contract obligation evidence extractor
by nowrich
Extracts structured obligations, parties, deadlines, and legal risks from contracts into machine-readable JSON.
Secure checkout via Stripe
Works with the AI tools you already use
See it in action
You say
Analyze the attached vendor_agreement.pdf and extract all payment-related obligations, deadlines, and any clauses using vague terms like 'reasonable efforts'.
Your agent does
{ "obligations": [ { "id": "OBG-102", "text": "Client shall pay all invoices within 15 business days.", "party_responsible": ["Client"], "deadline": {"type": "duration", "value": "15 business days"}, "evidence_refs": ["Section 4.1"] } ], "flags": [ { "type": "ambiguous", "location": "Section 7.2", "description": "Uses 'commercially reasonable efforts' without defining metrics." } ] }
What you get
About this skill
The problem
Manual contract review is slow, expensive, and prone to human oversight. Missing a single deadline, ambiguous clause, or conflicting obligation can lead to significant legal and financial liability.
What it does
- Parses PDF, DOCX, and plain text contracts into structured data models.
- Extracts specific obligations, responsible parties, and associated deadlines or timeframes.
- Maps conditions precedent and concurrent triggers that modify contractual duties.
- Identifies and flags ambiguous language, logical conflicts between clauses, and missing information.
- Generates a verifiable audit trail linking every extracted data point to its source location in the document.
Why this beats prompting it yourself
General LLM prompts often miss subtle dependencies or fail to maintain strict JSON schemas across long legal documents. This skill implements specific logic for clause segmentation, temporal keyword parsing, and conflict detection via dependency graphs. It ensures high-precision extraction that is ready for integration into CLM or ERP systems without post-processing.
Use cases
- Automate the ingestion of vendor agreements into procurement tracking systems.
- Conduct due diligence during M&A by identifying high-risk or conflicting clauses.
- Generate compliance checklists by mapping all "shall" and "must" requirements to owners.
- Audit legacy contracts for undefined terms or missing effective dates.
Known limitations
Scanned documents require clear OCR for high accuracy. High-risk flag types should include a human-in-the-loop review checkpoint to validate interpretation.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Frequently Asked Questions
Popular in Finance, Legal & Accounting
akte-generator
Automate Belgian notarial deed drafting by mapping dossier data into templates with smart placeholder detection.
voorraadwaardering-controle
Controleert een voorraadlijst op plausibiliteit via een Python-script: negatieve aantallen, waarde-afwijkingen, verkoopprijs onder kostprijs (LOCOM-signaal) en trage rotatie.
What Did I Just Agree To?
Turn complex legalese into a plain-English map of your rights, risks, and red flags.
case-retrieval
Professional Chinese judicial case search and rule induction powered by the Deli Legal API.