Practices for Governing Agentic AI Systems
OpenAI published a framework document outlining governance practices for agentic AI systems. The piece addresses how to manage AI agents that take sequences of actions, make decisions, and operate with varying degrees of autonomy. It likely covers topics such as human oversight, authorization boundaries, and accountability structures for agentic deployments.
Related guides (4)
Related events (8)
How should AI systems behave, and who should decide?
OpenAI published a policy post clarifying how ChatGPT's behavior is shaped and governed, outlining plans to allow greater user customization of model behavior. The post also describes intentions to solicit broader public input into decision-making around AI system behavior. This represents an early public articulation of OpenAI's approach to behavioral governance and value alignment in deployed systems.
Planning for AGI and Beyond
OpenAI published a strategic document outlining its mission and approach to developing artificial general intelligence that benefits all of humanity. The post articulates OpenAI's long-term planning philosophy around AGI safety, deployment, and governance. It represents a high-level policy and values statement from the leading frontier AI lab rather than a technical announcement.
OpenAI's Frontier Governance Framework
OpenAI has published its Frontier Governance Framework, a document outlining the company's AI safety, security, and risk management practices. The framework is explicitly positioned to align with emerging regulatory requirements from the EU and California. As a Tier 1 source announcement, this represents OpenAI's formal public stance on frontier model governance and regulatory compliance strategy.
Governance of Superintelligence
OpenAI published a position piece arguing that now is the appropriate time to begin developing governance frameworks for superintelligence—AI systems conceived as dramatically more capable than AGI. The post signals OpenAI's view that existing regulatory approaches will be insufficient for superintelligent systems and calls for new international coordination mechanisms. It represents an early public framing by a major lab of the policy challenges specific to post-AGI AI.
Anthropic publishes framework for safe and trustworthy agent development
Anthropic released a formal framework for responsible agent development, articulating principles around human oversight, transparency, value alignment, and privacy for autonomous AI agents. The document draws on Claude Code as a reference implementation and cites enterprise deployments at Trellix and Block as real-world examples. The framework is positioned as a contribution to emerging industry standards for agentic AI systems, acknowledging open technical challenges in value alignment measurement and oversight calibration.
OpenAI Safety Practices Update
OpenAI published a safety update reaffirming its commitment to responsible development and deployment of AGI. The post is a high-level statement from a Tier 1 lab on its safety posture. The body excerpt is brief and does not detail specific new policies, evaluations, or technical measures.
Frontier AI regulation: Managing emerging risks to public safety
OpenAI published a policy position on regulating frontier AI systems, focusing on managing emerging risks to public safety. The piece outlines OpenAI's perspective on how governments and regulatory bodies should approach oversight of the most capable AI models. This represents a formal public stance from a leading AI lab on the shape of future AI governance frameworks.
OpenAI co-founds Agentic AI Foundation, donates AGENTS.md
OpenAI has co-founded the Agentic AI Foundation, a new organization housed under the Linux Foundation, aimed at developing open and interoperable standards for safe agentic AI systems. As part of this initiative, OpenAI is donating AGENTS.md, a specification document, to the foundation. The move signals OpenAI's intent to shape industry-wide norms around agentic AI through open governance structures rather than proprietary control.