Sprint 4 Compliance
ClientPulse AI Model Card - California AI Executive Order Transparency Requirements
Sections
Product Name
ClientPulse by Aurora AI Solutions Studio UG
Version & Classification Date
Version 1.0 (Beta) | Classification Date: April 10, 2026
What It Does
ClientPulse is an AI-powered Client Health Intelligence platform that combines financial, relationship, delivery, and engagement signals into a composite Client Health Score (0–100). The system predicts client churn, identifies upsell opportunities, and generates AI-recommended action plans—all requiring explicit human approval before any client-facing communication.
| Agent | Function | Data Source |
|---|---|---|
| Financial Signal Agent | Analyzes Stripe invoicing data; calculates financial health sub-score (30% weight) | Stripe API |
| Meeting Intelligence Agent | Transcription + extraction: sentiment (1–10), action items, scope changes, escalations | Whisper + Claude Sonnet |
| Health Scoring Agent | Composite 0–100 score from Financial (30%), Relationship (30%), Delivery (25%), Engagement (15%) | All signals |
| Churn Prediction Agent | Probability (0–100%) per client based on multi-signal pattern matching | Claude Sonnet |
| Upsell Detection Agent | Transcript analysis for expansion signals and cross-sell opportunities | Claude Sonnet |
| Monday Brief Agent | Weekly summary generation with action proposals (requires approval) | Claude Sonnet |
| Action Proposal Engine | Auto-drafts save plans and retention actions for at-risk clients | Claude Sonnet |
Model Configuration
Primary Model: Anthropic Claude Sonnet (analysis, scoring, prediction)
Transcription: OpenAI Whisper API
Temperature (Scoring/Prediction): 0.3 (deterministic)
Temperature (Brief Generation): 0.7 (creative)
Processed Data Types
NOT Collected
| Framework | Classification | Notes |
|---|---|---|
| EU AI Act | Limited Risk (Article 52) | AI-driven scoring requires transparency obligations; not high-risk but above minimal |
| California AI Executive Order | Moderate Risk | Health Score + Churn Prediction are AI assessments of business relationships; requires transparency & bias documentation |
| Colorado AI Act | Potentially Applicable | Effective June 30, 2026. Churn-based action proposals could constitute “consequential decisions.” Bias assessment required. |
| AMERICA AI Act (Draft) | Moderate Risk | Scoring system with measurable business impact |
| GDPR / EU Data Protection | Compliant | EU hosting (Frankfurt), data minimization, right-to-delete |
All automated outbound actions are queued in an approval system requiring explicit human authorization:
Action Queuing
Monday Brief emails, churn alerts, save plans, check-in invites are drafted and held for review
Human Approval Required
Agency owner must explicitly approve each action before it reaches client
Optional Auto-Approve
Per-action-type auto-approve toggle available once trust is established
No Autonomous Communication
Zero client-facing outbound communication is sent without explicit human approval in this sprint
AI-Generated Disclosures
All health scores clearly labeled as “AI-generated using financial, relationship, and delivery signals”
Signal Source Display
Each score shows which data sources contributed to the final calculation
Audit Logging
All AI-driven recommendations logged with input data, model version, and timestamp
Public Model Card
This page is publicly accessible and linked from Impressum and in-app footer
Algorithm Foundation
Health Score algorithm uses only objective business metrics: payment timeliness, meeting frequency, contract value trends, no demographic or protected-class data
Data Restrictions
No collection or use of demographic, racial, gender, or protected-class information
Bias Impact Assessment
Conducted per Colorado AI Act requirements (see /docs/BIAS-IMPACT-ASSESSMENT.md)
Review Cadence
Quarterly evaluation; A3 + D3 evaluation tests serve as regulatory canaries
Future Work (Sprint 5)
Synthetic test cohort evaluation planned to measure fairness across client segments
Health Score Accuracy: Depends on data completeness; clients with <3 meetings and no Stripe connection will have lower-confidence scores
Churn Prediction: Requires minimum 30 days of history per client
Transcription Quality: Depends on audio quality and speaker diarization accuracy
Language Support: Sentiment analysis is English-only in v1.0
Recursive Learning: Self-calibration requires 50+ client outcomes—not available until Sprint 6
Contact for Questions
Review Cycle
Quarterly assessment of model performance, bias indicators, and regulatory changes
Next review: July 2026
Regulatory Monitoring
Active monitoring for: