Directed Improvisation
Term
Directed Improvisation
Citable Version (DOI): http://dx.doi.org/10.2139/ssrn.6232019
Idea level
Model
Definition
Directed Improvisation, as articulated by Yuen Yuen Ang in 2016, is a model for enabling collective creativity that combines top-down direction with bottom-up improvisation, in contrast to rigid control or decentralized chaos.
While directed improvisation has appeared in other domains such as computer programming and performing arts, Ang is the first to apply it systematically to development and governance in How China Escaped the Poverty Trap (2016), with later extensions to U.S. innovation policies and human-AI co-creation.
Mechanisms
☐ Variation: Multiple local actors generate different solutions in parallel, by “using what they have”
☐ Selection: Clearly define and reward success; scale up what works, discard what doesn’t
☐ Niche creation: Ensure actors don’t just mimic each other but find unique roles suited to their conditions
☐ Coevolution: Directed improvisation as meta-institution enabling state-market coevolution
Sources
First articulation and empirical demonstration:
Ang, Y.Y. (2016) How China Escaped the Poverty Trap, Chapter 2 (“Directed Improvisation”) and Chapter 2 (Table 2.1).
Later extensions
Ang, Yuen Yuen. “The False Choice Between Neoliberalism and Interventionism.” Project Syndicate (2023).
Ang, Yuen Yuen. “Directed Improvisation with AI.” PhD course taught at JHU, Syllabus Posted on SSRN (2026).
Genealogy
[Paradigm] AIM (Adaptive, Inclusive, Moral Political Economy)
→ [Pillar] Adaptive Political Economy (APE)
→ [Concept] Complex vs. Complicated
→ [Concept] Uncertainty vs. Risk
→ [Concept] Influence vs. Control
→ [Model] Directed Improvisation
→ [Application] Development and governance in reform-era China (How China Escaped the Poverty Trap)
→ [Application] U.S. innovation promotion policies
→ [Application] Directed Improvisation with AI: redefining human-AI relationship as director-improviser, rather than commander-tool
Quotes
“At first blush, ‘directed improvisation’ seems to be a contradiction in terms, as we normally think about ‘directed’ as controlling and giving top-down orders and ‘improvisation’ as decentralized and free-flowing… In fact, direction and improvisation are necessary complements. A skilled director is not one who dictates to actors what exactly they should do; rather, he or she enthuses and empowers them in the creative process.”
— Ang, How China Escaped the Poverty Trap (2016), p. 69
“But this is a false choice. Governments are not limited to a binary choice between laissez-faire and top-down planning. A third option, long-neglected by policymakers and economists, is for governments to direct bottom-up processes of improvisation and creativity, akin to the role of an orchestra conductor.”
— Ang, “Interventionism and Neoliberalism” (2023)
“Anchored in Ang’s model of directed improvisation, the course centers direction as a meta-level skill, treating AI not as a passive tool but as a complex, co-creative system whose outputs depend on how humans guide it. Moving beyond simple commands and prompts, it introduces a method of paradigm-level direction, where humans direct the underlying assumptions, values, positionality, and concepts of AI.”
— Ang, Directed Improvisation with AI (2026)
Concept Constellation
Across Ang’s work, Directed Improvisation consistently co-appears with the following concepts and analytic themes:
Paradigm: Adaptive Political Economy
Ontological distinctions: Complex vs. Complicated; Influence vs. Control; Uncertainty vs. Risk
Applications of directed Improvisation: China, USA, Human-AI Co-Creation
Directed Improvisation enables Coevolutionary Development (as seen in China, USA, Nigeria)
Complexity & Development (global development agenda)
[Compare external term]
Adaptive Efficiency (Douglass North)
Complexity and Development (Owen Barder)
Gradual Institutional Change (Thelen & Mahoney)