🔒 Security & Confidentiality Architecture
For enterprise business owners, chief financial officers, and agency leads, data privacy is non-negotiable. AMBA was engineered from day one on a Local-First, Privacy-First paradigm.
🛡️ Core Security Tenets
1. Zero Cloud File Storage
Your documents, spreadsheets, analytical SQLite tables, and vector embeddings remain on your laptop. AMBA has no cloud backend, no remote database, and no server collecting telemetry or copies of your work.
2. Ephemeral Frontier LLM Reasoning Only
When you run a task, AMBA extracts only the necessary contextual text snippets or SQL query results required to answer your prompt and sends them via outbound HTTPS to your chosen LLM provider (OpenAI, Anthropic, or Google).
- Your enterprise data is processed in-memory by the LLM provider under enterprise API privacy terms.
- It is never used to train public models.
3. Air-Gapped Financial Security Matrix
In sensitive domains like Invoice Reconciliation, P&L Variance, and Payroll Audit:
allowInternetis turned OFF by default.- Even if an LLM is prompted or tricked into attempting a web call, AMBA's Rust policy engine enforces a strict sandbox boundary, completely severing outbound HTTP requests from that project.
4. Hardware-Encrypted OS Keychain
- API keys are never stored in
.envfiles, git repositories, or plaintext files. - All secrets are delegated to Apple Keychain or Windows Credential Manager.
5. Deterministic Math Defense (Anti-Hallucination)
- LLMs are notoriously prone to math errors and number hallucination.
- AMBA forbids mental arithmetic in financial templates. All calculations are executed deterministically through standard SQLite queries over local tables.