grammars, and evaluators.
design-research-analysis analyzes the traces, event tables, and outcomes generated during studies.
design-research-experiments sits above the stack as the study-design and orchestration layer, defining hypotheses, factors, conditions, replications, and artifact flows across agents, problems, and analysis.
Together these libraries support end-to-end design research pipelines, from study design through execution and interpretation.
