LLM governance / policy control planeCompliance

Export Policy Gateway audit logs to Amazon S3

Store Policy Gateway audit logs in S3 for durable retention, batch analytics, and compliance archives.

Archive Policy Gateway audit logs in S3 so compliance teams can retain events for long-term investigations.

Exports are available on enterprise plans; contact help@abliteration.ai to enable a log export sink.

Updated Jan 16, 2026Compliance integrations

Quick start

Example request
{
  "destination": "s3",
  "bucket": "ai-audit-logs",
  "prefix": "policy-gateway/",
  "format": "jsonl"
}

Service notes

  • Pricing model: Usage-based pricing (~$5 per 1M tokens) billed on total tokens (input + output). See the API pricing page for current plans.
  • Data retention: No prompt/output retention by default. Operational telemetry (token counts, timestamps, error codes) is retained for billing and reliability.
  • Compatibility: OpenAI-style /v1/chat/completions request and response format with a base URL switch.
  • Latency: Depends on model size, prompt length, and load. Streaming reduces time-to-first-token.
  • Throughput: Team plans include priority throughput. Actual throughput varies with demand.
  • Rate limits: Limits vary by plan and load. Handle 429s with backoff and respect any Retry-After header.

What gets exported

#

Policy Gateway audit logs include consistent decision metadata for compliance reviews.

  • policy_id, decision, effective_decision, reason_code
  • policy_user, project_id, policy_target for audit trails
  • rollout_mode, enforced for rollout tracking
  • triggered_categories, allowlist_hits, denylist_hits
  • model, created_at, and optional data classification tags

Export configuration

#

Write audit logs as JSON lines files in S3.

  • Create a dedicated bucket and prefix for audit logs.
  • Partition by date to keep queries efficient.
  • Encrypt objects with SSE-S3 or SSE-KMS for compliance requirements.

Recommended S3 object layout

#

Partition by date so Athena and other tools can query efficiently.

Recommended S3 object layout
s3://ai-audit-logs/policy-gateway/date=2026-01-16/part-00001.jsonl

Sample JSON line

#

Each line is a single audit log event.

Sample JSON line
{"policy_id":"support-guardrails","decision":"rewrite","effective_decision":"rewrite","reason_code":"REWRITE","policy_user":"user-12345","project_id":"support-bot","policy_target":"support-bot","rollout_mode":"enforced","enforced":true,"triggered_categories":["self-harm/intent"],"allowlist_hits":["refund policy"],"denylist_hits":[],"model":"abliterated-model","created_at":"2026-01-16T18:22:11Z"}

Verification checklist

#
  • Confirm new objects appear in the expected date prefix.
  • Run an Athena query filtering on policy_id and decision.
  • Validate object encryption and retention policies.

Common errors & fixes

  • 401 Unauthorized: Check that your API key is set and sent as a Bearer token.
  • 404 Not Found: Make sure the base URL ends with /v1 and you call /chat/completions.
  • 400 Bad Request: Verify the model id and that messages are an array of { role, content } objects.
  • 429 Rate limit: Back off and retry. Use the Retry-After header for pacing.

Related links