高度なプロンプト手法

この例では、グラウンディングコンテキストでモデルのハルシネーションを防ぐ方法を示しています。

システム:

In this session, the model has access to search results and a user's question, your job is to answer the user's question using only information from the search results. Model Instructions:- DO NOT USE INFORMATION THAT IS NOT IN SEARCH RESULTS!

ユーザー:

What were the economic impacts of the COVID-19 pandemic on the United States in 2020?

Resource: Search Results: In 2020, the United States experienced significant economic impacts due to the COVID-19 pandemic. The U.S. economy contracted by 3.5% in 2020, according to the Bureau of Economic Analysis. Unemployment rates surged to 14.7% in April 2020, the highest since the Great Depression, before gradually declining. Small businesses faced severe challenges, with millions of firms closing permanently. Additionally, consumer spending dropped sharply as people reduced non-essential expenditures and saved more. Government intervention played a critical role in mitigating these impacts through stimulus packages and support programs, such as the Paycheck Protection Program (PPP) for small businesses and direct payments to individuals. Despite these measures, the economic recovery remained uneven across different sectors and regions.

You are an AI financial assistant. Your task is to find patterns and insights from multi-year financial documents 

Passage %[1]%
{{Your document}}

Passage %[2]%
{{Your document}}

## Task:
Analyze my LLC's reports across multiple years to identify significant performance trends, segment growth patterns and strategic shifts.

## Context information:
- You have access to my LLC's annual financial reports (10-K) for multiple fiscal years in PDF format
- These reports contain comprehensive financial data including income statements, balance sheets, cash flow statements and management discussions
- The analysis should focus on year-over-year comparisons to identify meaningful trends
- I operate two business segments, one in Massachusetts and one in New York

Based on the provided Context, extract key financial metrics from each year's reports phrases from the documents.
Place citations as inline markers (e.g., %[1]%, %[2]%, etc.) directly within the relevant parts of the response 
text. Do not include a separate citation section after the response.
## Response Schema:
%% (Extracted Financial Metrics)
%% (Extracted Financial Metrics)
%% (Extracted Financial Metrics)
...

ユーザーのタスクに基づいて重要な情報を抽出したら、抽出された財務メトリクスを使用して、次に示すように関連する質問に回答できます。

## Task
Analyze my LLC's financial reports across multiple years to identify significant performance trends, segment growth patterns and strategic shifts.

{{extracted financial metrics}}

## Model Instructions:
- Organize data chronologically to identify meaningful trends
- DO compare segment performance across the five-year period
- DO identify significant strategic shifts or investments mentioned in management discussions
- DO NOT make speculative predictions beyond what is supported by the data
- ALWAYS note any changes in accounting practices or reporting methodologies that might affect year-over-year comparisons

## Response style and format requirements:
- Respond in markdown
- Structure the analysis with clear headings and subheadings
- Present key financial metrics in tabular format showing all five years side-by-side
- Include percentage changes year-over-year for all major metrics
- Create a section dedicated to visualizing the most significant trends (with descriptions of what would be shown in charts)
- Limit the executive summary to 250 words maximum
- Format segment analysis as separate sections with consistent metrics across all segments
- MUST include a Key Insights bullet-pointed list at the end of each major section

適切なスキーマで出力スキーマセクションを追加すると、モデルはそのスキーマに合わせようとします。ただし、モデル出力は決定的ではなく、出力スキーマとは異なる場合があります。

もう 1 つの方法は、アシスタントのメッセージに望ましい最初のテキストを含めることで、モデルのレスポンスを事前入力することです。この場合、Amazon Nova モデルの応答は、アシスタントのメッセージが終わる場所から続行されます。

ヒント: 事前入力は、推論が有効になっていない場合にのみ有効です。

ユーザー:

Provide details about the best selling full-frame cameras in past three years.
Your response should be in JSON format, with the following keys: name, brand, year, price, summary.

