Promptless Evidence

Promptless evidence records governance decisions without storing prompt text. It gives operators and auditors proof of policy behavior through safe metadata, identifiers, statuses, counts, approvals, exports, lineage, and replay jobs.

Use promptless evidence when the organization needs accountability for AI and endpoint policy decisions but should not retain raw prompts, completions, lookup values, matched PII, or backend responses in the evidence system.

Evidence APIs

APIPurpose
/api/v1/llm/governance_exportsCreate and retrieve safe export artifacts.
/api/v1/llm/governance_lineageRecord safe lineage events for policy decisions and artifacts.
/api/v1/llm/governance_replay_jobsTrack replay jobs for policy and evidence validation.
/api/v1/llm/governance_feature_records/{feature_kind}Store feature-specific records such as simulations, approvals, DLP scans, evals, and dashboard views.

Feature Records

Supported feature kinds include:

Feature kindUse it for
policy_simulationPreview stored policies against safe request metadata.
approval_requestCapture human approval or attestation state.
evidence_pack_templateDefine reusable evidence export templates.
entitlement_sync_jobTrack IdP, SCIM, or import sync jobs.
resource_controlStore resource labels and allowed-group controls.
model_eval_jobTrack model evaluation or drift jobs.
data_quality_checkTrack endpoint or template quality checks.
dashboard_viewStore curated dashboard views.
dlp_scanStore DLP scan metadata and safe counts.

Evidence Model

Evidence fieldExample
Subject identifiersUser UUID, agent UUID, auth group UUID, gateway key UUID.
Resource identifiersEndpoint UUID, template UUID, route alias, model/provider ID.
Policy identifiersProfile UUID, binding UUID, boundary UUID, policy version.
Decision metadataAllow, audit, redact, block, skipped, error, approval pending.
CountsMatch counts, term counts, route counts, token counts, row counts.
LineageExport ID, replay job ID, approval record ID, feature record ID.

Promptless evidence is intentionally reconstructive rather than verbatim. It should let an auditor answer which policy applied, what action Eden took, and which safe artifacts prove it, without needing sensitive content.

Review Workflows

Evidence records support policy simulations before rollout, approval requests for sensitive actions, export packets for reviewers, lineage records tying decisions to artifacts, and replay jobs for validating updated policy against safe historical metadata.

Safety

Evidence records must remain promptless. Store identifiers, policy versions, statuses, counts, and safe metadata. Do not store raw prompts, raw lookup values, raw matched PII terms, or raw provider responses.

Last updated: July 10, 2026