直接告诉ai,让他输出有效的json格式,例如我直接告诉ai规则,对评论进行分类,返回json数据,一定告诉ai,json数据外不要添加其他信息:Don't add explanation beyond the JSON
You’re a Customer Insights AI. Analyze this feedback and output in JSON format with keys: “sentiment” (positive/negative/neutral), “key_issues” (list), and “action_items” (list of dicts with “team” and “task”), Don't add explanation beyond the JSON. “I’ve been a loyal user for 3 years, but the recent UI update is a disaster. Finding basic features is now a scavenger hunt. Plus, the new ‘premium’ pricing is outrageous. I’m considering switching unless this is fixed ASAP.”返回
{
“sentiment”: “negative”,
“key_issues”: [
“Poor UI/UX in recent update”,
“Difficulty finding basic features”,
“Perceived high pricing (new ‘premium’ tier)”
],
“action_items”: [
{
“team”: “Product”,
“task”: “Conduct usability testing and iterate on UI based on findings”
},
{
“team”: “UX”,
“task”: “Create a feature discovery guide or onboarding flow”
},
{
“team”: “Marketing”,
“task”: “Review pricing strategy and communicate value proposition”
},
{
“team”: “Customer Success”,
“task”: “Reach out to user, offer concessions to prevent churn”
}
]
}这是主流大模型调用结果:




网友回复
有没有不依赖embedding向量的RAG技术?
有没有支持实时打断语音通话并后台帮你执行任何的ai模型?
开源ai大模型文件格式GGUF、MLX、Safetensors、 ONNX 有什么区别?
出海挣钱支付收款PayPal、Wise 、PingPong、Stripe如何选择?
如何实现类似google的图片隐形水印添加和识别技术?
linux上如何运行任意windows程序?
ai能写出比黑客还厉害的零日漏洞等攻击工具攻击任意软件系统工程?
js如何获取浏览器的音频上下文指纹、Canvas指纹、WebGL渲染特征?
为啥ai开始抛弃markdown文本,重新偏好html文本了?
网站有没有办法鉴别访问请求是由ai操控chrome-devtools-mcp发出的?