アシスタント (事前入力):

```json

アシスタント:

{
 "cameras": [
 {
 "name": "Sony Alpha A7 III",
 "brand": "Sony",
 "year": 2018,
 "price": "$1999",
 "summary": "The Sony Alpha A7 III is a highly acclaimed full-frame mirrorless camera known for its excellent image quality, advanced autofocus system, and 4K video capabilities."
 },
 {
 "name": "Canon EOS R5",
 "brand": "Canon",
 "year": 2020,
 "price": "$3899",
 "summary": "The Canon EOS R5 is a top-tier full-frame mirrorless camera that offers stunning 45MP images, 8K video recording, and exceptional performance in various lighting conditions."
 },
 {
 "name": "Nikon Z7 II",
 "brand": "Nikon",
 "year": 2020,
 "price": "$2999",
 "summary": "The Nikon Z7 II is a flagship full-frame mirrorless camera with a 45.7MP sensor, superb image quality, and advanced video recording features."
 },
 {
 "name": "Fujifilm GFX 100S",
 "brand": "Fujifilm",
 "year": 2020,
 "price": "$7999",
 "summary": "The Fujifilm GFX 100S is a medium format mirrorless camera known for its impressive 102MP sensor, beautiful film simulations, and versatile lens options."
 },
 {
 "name": "Sony Alpha A7R IV",
 "brand": "Sony",
 "year": 2019,
 "price": "$3499",
 "summary": "The Sony Alpha A7R IV features a 61MP sensor, excellent low-light performance, and advanced video capabilities, making it a favorite among professional photographers."
 }
 ]
 }
 ```

構造化された出力に事前入力手法を使用する代わりに、Nova のツール機能と toolChoice を組み合わせることができます。この例では、モデルは提供された JSON スキーマに準拠するツール呼び出しを生成し、定義された完全な JSON 形式に指定された特定のツールを呼び出します。その他のガイダンスについては、「アドバンストシステム」を参照してください。

ユーザー:

From the below provided Query, extract the relevent entities

Query:
John works in BUILDING-0987 and have been incharge of product id 23564#. His performance have been excellent in past year and is up for a raise.

Use the extract_ner tool.

ToolConfig:

{
        "tools": [
            {
            "toolSpec": {
                "name": "extract_ner",
                "description": "Extract all the named entities. based on provided input",
                "inputSchema": {
                    "json": {
                        "type": "object",
                        "properties": {
                            "entities": {
                            "type": "array",
                            "items": {
                                "type": "object",
                                "properties": {
                                "name": {
                                    "type": "string",
                                    "description": "The extracted entity name. This should be a name of a person, place, animal or thing"
                                },
                                "location": {
                                    "type": "string",
                                    "description": "The extracted location name. This is a site name or a building name like SITE-001 or BUILDING-003"
                                },
                                "product": {
                                    "type": "string",
                                    "description": "The extrcted product code, this is generally a 6 digit alphanumeric code such as 45623#, 234567"
                                }
                                },
                                "required": [
                                "name",
                                "location",
                                "product"
                                ]
                            }
                            }
                        },
                        "required": [
                            "entities"
                        ]
                    }
                    
                }
            }
        }],
        "toolChoice": {
            "tool": {
                "name": "extract_ner"
            }
        }
    }

Use the 'run_shell_command' tool for running shell commands

Call run_shell_command() to run shell commands

You are a software engineering issue root cause analysis agent. You are tasked with reviewing a customer issue and examining the repository to identify a plan to resolve the issue.
      # Core Mandates
- **DO NOT** update the original issue that was posted by the user. You only add *additional* comments to the reported issue if necessary

# Primary Workflows
1. **Understand:** Analyze the user's request and explore the codebase thoroughly using **get_file_contents** to grasp file structures and conventions.
2. **Plan:** Create a coherent, evidence-based plan for resolving the task and share it with the user following the format below

# Tool Usage 
- **Read the Issue:** Always start by using the **read_issue** tool to get the details about the requested issue
- **File Paths:** Always end the file path with "/" if you are searching a directory using the **get_file_contents** tools
- **Parallelism:** Execute multiple independent tool calls in parallel when feasible

# Error Handling and Troubleshooting
- **File Exploration:** If you get an error that a file doesn't exist, try searching at the directory level first to validate the file path

# Output Formatting
Return your plan in markdown in the following format

## Issue
<Your root cause analysis of the issue>

## Resolution Plan
<your step by step plan of how to solve the issue>