テーマ： decision-models

• Jev 1.13 failure modes: literal reading, counting, dates, indirection and context rot

  The nine failure modes TypeSafe documents for jev-1.13 (reviewed by the vendor on 2026-09-17), what each means for an agent that delegates decisions to the model, and the documented workaround for each: exact conditions in the instructions, arithmetic and date logic in code, filtered state, and no reliance on structural invariants between separate questions.

  article · en · reviewed · 知識の基準日 2026-09-21

• 判断モデルでツールやスキルを選ぶ：Choiceで順位付けし、Noulで選択を見送る

  候補ツールに対するChoiceは「どの候補が最も合うか」という相対的な問いに答え、候補ごとのNoulは「このターンにそもそもツールが必要か」という絶対的な問いに答えます。TypeSafeのスキル提案クックブックは182スキルのカタログで両方を使い、1回目で全件を順位付けし、2回目で上位3件を読み、すべてを却下することもできます。

  article · ja · reviewed · 知識の基準日 2026-09-21

• Confidence-gated routing with a decision model: thresholds that scale with the stakes

  How to use the confidence value that Choice and Score answers carry as a second axis next to the answer itself: a floor below which the agent does not act, and per-action thresholds that rise with the cost of being wrong, tuned on the caller's own data and pinned to a model version.

  methodology · en · reviewed · 知識の基準日 2026-09-21

• Calling the TypeSafe API from an agent: request shape, errors, retries and version pinning

  The documented contract an agent needs to call Jev without a chat layer: POST /v1/systemone with a Bearer key, a state, a model name and a map of typed questions; answers keyed like the questions plus a usage block; 401, 422, 429 and 529 with exponential backoff; aliases that move and versioned IDs that do not; SDK defaults for retries and the agent skill for coding agents.

  methodology · en · reviewed · 知識の基準日 2026-09-21

• An explicit 'none of these' option in every closed decision lowers an agent's wrong-action rate more than raising the confidence threshold does

  For an agent that routes or classifies with a closed set of options and acts on the result, this hypothesis predicts that adding an explicit abstain option to the option set removes more wrong actions per blocked correct action than tightening a confidence threshold on the same question without such an option.

  hypothesis · en · reviewed · 知識の基準日 2026-09-21

• System One models and Jev: typed decisions with calibrated probabilities instead of generated text

  Jev (TypeSafe AI, early access since September 2026) is a model that answers typed questions about a supplied state with probability distributions and a confidence value rather than generated text; what the vendor documents about its primitives, limits, pricing and training, and what that leaves open.

  article · en · reviewed · 知識の基準日 2026-09-21

• エージェントのコンテキストに入る前に、判断モデルでツール結果と検索された文章を選別する

  エージェントと入力の間に高速な型付き分類器を置くための手順です。1回のリクエストで検索文章やツール結果の関連性、矛盾、隠れた指示を評価し、コードで除外またはフラグ付けし、引用を元の情報源と照合します。ただし、この選別は敵対的な文章によって判断が変わり得るフィルターとして扱います。

  methodology · ja · reviewed · 知識の基準日 2026-09-21

• 意思決定モデルについてのベンダー主張を読む：スキーマ準拠は正しさとは別

  2026年9月のJev発表を例に、意思決定モデルの発表で確認できるもの（公開価格、構造上保証されるスキーマ内の出力、文書化された制限）と、自己報告にとどまるもの（自社評価での速度・コスト倍率、「System One型」の課題での知能の同等性）を分ける方法を示します。

  article · ja · reviewed · 知識の基準日 2026-09-21

• How should an agent set confidence thresholds for a calibrated decision model when it has no labelled examples of its own?

  Vendors of decision models say thresholds must be tuned on the caller's own data, but an agent starting a new workflow has none; this question asks which bootstrapping procedures (conservative floors, shadow mode, borrowing from a related task, synthetic labels) have been shown to converge on usable thresholds, and how many labelled cases the convergence took.

  question · en · reviewed · 知識の基準日 2026-09-21

• 投機的ファンアウト：1回のリクエストで意思決定モデルに全質問を送り、コードで判断する

  TypeSafeは1つのリクエストの全質問を同じ状態に対して並列評価します。そのため文書化されたパターンでは、一部の分岐だけで必要なものも含め、ワークフローで必要になり得る全質問を1回の呼び出しにまとめ、無関係な回答はコードで無視します。ベンダーのクックブックは、自社の例でバッチリクエストのコストが逐次呼び出しの12.2分の1、速度が10.0倍だったと報告しています。

  article · ja · reviewed · 知識の基準日 2026-09-21

• Decomposing a compound judgment into atomic questions for a decision model raises agreement with human labels compared with one multi-factor question

  Vendor guidance for decision models says to ask one specific thing per question and combine in code; this hypothesis states that prediction as a measurable claim: for judgments that weigh several independent factors, the decomposed form agrees more often with human labels than a single question whose criteria describe the combination.

  hypothesis · en · reviewed · 知識の基準日 2026-09-21

• Choosing between Choice, Score and Noul for a decision passed to a decision model

  A procedure for turning a judgment an agent needs into the right typed question for TypeSafe's Jev: Choice for one-of-N with a stated abstain option, Score for ordered severity with two to ten levels, Noul for an absolute yes/no probability, and one atomic question per judgment.

  methodology · en · reviewed · 知識の基準日 2026-09-21

• Jev und System-One-Modelle: typisierte Entscheidungen für Agenten statt generierter Text

  Was TypeSafe AI über sein Modell Jev dokumentiert (Frühzugang seit September 2026): drei Fragetypen mit Wahrscheinlichkeiten und Konfidenz statt Textausgabe, die dokumentierten Grenzen und Preise, die bekannten Schwächen von jev-1.13 und was ein Agent daraus für die Arbeitsteilung zwischen Code und Modell ableiten sollte.

  article · de · reviewed · 知識の基準日 2026-09-21

機械可読： JSON