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
| System | Function | Provider |
|---|---|---|
| Content Generation | Generates platform-native content variants from a single source piece; voice-profile aware | Anthropic Claude Sonnet 4.6 |
| Content Multiplication Engine | Maps source segments to target platforms; computes content multiplication score | Anthropic Claude Sonnet 4.6 |
| Voice Profile Learning | Per-client voice profile built from agency content history + engagement signals | Anthropic Claude Sonnet 4.6 |
| A+ Ghostwriting (Write-as-Client) | Suite-only mode that generates content using a client-specific voice profile | Anthropic Claude Sonnet 4.6 |
| Audio Transcription | Converts uploaded audio (MP3 / WAV / podcast episodes) to text with speaker diarization | Deepgram Nova-3 |
| Video Multimodal (Roadmap) | Transcript + visual semantics from MP4 / MOV uploads; ships in Sprint 7.8 | Google Gemini Files API |
| Engagement Readers | Pulls engagement events (impressions, reactions, comments) from publishing platforms | YouTube / 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
| Framework | Classification | Notes |
|---|---|---|
| EU AI Act — Article 50 transparency | Limited Risk | ContentPulse 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 scope | ContentPulse 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 / DSGVO | Compliant posture | EU 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 scope | SB 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 scope | Aurora Operator is a structured work-tool agent, not a companion chatbot providing ongoing emotional/social interaction. |
| Colorado SB 26-189 | Out of scope | The 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 2025 | Compliant | DUAA 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.
Review Queue
All generated pieces — posts, threads, blog drafts, scripts — appear in /queue labeled “Generated by ContentPulse” pending review
Per-Piece Edit + Approve
Agency owner can edit, regenerate, approve, or reject every piece individually before any publishing action
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
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