AI Data Handling
Last updated: March 31, 2026
CaseProof uses AI to generate chronologies and identify evidentiary gaps. This page describes exactly which models are used, what data is sent to them, and what is retained.
Models Used
- OpenAI GPT-4o — accessed via the OpenAI API for all AI-generated outputs.
What Is Sent to OpenAI
- Document text excerpts extracted from uploaded files, used to generate chronologies and gap analyses.
- Selected structured matter fields and intake responses relevant to the task, such as case dates, parties, and evidence context.
- Structured prompts constructed server-side that include relevant task instructions.
What Is NOT Sent to OpenAI
- Raw file binaries (PDFs, images, videos)
- User account information (name, email, billing data)
- Authentication credentials or session tokens
- Any data unrelated to the specific matter being processed
OpenAI Data Retention
OpenAI states that API inputs and outputs are not used for model training by default under its current API policies. CaseProof does not currently advertise Zero Data Retention as enabled for every customer workspace.
If our provider retention posture changes materially, we will update this page.
How Outputs Are Stored
Generated chronologies, gap findings, and saved document drafts are stored in your CaseProof workspace. OpenAI's handling of API request and response data is governed by OpenAI's API policies, while the copies stored inside CaseProof remain subject to the same access controls and encryption posture as other workspace data.
Human Review Requirement
Chronology events and gap findings begin in draft and review states inside the app. Generated documents are draft work product and must be reviewed by counsel before use. CaseProof does not present AI outputs as legal advice or final authoritative work product.