고급 프롬프트 기법

이 예제에서는 그라운딩 컨텍스트를 통해 모델에서 할루시네이션을 방지하는 방법을 보여줍니다.

시스템:

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!

사용자:

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)
...

사용자의 태스크를 기반으로 주요 정보를 추출한 후, 추출된 재무 지표를 사용하여 다음과 같이 관련 질문에 답변할 수 있습니다.

## 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

적절한 스키마로 출력 스키마 섹션을 추가하면 모델이 해당 스키마에 맞게 설정됩니다. 그러나 모델 출력은 결정적이지 않으며 출력 스키마와 다를 수 있습니다.

또 다른 접근 방식은 어시스턴트의 메시지에 원하는 초기 텍스트를 포함하여 모델의 응답을 미리 채우는 것입니다. 이 경우 Amazon Nova 모델의 응답은 어시스턴트의 메시지가 중단된 지점부터 계속됩니다.

팁: 미리 채우기는 추론이 활성화되지 않은 경우에만 유효합니다.

사용자:

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.

어시스턴트(미리 채우기):

```json

어시스턴트:

{
 "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."
 }
 ]
 }
 ```

구조화된 출력에 대해 미리 채우기 기술을 사용하는 대신 Nova의 도구 기능을 toolChoice와 결합할 수 있습니다. 이 예제에서 모델은 제공된 JSON 스키마를 준수하고 정의된 전체 JSON 형식으로 지정된 특정 도구를 직접 호출하는 도구 직접 호출을 생성합니다. 추가 지침은 고급 시스템을 참조하세요.

사용자:

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>