> ## Documentation Index
> Fetch the complete documentation index at: https://docs.decimal.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Security & Data Handling
> What DecimalAI stores, how it's encrypted, retention policies, and deletion.
This page is the source of truth for what DecimalAI does with your data. For a quick scan, jump to **[Data we store](#data-we-store)** or **[How to delete data](#how-to-delete-data)**.
## Data we store
For each trace ingested via the SDK or API:
| Field | What it contains |
| -------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| `agent_name` | A free-form string you choose in `decimalai.init()`. |
| `user_input` | The text passed into your agent. Stored verbatim. |
| `final_output` | The agent's response. Stored verbatim. |
| `spans` | Per-step span tree (tool calls, retrieval, sub-spans). |
| `llm_calls` | For each LLM invocation: rendered prompt (all messages), completion text, model name, provider, token counts, tool calls, finish reason. |
| `metadata` | Cost estimate, latency, timestamps, manifest hash, and arbitrary tags you attach. |
| `eval_scores` | Any quality or compatibility scores you push or that we compute. |
For each manifest registered via the SDK:
| Field | What it contains |
| --------------------- | ----------------------------------------------------------------------------------------------- |
| `components` | Tool names, tool JSON schemas, model names + params, prompt text, skill names + content hashes. |
| `agent_models_json` | The full model config block from your framework. |
| `graph_topology_hash` | 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()`.
## What we do NOT store
* **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.
## Encryption
* **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 SHA-256 hashes; only the prefix (`dai_sk_...`, or `dai_pk_...` for a public key) is visible after creation. BYOK LLM keys are encrypted at rest with Fernet (AES-128-CBC with an HMAC-SHA256 authentication tag) using a server-managed key.
## Retention
| Plan | Trace retention | Manifest retention | Skill / dataset retention |
| ---------- | --------------- | ------------------ | ------------------------- |
| Free | 14 days | Forever | Forever |
| Core | 30 days | Forever | Forever |
| Pro | 90 days | Forever | Forever |
| Enterprise | 365 days | Forever | Forever |
Traces older than your retention period are deleted automatically (rolling, daily). Manifests, skills, and datasets are kept indefinitely so your version history stays intact.
## How to delete data
| What you want to delete | How |
| ----------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| All traces for an agent | Settings → Agents → click agent → **Purge traces** (admin role) |
| All traces for your org | `DELETE /api/v1/admin/purge/traces` (admin role) — purges all traces, spans, LLM calls, and eval scores for the organization |
| A workspace + everything in it | Settings → Workspaces → **Delete workspace** (workspace admin) |
| All data for a specific user (GDPR) | Email [support@decimal.ai](mailto:support@decimal.ai) — endpoint on the [roadmap](/roadmap) |
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.
## Compliance
DecimalAI is **not currently SOC 2 certified.** The certification is in progress (target: late 2026).
| Item | Status |
| --------------------------------------- | ------------------------------- |
| SOC 2 Type II | In progress (target: late 2026) |
| Security questionnaire (SIG Lite, CAIQ) | Available on request |
| Architecture diagram + threat model | Available on request |
| Penetration test summary | Available on request |
| DPA / standard contractual clauses (EU) | Available on request |
For enterprise procurement reviews, we provide:
* Detailed security questionnaire (SIG Lite, CAIQ)
* Architecture diagram + threat model
* Penetration test summary (available on request)
* DPA / standard contractual clauses for EU data flows
Email [security@decimal.ai](mailto:security@decimal.ai) for the docs package.
## Hosting region
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.
## Reporting a vulnerability
If you find a security issue, please **do not** open a public GitHub issue. Email [security@decimal.ai](mailto:security@decimal.ai) — PGP key available on request. We respond to security reports within 24 hours and follow [coordinated disclosure](https://en.wikipedia.org/wiki/Coordinated_disclosure) practice. We do not currently run a paid bug bounty.