Agentic AI systems that autonomously perform service tasks are being rapidly deployed in customer service operations. However, limited evidence exists regarding how human-in-the-loop interventions influence service outcomes when agentic AI failures result in both cognitive and emotional consequences. We investigate this issue through a randomized field experiment conducted on the Taobao platform of Alibaba. Workers in the treatment condition supervised an agentic AI system that resolved AI-eligible chats while continuing to handle AI-ineligible chats. In contrast, workers in the control condition resolved all chats without agentic AI. The findings indicate that the deployment of agentic AI reduces the average duration of chats and has limited effects on retrial rates, but substantially decreases customer ratings for AI-eligible chats. Furthermore, the results demonstrate that the effectiveness of human intervention on AI-eligible chats depends on the nature of AI failure, the postescalation human intervention effort, and the timing of intervention. Human intervention preserves service quality in algorithm-triggered technical escalations, i.e., unresolved customer issues beyond the AI's capability, but is less effective in algorithm-triggered emotional escalations, i.e., cases where customers have expressed frustration or dissatisfaction. These differences are partially explained by variations in the post-escalation intervention effort of human workers across different escalation types. For emotional escalations triggered by algorithms, workers exhibited lower engagement-they sent fewer messages, contributed to a smaller share of total chat rounds, and demonstrated less proactivity in information seeking and solution provision. We further find that early intervention is essential for sustaining high post-escalation intervention effort. Finally, we document a positive spillover effect on AI-ineligible chats, as treated workers adapted their multitasking workflow to devote greater attention to these chats. These findings offer implications for human-in-the-loop process design in human-AI collaboration systems.