Hash of the multi-agent topology (no graph contents stored).
Prompt and output text is stored in plaintext. If your prompts or agent outputs contain PII, credit card numbers, or other sensitive data, you must scrub it client-side before traces are sent. The SDK does not redact for you — run your own sanitizer between agent execution and decimalai.send().
Your LLM API keys. Pre-deploy regression checks don’t need them. The Playground stores BYOK keys encrypted at rest, scoped to the workspace, never logged.
Your source code. The SDK never reads files outside the SKILL.md auto-discovery paths (.claude/skills/, .agents/skills/).
Inbound request bodies to the platform API beyond what’s documented as an endpoint payload.
At rest. All data in Postgres is encrypted at rest by Cloud SQL (Google-managed AES-256); object storage is Google Cloud Storage, encrypted at rest by default (AES-256).
In transit. All API traffic uses TLS 1.2+. HSTS is enabled on api.decimal.ai and app.decimal.ai.
Secrets. API keys are stored as bcrypt hashes; only the prefix (dai_sk_..., or dai_pk_... for a public key) is visible after creation. BYOK LLM keys are encrypted with a per-workspace KMS-derived key.
Traces older than your retention period are deleted automatically (rolling, daily). Manifests, skills, and datasets are kept indefinitely so your version history stays intact.
Deletions are hard deletes — the row is removed, not soft-flagged. Backups retain deleted data for up to 30 days for disaster recovery; after that the row is unrecoverable.
Production runs on Google Cloud Platform (Cloud Run + Cloud SQL for PostgreSQL) in region us-central1 (project decimalai-prod). Enterprise customers can request a different GCP region; we’ll spin up an isolated stack and migrate.
If you find a security issue, please do not open a public GitHub issue. Email security@decimal.ai — PGP key available on request. We respond to security reports within 24 hours and follow coordinated disclosure practice. We do not currently run a paid bug bounty.