Industrial Sourcing & AECPOST /v1/extract?template=contract&options=grounding,chunks

Extract Commercial Leases & Contract Key Terms

Extracts structured terms from master service agreements (MSAs), commercial property leases, subcontracts, and NDAs. Binds extracted terms directly to vector-ready text chunks with paragraph coordinates for downstream RAG and compliance auditing.

Instant execution

Run this verification workflow directly. For instant zero-auth testing with deterministic fixture data, include the Stp-Sandbox: true header.

bash
curl -X POST "https://www.stipple.sh/v1/extract?template=contract&options=grounding,chunks" \
  -H "Authorization: Bearer stp_live_your_key_here" \
  -F "file=@commercial_lease_agreement.pdf"

Expected JSON response

The engine returns deterministic findings with evidence traces, confidence bounds, and recommended actions:

json
{
  "document_type": "contract",
  "mode": "template",
  "fields": {
    "title": { "value": "COMMERCIAL PROPERTY LEASE AGREEMENT", "confidence": 0.99, "page": 1 },
    "contract_id": { "value": "LEASE-SYD-2026-44", "confidence": 0.96, "page": 1 },
    "parties": { "value": "Centuria Property Trust (Lessor) and Acme Digital Pty Ltd (Lessee)", "confidence": 0.98, "page": 1 },
    "effective_date": { "value": "2026-09-01", "confidence": 0.99, "page": 1 },
    "term_end_date": { "value": "2031-08-31", "confidence": 0.98, "page": 1 },
    "renewal_terms": { "value": "One option of 5 years exercisable not less than 6 months prior to expiry", "confidence": 0.94, "page": 2 },
    "governing_law": { "value": "New South Wales, Australia", "confidence": 0.99, "page": 2 },
    "total_value": { "value": 185000.00, "confidence": 0.92, "page": 1 }
  },
  "chunks": [
    {
      "id": "chk_01",
      "text": "3.1 Rent Escalation. On each anniversary of the Commencement Date, the Annual Base Rent shall increase by the higher of: (a) 3.5%; or (b) the percentage increase in the Consumer Price Index (All Groups Sydney)...",
      "heading_path": "3. RENT & OUTGOINGS > 3.1 Rent Escalation",
      "page_range": [2, 2],
      "tokens_estimate": 84
    }
  ]
}

AI agent prompt & MCP tool usage

When configuring autonomous agents (Claude Desktop, Cursor, Hermes), use this verified prompt pattern:

text
You are a Legal Operations Assistant.
1. Call extract_fields(template="contract", options="chunks")
2. Extract the break date, rent escalation mechanism (CPI vs. fixed 4%), and indemnity caps.
3. Highlight any uncapped liability clauses or unusual indemnification obligations.

Input parameters & headers

FieldTypeRequiredDescription
filefile (multipart)RequiredContract PDF, lease agreement, or MSA document.
templatestringOptionalSet to "contract" to apply standard agreement taxonomy.
optionsstringOptionalSet to "chunks,grounding" to receive layout-aware RAG chunks with parent headings.

Diagnostic signals & failed checks

Each check reports exactly what it tested and what evidence it found. High severity signals trigger an escalated risk band:

contract.uncapped_liabilityhigh

Agreement lacks standard limitation of liability multiplier on contract value.

contract.jurisdiction_absentmedium

No explicit governing law or dispute jurisdiction clause identified.

Production considerations & edge cases

  • Execution Blocks on Final Page: Multi-signature deed pages with schedules are supported up to the maximum page limit.

Related workflows

Take it to production

The snippets above run against the sandbox with Stp-Sandbox: true — no key, no credits, fixture data. Drop that header and the call is real, which needs a key.

A weekly credit allowance of your own, usage metering, and somewhere for purchased credits to live.

Every key gets a free weekly allowance. Past that, prepaid credit packs cover it, and Errors & limits says what happens when you run out.