Your files stay with you. We only keep your brand kit.
The Design Engine tells your AI tools how to build on brand. The decks and documents they build stay in your environment, under your existing AI agreements.
How data moves
Design intelligence flows out.
The engine answers one question: what does this brand look and sound like? Colors, typography, layout rules, templates and build instructions flow outbound to your AI tools over MCP. Those instructions are the product. Your documents stay with you.
Generation happens in your environment.
Your decks and documents are built client-side by your own AI (Claude, ChatGPT, Copilot or any tool that supports MCP) under your existing AI agreements. The content your team creates never transits our infrastructure.
We hold your brand kit. Nothing else.
Logos, fonts, colors and templates you choose to give us, typically public-facing marketing collateral, plus anonymous quality metrics. That's everything we hold.
What we store, and what we don’t
Data custody: what we store, what passes through and what never reaches us.
What we store
- Brand collateral you provide: logos, fonts, colors, uploaded templates
- Style profiles derived from that collateral
- Quality metrics: scores, layout names, slide counts
What transits, never stored
- Slide metadata (layout names, titles, word counts) during quality scoring
- Scored in memory, discarded on response
- Email addresses during brand sharing: resolved to an account ID, then dropped
What never reaches us
- The contents of your documents, decks and diagrams
- Your business data, customer data or files your team generates
- Passwords (OAuth-only sign-in) or email addresses in our application tables
We operate no AI models.
The engine is deterministic software. It computes design directives from your brand attributes. There is no model to train, so nobody trains on your data.
AI touches your assets in exactly one place: when you upload brand files, Claude (via the Anthropic API) analyzes them to extract your palette, type system and visual language. Anthropic does not train on API data. The analysis runs once, and the results become your editable brand profile.
Everything your team generates, every deck, document and diagram, is produced by your AI tools, under your agreements, in your environment. There's nothing on our side for your AI governance team to review, because nothing is generated on our side.
Security practices
- Identity is delegatedSign-in is OAuth-only via Google, GitHub or Microsoft. We store no passwords, and no email addresses in our application tables. Users are referenced everywhere as opaque IDs, including brand-sharing records.
- Modern MCP authAI-tool connections use OAuth 2.1 with PKCE, dynamic client registration and RFC 8707 resource binding. Legacy API keys are SHA-256-hashed at rest, one active key per brand, revoked on rotation.
- Tenant isolationRow-level security with owner-only access on every brand table, and a single authorization chokepoint in the engine that every brand-scoped tool routes through, enforced by tests.
- Encryption everywhereTLS for every connection in transit; AES-256 at rest on our database and file storage.
- Locked-down websiteHSTS, content-security policy, frame-deny and strict referrer headers across the site. Every API route that touches account or brand data is authenticated.
- Telemetry without PIIError monitoring is configured to strip personal data before it leaves our stack. Debugging relies on event data only.
Subprocessors
- SupabaseDatabase, authentication, file storage
- RailwayEngine hosting
- VercelWebsite hosting
- AnthropicBrand-file analysis (API data not used for model training)
- HubSpotMarketing contacts (website forms only)
- SentryError monitoring, PII-stripped
- Cookiebot (Usercentrics)Cookie consent banner
- Google AnalyticsWebsite analytics, after statistics consent
Frequently asked questions
Does The Design Engine see our documents?
No. Your decks and documents are built by your own AI tools in your environment. The Design Engine only sends brand instructions to those tools and keeps the brand kit you give it.
Is our data used to train AI models?
No. The engine runs no AI models. Uploaded brand files are analyzed once through the Anthropic API, and Anthropic does not train on API data.
How do AI tools connect to The Design Engine?
Through the Model Context Protocol (MCP), using OAuth 2.1 with PKCE, dynamic client registration and RFC 8707 resource binding. Legacy API keys are stored only as SHA-256 hashes.
Do you store passwords?
No. Sign-in is OAuth-only through Google, GitHub or Microsoft, so we never receive or store a password.
Do you have SOC 2?
Not yet. SOC 2 is on our roadmap. Architecture and data-flow documentation is available now, and we will complete your security questionnaire.
Which subprocessors do you use?
Supabase for the database, authentication and file storage, Railway for engine hosting, Vercel for website hosting, Anthropic for brand-file analysis, HubSpot for website form contacts, Sentry for error monitoring and Cookiebot (Usercentrics) for cookie consent.
Working through a vendor review?
Architecture and data-flow documentation is available on request, and we'll complete your security questionnaire. Formal certification (SOC 2) is on our roadmap as we scale; the architecture above is why most reviews are short.