PUNK

// trust center · reviewed 2026-07-20

Evidence first. Claims second.

Punk is an adaptive runtime for AI agents. This center separates implemented product controls, customer-configurable deployment choices, unavailable or unverified items, and topics that need contractual review.

Review scope

This is a product posture summary, not a certification, legal commitment, or customer-specific security addendum. Review the actual deployment and configured providers before relying on a control.

// current product controls

Controls implemented in the runtime.

These describe product behavior documented for the current runtime. Some require deployment configuration to be effective.

Scoped execution

Organizations are the tenant boundary. Runs, traces, settings, keys, credentials, workflows, and approvals are tenant-scoped; app, agent, and subject identifiers further attribute activity.

Evidence and rollback

Run evidence includes route explanations and a per-run trace-integrity hash chain. Artifact promotion requires replay and shadow evidence; rollback and quarantine controls are part of the runtime lifecycle.

Credential handling

Tenant API keys, sessions, and one-time tokens are stored as hashes. Stored credential secrets use AES-256-GCM when a valid PUNK_ENCRYPTION_KEY is configured before storage.

Conservative actions

Tools have side-effect levels 0–4. Undeclared tools default to level 3, a user-visible write. Replay and shadow are designed to suppress side effects.

Retention and redaction

Trace retention defaults to 90 days unless a tenant setting or job override applies. Stored trace redaction can deterministically mask string leaves before append.

Operational visibility

Run detail, audit, readiness, integrity, and evidence-packet endpoints support a deployment review. The public status page reports a live health signal.

// customer-configurable

Controls that need an explicit deployment decision.

Setting or choiceWhat it changesReview action
RetentionTenant retention can override the default 90-day sweep window.Confirm retention, backups, and evidence-export needs before production traffic.
Trace redaction and streaming DLPRedaction masks stored trace strings; streaming DLP masks supported sensitive patterns in returned bytes.Enable and test against the customer workload; both affect evidence fidelity or output readability.
Learning and cache postureSemantic cache, model substitution, and cross-tenant aggregate learning are tenant settings.Start in observe mode and do not enable cross-tenant aggregate learning without explicit opt-in.
Provider and credentialsHosted provider configuration or tenant BYOK can serve live traffic.Review each configured provider's own data, retention, training, DPA, and subprocessor terms.
Side-effect policyPolicies and approvals govern tool actions.Keep level 3 and 4 tools approval-required or denied for an initial pilot.

// unavailable or unverified

Do not treat these as current commitments.

Certifications

No completed SOC 2, ISO 27001, HIPAA, or other formal compliance attestation is claimed here.

Enterprise identity

SSO, SAML, and SCIM are not claimed without separate implementation and evidence.

Contractual promises

No public SLA, incident-notification SLA, data-residency promise, BAA, customer-managed key support, or database-level row-security commitment is offered here.

Encryption scope

Credential encryption is documented; database, disk, backup, provider, and edge-encryption posture remains deployment-specific evidence.

Legal workflow

A public DPA, BAA, or signed customer agreement is not represented by this site. Those requests require separate review.

Bring the deployment evidence.

For an enterprise review, start with a readiness receipt, sample evidence packet, relevant policies, tenant settings, enabled connectors, provider-key source, and backup or incident evidence.