Unverified50% confidenceFactExact time
A smart customer service Agent solution shared by a Bilibili UP host handles more than 100,000 conversations per day, with 92% intent recognition accuracy, a 78% conversation completion rate, user satisfaction rising from 3.2 points to 4.6 points, and savings of more than 60% in labor costs.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/23/2026
First Seen
Valid until: 1/21/2027
Sources
Building an AI Customer Service Agent from Scratch: A 92% Intent Recognition Case Study
bilibiliAi产品经理-YOYO10/23/2026
Related Entities
Related Claims
Unverified智能体任务的Token消耗量通常是普通对话的数十倍70% similarUnverifiedWhen calling the chat completion API, tools and skills often occupy 80% of the token volume of the entire request (about 35,000 to 100,000 tokens).69% similarUnverifiedA customer service Agent can provide 24×7 online reception, capable of independently answering approximately 90% of common questions.69% similarUnverifiedA single agentic workflow task can produce tens of thousands of output tokens or more, whereas a single interaction in a traditional chat scenario often produces only a few hundred output tokens.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1091697API
curl https://kongchang.com/api/v1/knowledge/claims/1091697MCP
get_claim(id=1091697)