> ## Documentation Index > Fetch the complete documentation index at: https://puzzlet-9ba7bb98.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Security > How AgentMark protects your data: architecture, SSO, encryption, PII masking, retention, and subprocessors ## Architecture The diagram below shows how data moves through AgentMark, the trust boundaries it crosses, and where it rests. Share it with your security team as-is; it lives in the same repository as the product and gets updated with every architecture change. ```mermaid theme={null} flowchart LR subgraph customer["Your infrastructure"] app["Your application
AgentMark SDK with PII masking"] team["Your team
browser, CLI"] end subgraph cloud["AgentMark cloud"] gw["API gateway
Cloudflare Workers
per-app API keys, rate limits"] buffer["Ingestion buffer
Cloudflare Queues"] ch[("ClickHouse Cloud
traces and scores
deleted after 90 days")] pg[("Supabase Postgres
accounts, prompts, RLS")] vault[("Supabase Vault
encrypted provider keys")] dash["Dashboard
Next.js on Vercel"] fly["Managed deployments
Fly Machines"] end gemini["Google Gemini API
Topics feature only"] app -- "TLS 1.2+" --> gw team -- "email/password or SAML SSO" --> dash gw --> buffer --> ch gw --> pg dash --> pg dash -- "retention-scoped queries" --> ch gw -- "dispatches runs" --> fly vault -- "injects keys at build" --> fly ch -- "trace content for clustering" --> gemini ``` Key boundaries: * **PII masking runs inside your process.** Redaction happens before telemetry leaves your infrastructure, so masked values never reach AgentMark. * **The gateway authenticates every request** against per-app, permission-scoped API keys before storing anything. * **Telemetry and application data live in separate stores.** ClickHouse holds traces and scores; Supabase Postgres holds accounts, prompts, and metadata behind row-level security. * **Third-party AI providers only see what a feature needs.** The [subprocessor list](https://www.agentmark.co/subprocessors) names each provider, its purpose, and the data involved. ## Authentication AgentMark supports email/password authentication for all tiers and SAML 2.0 SSO for Team and Enterprise tiers, covering Azure AD, Okta, Google Workspace, and any SAML 2.0-compliant IdP, with domain allowlisting, SSO enforcement, and attribute mapping. See [SSO](/deploy/users-and-access-control#sso) for configuration. ## Data protection ### PII masking Redact sensitive data from traces before it leaves your application. Masking runs in your application process, so it redacts configured attributes before the OTel exporter sends them. ```typescript theme={null} import { AgentMarkSDK, createPiiMasker } from '@agentmark-ai/sdk'; const sdk = new AgentMarkSDK({ apiKey: process.env.AGENTMARK_API_KEY!, appId: process.env.AGENTMARK_APP_ID!, mask: createPiiMasker({ email: true, ssn: true }), }); sdk.initTracing(); ``` For a zero-code option, set `AGENTMARK_HIDE_INPUTS=true` or `AGENTMARK_HIDE_OUTPUTS=true` to redact LLM request inputs or response outputs to `[REDACTED]` before export. The flags cover every content-bearing input and output attribute: the AgentMark SDK keys (such as `agentmark.request.input` and `gen_ai.request.input`), the Vercel AI SDK telemetry keys (`ai.prompt*`, `ai.response*`), and the OTel GenAI message and tool keys. Attributes that carry no message content, such as `gen_ai.request.model`, aren't redacted. The full attribute list is in the [masked attributes reference](/observe/pii-masking#masked-attributes-reference). [Full PII masking docs →](/observe/pii-masking) ### Encryption * **In transit**: all API communication uses TLS 1.2+ (terminated at Cloudflare) * **At rest**: data stored in Supabase (PostgreSQL) and ClickHouse with provider-managed encryption at rest ### Provider API keys AgentMark stores the AI provider keys you configure per environment (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.) as encrypted secrets in the AgentMark vault, using authenticated encryption with a root key held outside the application database. * **Scoped per app:** one app's keys are never visible to another * **Decrypted only when needed:** AgentMark pulls values from the vault and provides them to the serving machine at runtime, or when an authorized Dashboard user explicitly clicks "reveal" on a single variable * **Never written to logs:** request logs and trace exports omit env var values * **Deleted on demand:** removing a variable from the Dashboard deletes the underlying vault secret in the same transaction ### AgentMark API key security AgentMark issues API keys (the keys your code uses to authenticate with AgentMark) with per-tier rate limiting, each scoped to a single app, so no single key grants access across your organization. Each key carries a permission set enforced by the gateway on every request. See [API keys](/deploy/api-keys) for the Dashboard walkthrough and [Users and access control](/deploy/users-and-access-control#api-keys) for role presets and the permission catalog. ### No training on your data AgentMark never uses your data (prompts, traces, datasets, evaluation results, or other telemetry) to train AI or machine learning models. Features that rely on third-party AI providers, such as [trace topics](/observe/topics), run under commercial API terms that prohibit the provider from training on your data. The [Terms](https://www.agentmark.co/terms) and [Privacy Policy](https://www.agentmark.co/privacy) state this commitment, and the [subprocessor list](https://www.agentmark.co/subprocessors) names every AI provider involved. ## Subprocessors AgentMark publishes a versioned list of every subprocessor that handles customer data, including what each one processes and where it runs, at [agentmark.co/subprocessors](https://www.agentmark.co/subprocessors). That page gets updated before a new subprocessor starts handling customer data. ## Data residency If you have regional hosting, on-prem, or data residency requirements, [reach out](mailto:hello@agentmark.co). Enterprise deals can accommodate custom arrangements. ## Data retention Your tier's retention window governs telemetry end to end: how far back the Dashboard and API can query, and when AgentMark physically deletes the underlying data (traces, spans, scores, and offloaded payloads) from its stores. | Tier | Retention | | ---------- | --------------------------------- | | Free | 7 days | | Growth | 90 days | | Team | 90 days | | Enterprise | Configurable, including unlimited | Telemetry older than the window no longer appears in query results, and a daily cleanup job hard-deletes it from storage. The cleanup job measures age from ingestion time, so late-arriving data still gets its full window. Enterprise agreements can tune retention per tenant through an [entitlement override](/deploy/billing-and-usage#entitlement-overrides): longer or unlimited windows for audit needs, or shorter windows to meet data-minimization requirements. [Reach out](mailto:hello@agentmark.co) to configure it. ## Temporary support access When Enterprise customers need hands-on support, AgentMark support engineers can grant themselves temporary read-only access to a tenant's data. Access auto-expires after 24 hours and requires customer permission confirmation. AgentMark records all access grants in an immutable audit log.

Have questions?

Reach out any time: