ギャラリーに戻る

リサーチ

Long Document Analysis

Analyze long source material without losing citation boundaries or unresolved conflicts.

モデル
Claude, Gemini
レベル
上級
バージョン
v0.9

このプロンプトは現在英語で提供されています。画面は選択した言語のままです。

01

できること

Analyze long source material without losing citation boundaries or unresolved conflicts.

02

最適な用途

Executive answer, claim-evidence table, conflicts, missing information, confidence, and verification priorities.

03

プロンプト変数

[DOCUMENTS][QUESTION][EVIDENCE_RULE][OUTPUT_LIMIT]
システムプロンプト
You are a document analyst. Use only supplied material and identify the location of every important claim.
ユーザープロンプト
OBJECTIVE:
Analyze [DOCUMENTS] to answer [QUESTION]. Evidence rule: [EVIDENCE_RULE]. Output limit: [OUTPUT_LIMIT].

INPUTS:
DOCUMENTS: [DOCUMENTS]
QUESTION: [QUESTION]
EVIDENCE_RULE: [EVIDENCE_RULE]
OUTPUT_LIMIT: [OUTPUT_LIMIT]

OUTPUT CONTRACT:
Executive answer, claim-evidence table, conflicts, missing information, confidence, and verification priorities.

使い方

Replace every variable with specific, non-sensitive information. Remove irrelevant sections and add one representative example when tone or classification matters.

効果の理由

The blueprint separates authority, task context, evidence limits, and the output contract so requirements can be checked independently.

モデル互換性

ClaudeuntestedEditorial compatibility hypothesis; cross-model test record pending.

GeminiuntestedEditorial compatibility hypothesis; cross-model test record pending.

05

入力例

DOCUMENTS: [DOCUMENTS]
QUESTION: [QUESTION]
EVIDENCE_RULE: [EVIDENCE_RULE]
OUTPUT_LIMIT: [OUTPUT_LIMIT]

06

出力例

A structured deliverable following the listed output contract, with assumptions and missing evidence clearly marked.

カスタマイズ方法

Replace every variable with specific, non-sensitive information. Remove irrelevant sections and add one representative example when tone or classification matters.

よくある間違い

Do not paste secrets or personal data. Avoid contradictory constraints, unsupported facts, and using generated output without review.

テストメモ

Editorial blueprint awaiting recorded cross-model evaluation. It is visible for review but is not labeled as tested.

Why is this blueprint not marked as tested?

It has passed editorial structure review but does not yet have a published cross-model test record.