能够接听真实电话的人工智能接待员

1作者: kaansarac大约 2 个月前原帖
我们正在构建一个人工智能接待员,能够接听真实电话、捕获潜在客户、预约安排并发送5分钟的后续跟进。我们的首个细分市场是婚礼场地。我是其中一位创始人。 <p>对HN可能感兴趣的内容:</p> 对话循环:电话 → 流式自动语音识别(ASR) → 大语言模型工具(LLM) → 日历/电子邮件 → 语音合成(TTS),具备轮流发言和插话控制功能。 日历预约:缓冲时间逻辑 + 防止重复预约;我们提供一个最小功能API用于“提供时段/预约时段/确认”。 多渠道捕获:将电话、电子邮件和表单潜在客户统一为一个记录,包含转录和字段(姓名、日期、客人数量、预算)。 垃圾邮件过滤:在接触到员工之前阻止模式(例如,1-800电话/机器人电话);为VIP设置安全通行规则。 评估工具:脚本化的通话场景(可用性、定价、政策)→ 检查基础(答案必须在您的文档中)→ 对正确性、安全性和升级时机进行评分。 <p>未成功的方面:</p> 在知识摄取之前过于急于回答;我们现在对经过验证的来源严格限制回答,其他情况下会记录信息或升级处理。 Elevenlabs;延迟过高,无法构建类似人类的体验。 对边缘案例的困惑(“如果……你的取消政策是什么?”)。我们增加了文档优先检索 + 回退到“收集信息 + 路由”。 <p>目前的数字(早期阶段,仅有6位客户,正在改善):</p> 目标回答时间:接听时间小于一秒;电子邮件的首次回复时间为5分钟。 减少漏接电话和更快的参观安排是主要成果;一旦数据成熟,我们乐意分享更多信息。 <p>隐私/伦理:</p> 客户内容不会用于训练我们的模型。 明确的同意和录音政策;个人身份信息(PII)在存储和传输中均加密。 <p>我希望得到的反馈:</p> 针对语音代理的更好离线评估(超出愉快路径脚本)。 您发现有效的轮流发言和插话策略。 在信任AI处理电话之前,您希望的故障模式处理。 <p>链接:https://mikla.ai</p>
查看原文
We’re building an AI receptionist that answers real phone calls, captures leads, books appointments, and sends 5‑minute follow‑ups. Our first niche is wedding venues. I’m one of the founders.<p>What might be interesting to HN:<p>Conversation loop: telephony → streaming ASR → LLM tools → calendar&#x2F;email → TTS, with turn‑taking and barge‑in control. Calendar booking: buffer‑time logic + double‑booking prevention; we expose a minimal function API for “OfferSlots&#x2F;BookSlot&#x2F;Confirm.” Multi‑channel capture: unify phone, email, and form leads into one record with transcript + fields (name, date, guest count, budget). Spam filtering: block patterns (e.g., 1‑800s &#x2F; robocalls) before they hit staff; safe pass‑through rules for VIPs. Evaluation harness: scripted call scenarios (availability, pricing, policy) → check for grounding (answers must be in your docs) → score for correctness, safety, and escalation timing.<p>What didn’t work:<p>Over‑eager answers before knowledge ingestion; we now hard‑gate answers on verified sources and otherwise take a message or escalate. Elevenlabs; Latency is way too much to build a human like experience. Confusion on edge cases (“What’s your cancellation policy if…”). We added doc‑first retrieval + fallback to “collect info + route.”<p>Numbers so far (early, only 6 customers and improving):<p>Target answer time: sub‑second pickup; 5‑minute first reply on email. Reduction in missed calls and faster tour scheduling are the main wins; happy to share more once data matures.<p>Privacy&#x2F;ethics:<p>Customer content is not used to train our models. Clear consent and recording policies; PII is encrypted at rest and in transit. What I’d love feedback on:<p>Better offline evaluation for voice agents (beyond happy‑path scripts). Turn‑taking and barge‑in strategies you’ve found to work well. Failure‑mode handling you’d want before trusting an AI with calls.<p>Link: https:&#x2F;&#x2F;mikla.ai