Skip to content
Security & Privacy

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:

Track your clicks, scrolls, or navigation patterns
Use cookies for tracking or advertising
Share your data with advertisers or data brokers
Train AI models on your documents or conversations
Store your data in jurisdictions without strong privacy laws
Access your case data without your explicit action
Sell aggregated or anonymized usage data
Use third-party analytics or tracking scripts
Fingerprint your browser or device
Send marketing emails without your explicit opt-in

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

Practice
Typical
Us
User tracking / analytics
Yes
No
Data sold to third parties
Often
Never
AI training on user data
Common
Never
Cookie consent banner needed
Yes
No
Marketing emails by default
Yes
No
Security posture published
Rarely
This page
AI costs included in plan
No (overage fees)
Yes
Documents in proprietary format
Often
Never
Full data export available
Rarely
Always
Vendor lock-in
Yes
None
No Vendor Lock-In

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.