Extract the employee, severance amount, benefits continuation, release of claims, and restrictive covenants from a separation agreement or release PDF.
The full guide: Severance and release of claims in a separation agreement
Need to scale? Create an API key, then run this from your own code or an agent.
Create an API keyFree account required
Upload a file or pick a sample, and see the fields come back.
No signup · nothing stored
The document number, the document date, the effective (separation) date, the employee name, id, and position, the employer name, the employment start date, the severance amount with its currency, and the severance period in weeks.
A separation agreement pairs a severance payment with a release of claims and post-employment restrictions. A termination letter is the employer notice ending employment, and a settlement agreement resolves a specific legal dispute. For the notice use the termination letter extractor; for a dispute settlement use the settlement agreement extractor.
Whether the agreement includes a release of claims, a covenant not to sue, a non-disparagement obligation, a confidentiality obligation, a non-compete, a no-solicit of employees, a no-solicit of customers, an anti-assignment clause, and termination for convenience each come back as booleans, alongside the non-compete duration in months.
Yes. The severance payments table returns each payment date, amount, and type (lump sum, installment, or deferred); the benefits schedule table returns each benefit type with its start and end dates and coverage amount; and the restricted activities table returns each restriction type with its duration, geographic scope, and description.
No. It reports the fields present on the agreement as structured data and gives no legal opinion on the release or restrictions. It also captures benefits continuation and duration, the governing law, and the signature date. PDF only, up to 10MB and 100 pages; processed for extraction only and not retained.
The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.
See document data extraction if you run this for people and payroll teams, or the extraction API if you are building it in.