Your legal documents contain some of the most sensitive information in your life. We built SynthCounsel with a simple principle: your data is yours, and no one else's.
Our security commitments
These aren't marketing slogans. They're architectural decisions built into the product.
Zero Telemetry
No Google Analytics. No Mixpanel. No Segment. No tracking pixels. No fingerprinting. We don't collect usage data, period. You'll never see a cookie banner because we don't use cookies for tracking.
No AI Training on Your Data
Your documents, case details, and AI conversations are never used to train AI models. When we send text to AI providers for document generation, we use API configurations that explicitly opt out of training.
No Third-Party Data Sharing
Your data is never sold, rented, or shared with data brokers, advertisers, or any third party. The only external services that touch your data are Supabase (database) and your AI provider (document generation).
Encryption at Rest & In Transit
All data is encrypted in transit (TLS 1.3) and at rest (AES-256). Database backups are encrypted. Uploaded documents are stored in encrypted object storage.
AI Costs Included
No API keys to manage. SynthCounsel covers the cost of every AI request as part of your subscription. We hold the relationship with Anthropic on your behalf and pass through their no-training data terms.
Row-Level Security
Every database query is scoped to your user ID using Supabase Row Level Security. There is no API endpoint that can access another user's data. This is enforced at the database level, not the application level.
Full Audit Trail
Every document generation, login, and data access is logged in an audit trail visible only to you. You can see exactly what happened, when, and what data was used.
Open Security Posture
This page is our security posture document. We believe security through transparency is stronger than security through obscurity. If you have questions, contact us.
We will never:
How we handle AI
Document generation requests
When you generate a document, we send the minimum necessary context to the AI provider (Anthropic). This includes your case details and document parameters. We use API configurations that explicitly opt out of model training. The AI processes your request and returns the result — it doesn't store your data.
Chat conversations
Chat messages are sent to the AI provider for response generation only. Conversations are stored in your account (encrypted at rest) so you can reference them later. They are never shared with other users or used for training.
Document classification
When you upload a document, the AI reads it to classify the document type, extract dates, and identify parties. This happens in a single API call — the AI doesn't retain the document content after processing.
Compare our privacy to the industry
Your documents, your data
Your documents are yours. Download them. Take them to any attorney. File them yourself. SynthCounsel uses no proprietary formats — everything you generate is a standard PDF or DOCX file that works everywhere.
PDF & DOCX downloads
Every generated document downloads as a standard PDF or DOCX. No proprietary viewer, no platform-only format, no export fee.
Full case data export
Export all your cases, documents, and case details as JSON at any time. Your data is never held hostage behind a cancellation flow.
Open-core MCP server
The SynthCounsel MCP server is open-core. Use it locally, self-host it, or connect it to your own AI tools.
If you cancel today, you keep every document you generated — as standard files, in whatever folder you saved them to. That's the whole point.
Privacy isn't a feature. It's the architecture. We built SynthCounsel from day one with zero telemetry, encrypted storage, and row-level security. See also: Privacy Policy · UPL & Legal Disclaimer.