Skip to content

Pre-Launch Compliance

AI Model Card

ContentPulse AI Model Card — EU AI Act Article 50 transparency + California AI Executive Order disclosures

Sections

Product Description

Product Name

ContentPulse by Aurora AI Solutions Studio UG

Version & Classification Date

Version 1.1 (Final-product reality) | Classification Date: May 24, 2026

Aurora Operator (AI Agent)

ContentPulse embeds the Aurora Operator — a named AI agent that runs structured skills (create-pitch, create-campaign,create-ad-copy, plus the cross-product draft-renewal-pitch,run-expansion-play, draft-winback-campaign) under your own Bring-Your-Own-Key (BYOK) LLM credential (Anthropic Claude / OpenAI GPT / Google Gemini). Operator output streams into a review slide-over with an Article 50 disclosure banner; you accept or reject before anything reaches the publishing queue. Agent loop is capped at 5 tool calls per invocation and ~1,500 output tokens per skill.

Closed-loop signal pipeline (CTP ↔ CP)

ContentPulse and ClientPulse share a unified signals pipeline (20+ kinds). A signal generated in CTP (e.g. ad_burn_no_results,content_velocity_drop) can trigger Operator skills in either product. All signals remain inside your Aurora workspace (Supabase EU Frankfurt) under row-level security and are never shared across accounts.

EU AI Act Article 50 transparency commitment

Every generated piece carries: (a) a visible “AI-assisted” or “Generated by ContentPulse” surface label, and (b) machine-readable provenance — HTML<meta name="ai-generated">tags on rendered output pages (e.g. the public share page /share/[token]), C2PA-compatible manifest on media outputs (image / video / audio — pipeline shipping by Oct 2026 per the compliance roadmap), and a JSON sidecar for export bundles where the destination platform does not preserve HTML metadata. Customers re-distributing CTP output should preserve these markers per Terms §10.1.

What It Does

ContentPulse is the content-production half of the Aurora agency operating system, built for 5-50 person marketing agencies. It ingests long-form input (audio, video, transcripts, URLs) and generates platform-native variants in per-client voice — LinkedIn posts, X threads, blog posts, podcast scripts, and more. Every generated piece is held in a human review queue and requires explicit agency approval before publishing. Voice profiles are learned per-client from engagement metrics; no demographic data is collected.

AI Systems Used

SystemFunctionProvider
Content GenerationGenerates platform-native content variants from a single source piece; voice-profile awareAnthropic Claude Sonnet 4.6
Content Multiplication EngineMaps source segments to target platforms; computes content multiplication scoreAnthropic Claude Sonnet 4.6
Voice Profile LearningPer-client voice profile built from agency content history + engagement signalsAnthropic Claude Sonnet 4.6
A+ Ghostwriting (Write-as-Client)Suite-only mode that generates content using a client-specific voice profileAnthropic Claude Sonnet 4.6
Audio TranscriptionConverts uploaded audio (MP3 / WAV / podcast episodes) to text with speaker diarizationDeepgram Nova-3
Video Multimodal (Roadmap)Transcript + visual semantics from MP4 / MOV uploads; ships in Sprint 7.8Google Gemini Files API
Engagement ReadersPulls engagement events (impressions, reactions, comments) from publishing platformsYouTube / X / Apple Podcasts (Direct APIs) + Manual URL ingest for LinkedIn

Model Configuration

Primary Model: Anthropic Claude Sonnet 4.6 (claude-sonnet-4-6)

Transcription: Deepgram Nova-3 (~$0.26/hr, diarization included)

Video (roadmap): Google Gemini Files API

Temperature (Generation): 0.7 (creative)

Temperature (Voice Profile Build): 0.3 (deterministic)

Data Processed

Processed Data Types

  • • Agency-uploaded media (audio, video, transcripts, URLs) processed via Deepgram / Gemini and stored in Supabase EU
  • • Agency content history + voice-profile artifacts (per-client when on Suite)
  • • Engagement metrics from publishing platforms (impressions, reactions, comments)
  • • Agency owner email + account metadata for communications

NOT Collected

  • • PII of an agency's end-clients (only what the agency explicitly uploads)
  • • Biometric data, demographic data, or protected-class information
  • • Health, employment, or financial-services records

