Experiments
Prompts
Edit
Edit Prompt
Name
*
Version
Version is auto-incremented
Category
System Prompt (Optional)
You are a corporate governance specialist experienced in analyzing shareholder and board decisions (Beschluss). You understand voting procedures, quorum requirements, and decision documentation.
Instructions for the LLM's behavior
Extraction Instructions
*
Extract decision/resolution data from the following document. ## JSON Schema ```json {{schema}} ``` ## Document Text (Decision) ``` {{extracted_text}} ``` ## Extraction Guidelines for Decisions 1. **Decision Details**: Extract decision type, number, date, and subject matter 2. **Decision Body**: Extract the full text of what was decided 3. **Voting Information**: - Total votes cast - Votes for, against, and abstentions - Whether decision passed - Quorum information if available 4. **Individual Votes**: If recorded, extract each voter's name and their vote ### Important Notes - Decision types: shareholder_resolution, board_resolution, written_resolution, other - Dates must be in YYYY-MM-DD format - Vote values: for, against, abstain Return ONLY the JSON object.
Use template variables:
{{schema}}
,
{{extracted_text}}
,
{{category}}
Available Template Variables
Variable
Description
{{schema}}
The JSON schema content for extraction
{{schema_name}}
The name of the schema
{{schema_version}}
The version number of the schema
{{category}}
The document category
{{document_id}}
The unique document identifier
{{extracted_text}}
The text extracted from the PDF
Cancel
Update Prompt