← All integrationsINTEGRATION · COPILOTS AND SAAS AI

Kapālins for AWS CloudTrail

Amazon Bedrock: model invocations, guardrail and agent events recorded by CloudTrail. AWS CloudTrail runs its AI on its own side, where no gateway can sit. Kapālins reads the CloudTrail LookupEvents API, filtered to AI-relevant event sources and puts every event in the same timeline, rules and evidence chain as the rest of your estate.

See it governed liveSetup in four steps

See what no gateway sees

AWS CloudTrail’s own logs are the only record of how its AI is used. Kapālins is where that record meets everything else.

A risky action becomes an incident

The same detection rules as the gateway run on every AWS CloudTrail event, and a finding opens one incident card your SOC already triages.

Evidence an auditor accepts

Each event is attributed to a person and kept with the raw source record, inside the evidence pack.

CloudTrail allows two lookups a second per account; the connector paces itself to that.
AFTER THE FACT

AWS CloudTrail in the same timeline as everything else.

Kapālins reads the CloudTrail LookupEvents API, filtered to AI-relevant event sources every 15 minutes, turns each record into one event shape, and attributes it to a person from your directory.

  • A high-water mark, so nothing is read twice or skipped
  • The raw record kept exactly as it arrived
  • Source label "AWS CloudTrail" on every row
Kapālins Logs: one timeline of AI requests and policy verdicts
The Kapālins timeline in the pilot tenant on production. Personal addresses masked.
DETECT AND ACT

A finding, not a log line.

Rule families and custom checks run on AWS CloudTrail events after the fact. What matters opens an incident with the person, the rule and the evidence, and is pushed to your SIEM or ITSM.

  • Mute, risk-accept or escalate from the card
  • Notification clocks start when an incident is reportable
Kapālins incidents: sensitive data stopped before it left
Incidents in the pilot tenant: sensitive data stopped before it reached an AI service. Personal addresses masked.
PROVE

Counted in the number the board reads.

AWS CloudTrail activity feeds the AI Trust Index and the compliance obligations it proves, so it is governed rather than exempted.

  • Obligation, control, artifact, verification in one chain
Kapālins AI Trust Index KPI strip
The AI Trust Index in the pilot tenant: what the estate did this window, at a glance.
Setup

Four steps.

  1. Grant a read credentialAn IAM credential allowed to call cloudtrail:LookupEvents.
  2. Paste it in KapālinsIntegrations › AWS CloudTrail › Create. A live read validates it before anything is stored.
  3. Watch the first sweepLogs shows each event with its source, the person and the rules that fired.
  4. Tune the rulesMute, risk-accept or escalate from the incident card.
Request a briefing

See AWS CloudTrail governed in thirty minutes.

Bring the person who holds the credential. We connect it live and watch the first events land.

Request a briefing All integrations
FAQ

Questions buyers ask.

Does Kapālins change anything in AWS CloudTrail?

No. The connector reads with the credential you grant, or receives what the platform pushes. Nothing is written back.

How current is the timeline?

Pulled sources are swept every 15 minutes; pushed sources arrive as they happen. Each window overlaps the last, so a late record is caught next time.

Where is the credential kept?

Encrypted at rest with AES-256-GCM, decrypted only inside the ingestion job and the connect-time validation, never returned to the browser or written to a log.