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
如何编写一个chrome插件实现多线程高速下载大文件?
cdn版本的vue在网页中出现typeerror错误无法找到错误代码位置怎么办?
pywebview能否使用webrtc远程控制共享桌面和摄像头?
pywebview6.0如何让窗体接受拖拽文件获取真实的文件路径?
如何在linux系统中同时能安装运行apk的安卓应用?
python有没有离线验证码识别ocr库?
各家的ai图生视频及文生视频的api价格谁最便宜?
openai、gemini、qwen3-vl、Doubao-Seed-1.6在ui截图视觉定位这款哪家更强更准?
如何在linux上创建一个沙箱隔离的目录让python使用?
pywebview如何使用浏览器自带语音识别与webspeech 的api?