意图路由
对传入请求进行分类，并将每个请求路由到最优的处理器：确定性逻辑、专家 LLM，或人工。
并非每个用户请求都需要同一种处理器。有些可以通过数据库查询来回答。有些需要具备领域专属上下文的 LLM。有些则需要人。TypeSafe 可以作为一个快速、廉价的分类器部署在所有这些处理器之前，决定该调用哪一个。
示例：客服路由
假设你正在构建一个客服系统。消息不断涌入，需要被路由到正确的处理器。与其把每条消息都发送给昂贵的 LLM 去判断这是哪类请求，不如先分类、再相应地路由。
%%{init: {"fontFamily": "Inter, sans-serif", "flowchart": {"rankSpacing": 35, "wrappingWidth": 300, "subGraphTitleMargin": {"top": 12, "bottom": 36}}}}%%
flowchart LR
message["customer message"]
subgraph req["TypeSafe evaluates questions<br/>in parallel"]
direction TB
intent["<b>Choice:</b> intent"]
complexity["<b>Score:</b> complexity"]
%% Invisible links stack the questions; they are answered in parallel.
intent ~~~ complexity
end
message -- "one request<br/>message + 2 questions" --> req
req -- "one response<br/>2 answers with<br/>confidence" --> confidence{"<b>intent confidence<br/>≥ 0.5?</b><br/>your code"}
confidence -- "no" --> human["human agent"]
confidence -- "yes" --> route{"<b>which intent?</b><br/>"}
route -- "order_status" --> order["order lookup<br/>deterministic code"]
route -- "product_question" --> product["product specialist LLM"]
route -- "return_exchange" --> returns["returns specialist LLM"]
route -- "complaint" --> escalate{"<b>complexity > 1<br/>or its confidence < 0.5?</b><br/>"}
escalate -- "yes" --> human
escalate -- "no" --> complaint["complaint resolution LLM"]%%{init: {"fontFamily": "Inter, sans-serif", "flowchart": {"rankSpacing": 35, "wrappingWidth": 300, "subGraphTitleMargin": {"top": 12, "bottom": 36}}}}%%
flowchart LR
message["customer message"]
subgraph req["TypeSafe evaluates questions<br/>in parallel"]
direction TB
intent["<b>Choice:</b> intent"]
complexity["<b>Score:</b> complexity"]
%% Invisible links stack the questions; they are answered in parallel.
intent ~~~ complexity
end
message -- "one request<br/>message + 2 questions" --> req
req -- "one response<br/>2 answers with<br/>confidence" --> confidence{"<b>intent confidence<br/>≥ 0.5?</b><br/>your code"}
confidence -- "no" --> human["human agent"]
confidence -- "yes" --> route{"<b>which intent?</b><br/>"}
route -- "order_status" --> order["order lookup<br/>deterministic code"]
route -- "product_question" --> product["product specialist LLM"]
route -- "return_exchange" --> returns["returns specialist LLM"]
route -- "complaint" --> escalate{"<b>complexity > 1<br/>or its confidence < 0.5?</b><br/>"}
escalate -- "yes" --> human
escalate -- "no" --> complaint["complaint resolution LLM"]
第 1 步：分类意图与复杂度
questions
{
"questions": {
"intent": {
"type": "choice",
"instructions": "The primary intent of this customer message",
"criteria": {
"order_status": "Asking about an existing order",
"product_question": "Asking about a product before buying",
"return_exchange": "Wants to return or exchange something",
"complaint": "Unhappy with experience, wants resolution"
}
},
"complexity": {
"type": "score",
"instructions": "How complex is this request to resolve",
"criteria": [
"Simple lookup or standard procedure",
"Requires some judgment or multi-step process",
"Unusual situation, edge case, or escalation needed"
]
}
}
}第 2 步：路由到最优处理器
routing.py
def route_ticket(ticket_id, response):
intent = response.answers["intent"]
complexity = response.answers["complexity"]
if intent.confidence < 0.5:
# If we don't have enough confidence to classify, route to a human agent
return route_to_human_agent(ticket_id)
if intent.choice == "order_status":
handle_order_status(ticket_id)
elif intent.choice == "product_question":
handle_with_llm(ticket_id, PRODUCT_SPECIALIST)
elif intent.choice == "return_exchange":
handle_with_llm(ticket_id, RETURNS_SPECIALIST)
elif intent.choice == "complaint":
low_confidence = complexity.confidence < 0.5
# A higher complexity.score leans toward the "escalation needed" end of the scale.
if complexity.score > 1 or low_confidence:
# Too complex for safe automation, or we're not sure about the complexity; route to a human.
route_to_human_agent(ticket_id)
else:
handle_with_llm(ticket_id, COMPLAINT_RESOLUTION)一个意图路由到完全不涉及 LLM 的确定性代码。两个意图分别路由到加载了不同上下文的不同专家 LLM。还有一个意图利用复杂度分数在 LLM 与人工之间做出抉择。TypeSafe 用一次快速调用完成全部分类；昂贵的资源只会被真正需要的请求调用。
注意针对复杂度分数的额外置信度检查。正如置信度中所讨论的，结合系统所处的情境和决策的风险来理解低置信度分数的含义，始终十分重要。