工作流程
五種工作流程模式，每種都是由策略路由步驟構成的有界圖，生成一條完整的追蹤紀錄。
工作流程
五種常見結構。每個標籤頁展示流程圖及本範例中各步驟路由至的模型；點擊查看 flow_ir 可取得完整可複製的項（term）。建議先用 POST /x/flow/normalize 進行演練。每個節點宣告自身策略（filter + rank），圖表中的模型 ID 與成本展示實際路由結果——內部值保持英文。
低成本分類，依品質下限起草，再經一個強力 no-log 守衛在發送前審核——若不符規範可拒絕輸出。圖表中每個節點各自執行策略決策，「已排除」表示未通過篩選的候選，「已解析 · 執行」表示選中的模型。
查看 flow_ir
["flow", {
"u": {"kind": "input"},
"t": {"kind": "llm", "system": "Classify the ticket and extract the account id as JSON.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["has_cap", "supports_json_mode"]],
["neg", ["normalize", ["field", "price_out"]]], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u"]},
"d": {"kind": "llm", "system": "Write a reply using the ticket and the triage.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["cmp", "bench_intelligence", "ge", 0.55]],
["neg", ["normalize", ["field", "price_out"]]], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u", "t"], "template": "Ticket:\n$1\n\nTriage:\n$2"},
"g": {"kind": "llm", "system": "Check brand voice, PII, refund limits. Refuse if any fail.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["is", "no_log"]],
["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["d"]},
"out": {"kind": "output", "inputs": ["g"]}
}]先用低成本模型起草，再由能力更強的評審者指出缺陷，最後重寫——在預算內達到品質提升。圖表中各步驟獨立決策，流程依序為「待執行」→「執行中」→「已解析」。
查看 flow_ir
["flow", {
"u": {"kind": "input"},
"d": {"kind": "llm", "system": "Draft an answer.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["neg", ["normalize", ["field", "price_out"]]], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u"]},
"c": {"kind": "llm", "system": "Critique the draft: list concrete flaws and gaps.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["d"]},
"r": {"kind": "llm", "system": "Rewrite the answer, fixing every point in the critique.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u", "d", "c"], "template": "Question:\n$1\n\nDraft:\n$2\n\nCritique:\n$3"},
"out": {"kind": "output", "inputs": ["r"]}
}]從相同策略中進行 N 次帶種子的採樣（sample 將多個選擇分散至排名靠前的模型），再由裁判擇優選出結果。圖表中可見並行起草節點各自獨立決策的過程。
查看 flow_ir
["flow", {
"u": {"kind": "input"},
"n1": {"kind": "llm", "system": "Answer the question.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["sample", 0.5], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u"]},
"n2": {"kind": "llm", "system": "Answer the question.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["sample", 0.5], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u"]},
"n3": {"kind": "llm", "system": "Answer the question.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["sample", 0.5], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u"]},
"j": {"kind": "llm", "system": "Pick the single best candidate; return it verbatim.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["n1", "n2", "n3"], "template": "A:\n$1\n\nB:\n$2\n\nC:\n$3"},
"out": {"kind": "output", "inputs": ["j"]}
}]三個依系列（family）指定的模型並行起草，第四個模型綜合產出更優的單一答案。每個指定節點使用 family_eq 加常數 zero 評分器（過濾器已將候選限定在單一系列），圖表中「最終模型」標籤指向綜合步驟。
查看 flow_ir
["flow", {
"u": {"kind": "input"},
"a": {"kind": "llm", "system": "Draft an answer.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["family_eq", "gemini-3.1-pro-preview"]],
["zero"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
"b": {"kind": "llm", "system": "Draft an answer.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["family_eq", "claude-opus-4-8"]],
["zero"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
"c": {"kind": "llm", "system": "Draft an answer.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["family_eq", "deepseek-v4-flash"]],
["zero"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
"f": {"kind": "llm", "system": "Synthesize the single best answer from the drafts.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["add", ["scale", 0.7, ["normalize", ["field", "bench_intelligence"]]],
["scale", 0.3, ["neg", ["normalize", ["field", "price_in"]]]]],
["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["a", "b", "c"]},
"out": {"kind": "output", "inputs": ["f"]}
}]推理模型與程式設計模型在各自過濾器下並行運行，隨後由合併步驟整合——適用於同時需要推理與程式碼的任務。圖表中可見兩個分支各自經歷「已排除」／「已解析」的過程。
查看 flow_ir
["flow", {
"u": {"kind": "input"},
"rz": {"kind": "llm", "system": "Reason through the problem step by step.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["is", "cap_reasoning"]],
["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
"cd": {"kind": "llm", "system": "Produce any code the problem needs.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["cmp", "bench_coding_rank", "le", 5]],
["add", ["scale", 0.7, ["normalize", ["field", "bench_coding"]]],
["scale", 0.3, ["neg", ["normalize", ["field", "price_out"]]]]],
["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
"m": {"kind": "llm", "system": "Merge the reasoning and the code into one answer.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["add", ["scale", 0.6, ["normalize", ["field", "bench_intelligence"]]],
["scale", 0.4, ["neg", ["normalize", ["field", "price_out"]]]]],
["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["rz", "cd"], "template": "Reasoning:\n$1\n\nCode:\n$2"},
"out": {"kind": "output", "inputs": ["m"]}
}]