This study examines how AI innovation quality shapes national ESG performance, including its governance dimensions, across 82 countries from 2000 to 2023. AI quality is measured as citation intensity per capita, reflecting scientific influence and technological sophistication validated in prior macro studies rather than patent volume, as citations better capture deployable impact for policy applications like regulatory compliance monitoring and transparent decision systems. Building on resource-resilient world theory, we assess direct AI effects and conditional interactions with financial institutions, globalization exposure, human capital, corruption, economic complexity, and clean-energy transitions using robust multi-model econometrics including IV-GMM to address endogeneity. The findings reveal advanced AI innovation quality significantly improves composite ESG performance, with stronger effects in developed economies where institutional capacity amplifies technological capabilities. AI citation intensity translates scientific breakthroughs into practical governance tools, enhancing regulatory transparency (G pillar), emissions tracking (E pillar), and social compliance (S pillar), though developing nations face implementation barriers. The findings imply that high-quality AI innovation serves as a critical technological shock absorber, enabling nations to enhance regulatory transparency and manage resources more resiliently against external shocks. However, the divergence between developed and developing nations suggests that technological sophistication must be paired with institutional reforms and human capital development to avoid value destruction. Ultimately, strategically governing AI innovation quality is essential for aligning global technological trajectories with long-term ESG performance and sustainable development goals.

Purpose – This study aims to investigate how environmental regulation breaks the low-end knowledge lock-in of resource-based cities and promotes green technology innovation through knowledge management mechanisms, and to examine the important role of digital inclusive finance (DF) as a knowledge acquisition infrastructure. Design/methodology/approach – Drawing on dynamic knowledge management theory, this study uses a DID approach and uses panel data from 264 prefecture-level cities in China from 2014–2023, taking the Environmental Protection Tax Law (EPTL) as a quasi-natural experiment, to examine the effect of the EPTL on green technology innovation in resource-based cities, the mediating mechanisms of knowledge search and knowledge integration and the moderating mechanism of DF. Findings – The EPTL significantly promotes green technology innovation in resource-based cities, a result robust to a series of tests. Mechanism analyses reveal that the EPTL facilitates green innovation by enhancing knowledge search and knowledge integration. DF strengthens both mediating pathways. Heterogeneity analyses show that the positive effect is more pronounced in cities with weaker legal systems and those experiencing severe resource depletion. Originality/value – To the best of the authors’ knowledge, this study is among the first to conceptualize environmental regulation as a knowledge governance mechanism that breaks low-end knowledge lock-in in resource-dependent regions. It extends dynamic knowledge management theory by identifying knowledge search and integration as micro-foundations of the Porter effect, and reveals DF as a knowledge management infrastructure that lowers search costs and enhances integration efficiency.

Purpose – Knowledge governance has prioritised coordination efficiency over its distributive consequences – a blind spot this study terms the efficiency–equity gap. Drawing on Common Prosperity Theory, Organisational Justice Theory and Social Exchange Theory, this study aims to develop and test a framework operationalising common prosperity through distributive justice and perceived investment in employee development, tracing effects through knowledge governance mechanisms and transactive memory systems to innovative work behaviour. Design/methodology/approach – Data from 287 employees in knowledge-intensive Chinese organisations were analysed using covariance-based structural equation modelling and 5, 000-resample bootstrapping. A marker variable test confirmed negligible common method bias. Findings – A total of 7 out of 10 hypotheses were supported. Distributive justice (β = 0.130, p = 0.007) and perceived investment in employee development (β = 0.348, p < 0.001) predicted knowledge governance mechanisms, transactive memory systems (β = 0.683, p < 0.001) and innovative work behaviour (β = 0.236, p < 0.001). Distributive justice had no direct innovation effect (p = 0.862) but a significant indirect effect via governance (β = 0.024, p = 0.022), resolving the innovation paradox. The model explained 53.7% of the variance in innovative work behaviour. Practical implications – Governance systems need equity audits, inclusive credit allocation and expertise transparency across all levels. Originality/value – This study is the first to embed Common Prosperity Theory in knowledge governance as a design principle – introducing the efficiency–equity gap, resolving the innovation paradox and establishing knowledge governance mechanisms as a dominant antecedent of transactive memory system formation.