How do I follow what Weibo says about a product with AI?
Connect SocialToAI to your AI client over MCP, then ask in plain words. In this recorded run an AI client answered “How is the Xiaomi SU7 discussed on Weibo this month?” with 1 request on Weibo: 12 items read in 12.6 seconds for 20 credits ($0.067). Below are the calls it made, the answer with its sources, and the prompt and API calls to run it yourself. Recorded 2026-10-18.
The question
How is the Xiaomi SU7 discussed on Weibo this month?
A product's name on Weibo brings up reposts, ads and unrelated posts along with real opinions. Keeping only the posts about the product, and seeing what they compare it with, is slow by hand. Reading what this run returned by hand takes about 2 minutes (49 words at 240 a minute; 682 Chinese characters at 400 a minute).
What the AI did
It chose the tools itself: 1 request on Weibo. Each row is one tool call as the client showed it, with what it sent, how much came back and what it cost.
| Platform | Tool | Sent | Requests | Returned | Credits |
|---|---|---|---|---|---|
brand_buzz | brand: "小米SU7" · about: "小米的电动汽车" · platforms: ["weibo"] · window: "30d" · scale: "small" | 1 | 12 posts | 20 | |
| Total | 1 | 12 items | 20 | ||
The answer
What the client answered, from what it had read. The line under each finding is a post it read, or a figure from those posts.
8 of the 12 posts found are about it: 50% positive, 50% neutral, 0% negative. What they mention most:
- Comparison with others50%“离小米SU7也就一步之遥”4 posts
- Price13%“二手SU7 Ultra是我认为性价比最高的性能车，没有之一”1 post
- Quality13%“有这句“靓仔”，加上瓜子奉上，情绪价值提供拉满了。”1 post
The posts it rests on
A selection of what was read; the marked words are what a finding rests on. An item without a link says so.
- Weibo · post40hFinding 1
9月车市杀出一匹黑马，MG 07首月交付14577台，直接坐上无定语轿车第二的位置，把Model 3甩在身后，离小米SU7也就一步之遥。到底谁在买这车？看用户画像：七成是年轻人，29岁以下过半，本科以上学历超六成，扎堆在一二线城市，收
Open the source - Weibo · post1hFinding 2
#小米su7ultra# 帅爆了 这条该上最靓的仔 PS:二手SU7 Ultra是我认为性价比最高的性能车，没有之一 30w出头即可完你超级跑车梦
Open the source - Weibo · post2hFinding 3
有这句“靓仔”，加上瓜子奉上，情绪价值提供拉满了。 #小米su7# 这次事故没啥损失，前脸还是原版原漆。 http://t.cn/AXluaalN
Open the source
What it cost
1 request, 20 credits in total: $0.067 at the $10 rate. Every answer of the API states the credits it charged and the balance left, so your AI can tell you what a question cost. A call that fails costs nothing.
| Pack | Credits per dollar | This answer |
|---|---|---|
| $10 = 3,000 credits | 300 | $0.067 |
| $50 = 20,000 credits | 400 | $0.05 |
| $200 = 100,000 credits | 500 | $0.04 |
Ask it yourself
Connect SocialToAI to your AI client once (the steps for each client), then paste the question. You do not name tools or parameters: the client picks them.
How is the Xiaomi SU7 discussed on Weibo this month?The same in code: the calls this run made, as requests to the API.
curl https://api.socialtoai.com/v1/tools/brand_buzz \ -H "Authorization: Bearer $SOCIALTOAI_KEY" \ -H "Content-Type: application/json" \ -d '{ "brand": "小米SU7", "about": "小米的电动汽车", "platforms": ["weibo"], "window": "30d", "scale": "small" }'What to try next
- Ask next: “What do the negative posts say?”
- Ask next: “Compare it with a competitor”
- Ask which products it is compared with most.
- Ask for the posts with the most engagement, with links.
- Run it as one request with the ready-made tool Brand buzz: What people say about a brand or product on each platform: the share of each attitude, what is mentioned most, and the posts with the most engagement, each with its source link.
Last updated: