Summarize Document

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 summary text.

What this prompt is for

This template helps standardize outputs so reviewers can validate and code results quickly.

Step-by-step in Claira

1. Open Prompting > Template picker in your case.
2. Select Summarize Document and map the output to one or more review fields.
3. In Multi-Code, set the Scan as dropdown to Text, Image, Audio, or Video first; the template inserts only the matching instructions below (so you do not get more than one variant in the field at once). See Media scans for the file formats accepted by each mode. Other modes are unchanged.
4. Run a 10-25 document sample and inspect edge cases first.
5. Adjust instructions outside the prompt body (field mapping, workflow settings), then rerun.

The prompt

[Extracted text mode]
Provide a concise, factual summary of the document. Capture its main purpose, key events, and participants. Include the document type if identifiable. Limit to 3–5 sentences.

[Raw file mode: PDF/PNG/JPEG/WebP/HEIC/HEIF]
Provide a concise, factual summary of the attached source file. Review the file directly (including layout/table context) instead of extracted text. If sections are unreadable, image-only, or missing, explicitly note that limitation before giving best-effort findings. Limit to 3–5 sentences.

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

Email dated 2025-02-14 from Dana Lee to Jordan Park confirms the vendor contract amendment was approved and signed the same day.

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