Risk Classification

FrameworkClassificationNotes
EU AI Act — Article 50 transparencyLimited RiskContentPulse is a generative-AI content surface. Every output is surfaced with a visible “Generated by ContentPulse” label + machine-readable <meta name="ai-generated"> tag. C2PA media-provenance pipeline targeted for Oct 2026. Enforcement: 2 December 2026 (3-month grace cut per the May 7 2026 Digital Omnibus).
EU AI Act — Annex III (high-risk)Out of scopeContentPulse is content generation — not in any Annex III enumerated domain (biometrics, critical infra, education, employment, essential services, law enforcement, migration, justice). Annex III obligations are also postponed to 2 December 2027 per the May 7 2026 Digital Omnibus.
GDPR / DSGVOCompliant postureEU data residency (Supabase eu-central-1 Frankfurt, Vercel fra1, Resend AWS eu-west-1, Stripe Payments Europe Frankfurt), data minimisation, AES-256 at rest, TLS 1.3 in transit, RLS on every table, Art 22 HITL safeguard (Kanban review queue, no auto-publish), Art 17 erasure endpoint, DSAR endpoint roadmap targeting June 2026.
California SB 942 (AI Transparency)Out of scopeSB 942 covers generative AI providers with >1M monthly visitors in CA. Aurora is well under this threshold. Re-verify at ~500k MAU.
California SB 243 (Companion Chatbot)Out of scopeAurora Operator is a structured work-tool agent, not a companion chatbot providing ongoing emotional/social interaction.
Colorado SB 26-189Out of scopeThe original Colorado AI Act (SB 24-205) was repealed and replaced by SB 26-189 (signed 14 May 2026, effective 1 January 2027). SB 189 covers ADMT in employment, housing, lending, insurance, healthcare, education, essential government services — ContentPulse is in none of these.
UK GDPR + Data Use and Access Act 2025CompliantDUAA 2025 (commenced 5 Feb 2026) — ContentPulse outputs are HITL-gated; the Kanban review queue is the operative safeguard.

Human-in-the-Loop Controls

Every AI-generated piece is held in the agency's review queue. No piece reaches a publishing platform without explicit human approval.

1

Review Queue

All generated pieces — posts, threads, blog drafts, scripts — appear in /queue labeled “Generated by ContentPulse” pending review

2

Per-Piece Edit + Approve

Agency owner can edit, regenerate, approve, or reject every piece individually before any publishing action

3

Manual Publish Path

ContentPulse does not auto-publish. Agencies copy approved content into the publishing platform of their choice (or use the platform's native compose URL)

No Autonomous Publishing

Zero generated content is published to any external platform without explicit human approval and a manual publish action.

Transparency Measures

Article 50 Disclosure on Every Surface

A “Generated by ContentPulse” label is shown on the public share page (/share/[token]), the per-piece detail in /queue, and the composer output in /repurpose

Source Lineage Display

Every generated piece shows the source segment it was derived from (Content Map sidebar in the composer + per-piece source-segment panel)

Audit Logging

All generations + voice-profile updates are logged with input data, model version, and timestamp

Public Model Card

This page is publicly accessible and linked from the ContentPulse landing footer, the Aurora site footer, and the in-app footer.

Aurora Operator Article 50 banner

Whenever you open the Operator slide-over, a persistent banner displays: “Aurora Operator is an AI assistant. Output may need human review before use.” This satisfies EU AI Act Article 50(1) (AI-system disclosure to natural persons), effective 2 December 2026.

Machine-readable provenance on every generated piece

Public share viewer (/share/[token]) emits <meta name="ai-generated"> + <meta name="ai-disclosure" content="EU-AI-Act-Article-50"> in the document head. JSON export bundles carry an aurora_provenance sidecar field with skill id, version, BYOK provider, and timestamp. C2PA manifests on rendered media (image / video / audio) target Oct 2026.

Bias & Fairness

Voice-Learning Foundation

Per-client voice profiles are learned from the agency's own engagement metrics (impressions, reactions, comments) — never from demographic, racial, gender, or protected-class data.

Generation Prompt Review

Generation prompts are reviewed for fairness before deployment. Refusal classes (see Content Policy) cover political disinformation, fabricated PII, and impersonation of named individuals without consent.

Provider-Level Safety

Anthropic Claude Sonnet inherits Anthropic's constitutional AI safety training. Deepgram Nova-3 transcription is reviewed for diarization-quality bias on accented speech.

Future Work (Post-Launch)

Synthetic-test cohorts for measuring fairness across client segments are planned for Launch+30 → +60.

Limitations & Known Issues

Generation Quality: Output quality depends on source-input quality. Short, low-context inputs yield lower-fidelity variants.

Voice Profile Maturity: Per-client voice profiles need a minimum of 5 published-and-engaged pieces before recursive rebuilds kick in.

Transcription Accuracy: Depends on audio quality, speaker diarization, accents, and background noise.

Language Support: Voice profile + generation are English-first in v1.0; other languages supported on a best-effort basis.

LinkedIn engagement: LinkedIn does not expose engagement metrics via public API. Agencies can paste the public post URL on each piece in the queue to log engagement manually.

Contact & Review

Contact for Questions

hello@helloaurora.ai

Review Cycle

Quarterly assessment of model performance, bias indicators, and regulatory changes

Next review: July 2026

Regulatory Monitoring

Active monitoring for:

  • • EU AI Act Article 50 (effective Aug 2, 2026 — compliance target)
  • • California AI Executive Order + CA AI Transparency Act (compliance target)
  • • Colorado AI Act (effective June 30, 2026 — case-by-case)
  • • UK GDPR Article 22 + ICO AI Guidance

ContentPulse

The operating system for marketing agencies — per-client voice, approval workflow, engagement loop.

Legal

Aurora AI Solutions Studio UG (haftungsbeschränkt)

Contact: hello@helloaurora.ai

© 2026 Aurora AI Solutions Studio UG. All rights reserved.

Model Card Classification Date: May 24, 2026 (v1.1)