Trust Center

1. How MinuteSmith Works

MinuteSmith is an AI-assisted meeting-minutes service for HOA, condo, and nonprofit boards. Operators upload or record meetings, the service transcribes them, generates draft minutes, supports a structured review-and-approve workflow, and stores the approved record alongside related documents and action items.

The service is operated by JES Ventures LLC, a US limited liability company. The application is hosted on Railway. Data and authentication run on Supabase (managed Postgres + object storage). AI providers are Anthropic(Claude API) and OpenAI (Whisper transcription, text-embedding-3-small for retrieval).

2. How Ask AI Works

Ask AI is a retrieval-augmented generation (RAG) feature. It does not query a general AI with the user's question alone — it searches the user's own meeting history first, then asks Claude to synthesize an answer using only that context.

Detailed step-by-step explanation: /how-ask-ai-works.

3. What Leaves MinuteSmith

4. What Stays Inside MinuteSmith

• Customer accounts, board configurations, member rosters, and billing state.
• Approved minutes, raw transcripts, raw notes, agenda content, action items, and motions.
• Meeting recordings and uploaded board documents (in encrypted-at-rest object storage with no public URLs).
• Embeddings (numeric vectors) for retrieval. Stored in Postgres with the same board-scope rules.
• Audit logs for sensitive actions (document downloads, exports, member changes).

5. Board-Scoped Retrieval and Isolation

Cross-board isolation is enforced at two layers:

• Application layer: server-side route handlers fetch the requesting user's board memberships and pass only those board IDs to the search function.
• Database layer: the match_meeting_chunks database function is SECURITY DEFINER and contains a SQL-level board_id = ANY(board_ids) filter. Even if application code passed wrong board IDs, the database would refuse.
• Postgres Row-Level Security policies are enabled on every customer-data table.
• No customer's content is used as system-prompt context for another customer's request.

6. AI Vendor Data Handling

Both Anthropic and OpenAI provide commercial API agreements under which submitted data is not used to train their models. Both vendors retain submitted data for up to 30 days for trust-and-safety review. MinuteSmith is not currently on either vendor's zero-data-retention enterprise plan.

• Anthropic: anthropic.com/legal/privacy
• OpenAI: openai.com/policies/privacy-policy

7. Data Ownership

Customer board content (recordings, transcripts, minutes, action items, documents, embeddings derived from those) belongs to the customer. JES Ventures LLC processes this content to provide the service and does not use it to train any model, sell or rent it to third parties, or use it for marketing other products.

9. Security Controls

• Authentication via Supabase Auth (email + password / magic link). Session invalidation on credential change.
• Postgres Row-Level Security on every customer table.
• Principle of least privilege for service-role access.
• Cron jobs authenticate via shared secret and fail closed in production if misconfigured.
• Audit logging for sensitive actions (document downloads, exports, member changes).
• Strict Content Security Policy with a tighter Report-Only variant in observation mode.
• HSTS, X-Frame-Options DENY, X-Content-Type-Options nosniff, COOP/CORP, Permissions-Policy.

10. Current Limitations (honest)

• The AI redaction layer is currently disabled by default (ENABLE_AI_REDACTION=false). Operators may enable it; we document this as-is.
• Transcript-level encryption migration is scaffolded but not yet operationally active.
• Retention policies may be configured per board; the deletion executor is not running automatically in all environments. Confirm operator configuration before relying on retention windows.
• AI-generated answers can be incorrect. Citations always link back to the source meetings; verify before relying on Ask AI for legal, financial, or compliance decisions.
• MinuteSmith has not undergone a third-party penetration test.

11. What MinuteSmith Does Not Claim

• No SOC 2, ISO 27001, FedRAMP, or HIPAA certification. No HIPAA Business Associate Agreement.
• No end-to-end encryption. AI processing requires server-side decryption.
• No external penetration test on file.
• No zero-data-retention enterprise SKU with AI vendors. The 30-day vendor trust-and-safety retention window applies.
• No claim that AI cannot make mistakes. AI hallucination is a real risk; we mitigate but do not eliminate it.
• No claim that "nothing leaves MinuteSmith." Vendor APIs (Anthropic, OpenAI, Resend, Twilio, Stripe) process specific data described in section 3.