Set Up Clause and Party Fields for Contracts

What this guide helps you do

This guide shows how to configure a contract parser in PerfectParser, define party, date, and clause fields, run a test batch, and export agreement metadata. Skip the prompt on the first auto-detect pass if you want the AI to surface additional sections before you standardise the schema.

Why contracts are hard to parse

Contracts spread signature blocks, defined terms, and clause bodies across many pages with no fixed layout standard. Party names may appear in the preamble, signature pages, and headers with slightly different legal entity suffixes ("Inc." vs "Incorporated"). Effective date and termination date are buried in recitals on page one or in a term section on page eight. Financial contract value appears in some agreements as a cap in an order form attachment, not in the main body. Clause tables require summarisation, not verbatim OCR — the parser must identify section titles like "Indemnification" or "Limitation of Liability" and produce concise summaries. Date formats vary (written-out months vs numeric), and governing law may reference a state in one clause and a country in another. Multi-page exhibits attached at the end often contain the fields your workflow needs most.

Recommended Fields

We suggest configuring the following schema fields for your Contract Parser to capture all essential metadata and legal terms.

AI Prompt (Optional)

Use this only when you want to guide auto-detect toward a specific set of fields.

If you want PerfectParser to discover additional fields on its own, leave the AI Prompt (Optional) box blank for the first pass, review the detected schema, then add a prompt only if you need tighter consistency.

When you do use a prompt, copy and paste the following instructions into the AI Prompt (Optional) field during setup:

Extract the agreement type, names of all signing parties, effective start date, termination/end date, total financial contract value, and governing law jurisdiction. Also summarize the key clauses (like termination, liability, and payment terms) in a structured table.

Set up this parser in the dashboard

Create a parser

Go to Parsers → New Parser in the dashboard. Give it a name like "Contract Parser" and optionally select the document category.

Upload a sample document

Drag and drop a representative contract (PDF, PNG, or JPEG). Use a multi-page agreement if that is your norm — the AI needs to see where parties, dates, and clause sections appear across pages.

Detect fields or use standard fields

Paste the AI Prompt from the section above into the AI Prompt (Optional) box if you want tighter field mapping, then click Auto-Detect. To discover more fields automatically, leave the prompt blank and click Auto-Detect. Or skip auto-detect and add fields manually using the Recommended Fields table above.

Review and save your schema

Check that party_one and party_two capture full legal entity names, not abbreviations from headers. Confirm key_clauses is a Table with clause_name and summary columns. Click Save.

Run a test batch

Navigate to Bulk Extraction, choose One document per file for multi-page PDFs, upload a small test set, and click Extract All Files. Review the results in Batch History and export to CSV or Excel.

Common mistakes

• Omitting key_clauses and capturing only party names and dates — legal review workflows need clause summaries, not just metadata.
• Splitting a party name across two lines in the preamble and storing only the first line in party_one.
• Mapping signature date into effective_date when the agreement specifies a different commencement clause.
• Storing contract_value as Text when the amount appears with currency formatting — use Number for downstream reporting.

Next steps

• Create a Parser guide
• Bulk Extraction guide
• Export Results guide