Privacy Policy

When you use ceadr, we process the following data:

• Document content from sources you connect (Google Drive, Notion, Confluence, Slack, GitHub, Jira) or files you upload. To make your knowledge queryable by AI agents, ceadr is a persistent knowledge platform: document content is split into chunks, embedded as vectors, and stored so it can be retrieved and cited. A durable knowledge graph (entities, relationships, and cited excerpts) is built from it. Stored content is encrypted at rest and isolated to your workspace.
• Connection credentials. Connections you make in the ceadr app are brokered by Nango: ceadr stores a connection reference rather than your provider access token, and fetches the access token from Nango when it needs to reach your source. An older direct connection route still exists; a connection made through it keeps the provider's access token, and a refresh token where the provider issues one, encrypted in our own cache for 24 hours after it was last saved.
• Account and authentication data via our authentication provider, Clerk (user identifier, email, and session metadata) to sign you in and associate your workspaces.
• Analysis results (scores, extracted knowledge, contradictions, and metadata) stored in your workspace so the dashboards, ontology, and agent API can use them.
• Document metadata such as filenames, titles, word counts, and author names as provided by source connectors.
• Error reports from your browser, only if you allow error reporting in the cookie banner. When a page fails, we record the error message and technical trace, the page address, your browser and operating system, your window size, and the app version, so we can find and fix the fault. When you are signed in, a report can be linked to your account and workspace and noted in your workspace activity feed.

• Score documents for quality, completeness, and AI readiness
• Detect contradictions across your knowledge base
• Identify gaps against industry templates
• Build knowledge ontologies (entity and relationship extraction)
• Serve cited answers to the AI agents you connect to your workspace
• Generate audit reports and executive summaries

We do not sell your data, and we do not use your content to train our own models. Content sent to Anthropic's Claude API is not used by Anthropic to train models.

ceadr engages the following sub-processors to deliver the service. Each receives only the data it needs for its stated purpose. We give 30 days notice before adding a new sub-processor. To object, email julian@ceadr.ai.

• Anthropic

  policy

  Claude API for scoring, contradiction detection, ontology, summaries. API inputs are not used to train models.

  United States

• AssemblyAI

  policy

  Audio transcription with speaker diarization and chapter summaries.

  United States

• OpenAI

  policy

  Optional fallback path for audio transcription via Whisper. The MCP deployment helper also references OpenAI as one of the supported agent endpoints.

  United States

• Voyage AI

  policy

  Embedding model for document chunks (semantic search and contradiction pairing).

  United States

• Nango

  policy

  OAuth brokerage and proxied API access to your connected SaaS providers (Google, Notion, Atlassian, Slack, GitHub, Jira).

  United States

• Clerk

  policy

  Authentication and session management. Stores user identifier, email, and session metadata.

  United States

• Resend

  policy

  Transactional email (workspace invites, agent notifications, writeback confirmations).

  United States

• PostHog

  policy

  Product analytics and pageview capture. Only loaded when the visitor opts in via the cookie banner.

  United States

• Sentry

  policy

  Error and performance reporting. When our servers hit an error, and for a sample of the requests they handle without one, they send Sentry technical details of the request, which can include the page address, your browser and operating system, your workspace, and the names of files involved. These details can identify you. In your browser, Sentry runs only if you opt in through the cookie banner.

  European Union (Germany)

• Google (Calendar Appointments)

  policy

  Booking links for the demo / discovery call flow on the marketing site. Calendar bookings are scheduled directly with Google.

  United States, multi-region edge

• Vercel

  policy

  Hosting for the ceadr.ai web application. Receives all frontend traffic and edge logs.

  United States, multi-region edge

• Railway

  policy

  Hosting for the ceadr API engine and worker processes.

  United States

• Supabase

  policy

  Managed Postgres database and file storage. Holds your stored data, including document text split into chunks with vector embeddings, the knowledge graph, analysis results, agent queries and answers, workspace and member records, the audit log, uploaded files, copies of some original source files, data export bundles, and contact details submitted on our website.

  European Union (Stockholm, Sweden)

When you connect external sources, your connection is used to access data from Google, Notion, Atlassian, Slack, or GitHub on your behalf. We only read data unless you explicitly approve a writeback action.

In your browser, analytics (PostHog) and error reporting (Sentry, and our own error log) run only when you opt in through the cookie banner. You can revisit your choice at any time: Manage cookie preferences. Our servers report the errors they hit to Sentry whatever you choose, with the request details the Sentry entry above describes.

• Document content and derived knowledge: Chunks, embeddings, extracted entities, and cited excerpts are stored for as long as your workspace is active, so agents can query your knowledge with citations. They are deleted when you erase the underlying data or delete your workspace.
• Analysis results: Stored for the life of your workspace and removed on erasure or workspace deletion.
• Connection credentials: For connections made in the app, held by Nango; revoking the connection, or deleting your workspace, removes ceadr's access. Tokens saved through the older direct route leave our cache 24 hours after they were last saved, and you can revoke them sooner in your account settings with the provider.
• Account data: Retained while your account is active (managed via Clerk).
• Error reports: Kept for troubleshooting for 90 days, then deleted automatically by a daily cleanup. If you ask us to erase your data, we remove the error message, technical trace, page address, browser details and link to your account from any report that is linked to your account or whose message or page address contains your email address. The record that an error happened, and when, stays until the cleanup deletes it. If you have already closed your account, reports linked only to that account cannot be found this way and are deleted by the cleanup instead. A report sent while you were working in a workspace also adds a note to that workspace's activity feed, naming the page that failed with any email address or document name masked, and without your browser details; the cleanup deletes the note along with the report. Notes made before this change can still include your browser details, an address or a document name, until the cleanup deletes them.

To exercise your data subject rights under GDPR Articles 15 to 22 (access, rectification, erasure, portability, restriction, objection), email julian@ceadr.ai. We respond within 30 days. Workspace admins can also open export and erasure requests directly from the workspace settings.

CCPA and UK DPA 2018 requests follow the same path.

We use strictly necessary cookies to keep you signed in and maintain your session, including cookies set by our authentication provider, Clerk. We do not use advertising or cross site tracking cookies. In your browser, we use product analytics (PostHog) and error reporting (Sentry and our own error log) only when you opt in through the cookie banner (see section 3 to change or withdraw that choice).

Document content is processed by Anthropic's Claude AI, which operates in the United States. Our infrastructure providers (see the sub-processor table above) and OAuth connections to Google, Notion, Atlassian, Slack, and GitHub may also involve data transfer to US based servers. These transfers are governed by the respective providers' data processing agreements.

• Stored content is encrypted at rest and isolated per workspace by database row-level security
• Secrets and connection credentials are encrypted at rest
• Session cookies are HttpOnly and Secure
• Authentication on every endpoint (Clerk sessions for the app, bearer tokens for the agent API)
• Rate limiting on sensitive operations
• Every privileged action is recorded in a tamper-evident, append-only audit log

For privacy inquiries or to exercise your data rights, email julian@ceadr.ai.