Extract Author

Use this template for repeatable, defensible AI review in Claira.

When you select this template, Claira displays the prompt configuration panel. Map the output to a review field in your case — typically a Memo field for the extracted author name.

What this prompt is for

This template identifies who a document is from — the individual and/or organisation that created or sent it — across any document type: the primary sender of an email, the company issuing an invoice, the writer of a letter. It returns names in a clear, consistent format suitable for affidavits and structured coding.

Step-by-step in Claira

1. Open Prompting > Template picker in your case.
2. Select Extract Author and map the output to one or more review fields.
3. Run a 10-25 document sample and inspect edge cases first.
4. Adjust instructions outside the prompt body (field mapping, workflow settings), then rerun.

The prompt

Identify the author of this document: the name of the individual and/or organisation that created or sent it. For emails, this is the primary sender. For invoices, this is the company issuing the invoice. For letters, this is the person or organisation that wrote and sent the letter. If both an individual and their organisation are identified, return them as "Individual Name (Organisation Name)". Return the name(s) exactly as they appear in the document, with no commentary. If no author can be determined, return "Undetermined".

Recommended customizations

• Add case context before running (date range, custodians, issue framing).
• Keep output constraints explicit (format, allowed values, fallback behavior).
• Version your template configuration so results remain reproducible.

Worked example

Input excerpt

Invoice 2041 issued by Northwind Supply Ltd. on 2025-02-14, billed to Dana Lee, Fabrikam Inc., for consulting services rendered in January.

Expected output shape

A concise answer that follows the exact format required by the prompt and is directly mappable to your selected review field(s).

Troubleshooting

• If output is too broad, reduce scope and test with a smaller sample.
• If output format drifts, restate strict formatting requirements in workflow instructions.
• If quality varies across models, compare two models on the same fixed sample set.

Related

• Prompting Overview
• Custom Prompts