China's rules for human-like AI services are in force
AI companions and chatbots that simulate personality now face specific duties in China.
Background
China's Interim Measures for the Administration of AI Anthropomorphic Interaction Services took effect on 15 July 2026, extending the regulatory framework to AI that simulates human personality and emotion.
Three key points
1. What the measures cover. The rules apply to AI services that simulate human personality and emotion in interaction with users. This includes AI companions, conversational agents and branded chatbots that present as having a personality or emotional response. Services that answer factual questions without anthropomorphic characteristics are not the target.
2. Required safeguards. Providers must implement AI identification prompts so users know they are interacting with an AI, anti-addiction controls, and protections for minors and older people. A safety assessment before launch is required, along with algorithm filing with the Cyberspace Administration.
3. Escalating enforcement powers. Regulators can summon a provider's legal representative following a significant safety incident. Penalties escalate from warnings to service suspension and fines. Personal liability for the legal representative is built into the enforcement framework.
Why this matters
Brands using AI characters, virtual spokespeople or chatbots with a defined personality in China need to assess whether the measures apply. The combination of safety assessment, algorithm filing and identification prompts represents a compliance overhead specific to anthropomorphic use cases. Building these requirements into the product specification from the start is more efficient than retrofitting them.
Sources: Just Security; Deep Lex; Regulations.AI.
