AI Disclosure
Effective Date: April 1, 2026
1. AI-Powered Readings
CelestKin uses artificial intelligence to generate personalized astrological readings. Specifically, we use Claude (developed by Anthropic) via Amazon Web Services Bedrock to interpret your chart data and produce written readings. No human astrologer reviews or edits individual readings.
Model in production: Our current primary model is Anthropic Claude Opus 4.6 (model ID us.anthropic.claude-opus-4-6-v1), accessed via AWS Bedrock with extended-thinking reasoning enabled for most reading tiers. Shorter, lower-cost readings may use a smaller Claude tier (e.g. Haiku or Sonnet) selected per-tier in our backend. As Anthropic releases newer versions, we may transition to them without advance notice; the transition is transparent to you and does not change the types of data processed.
1a. Where AI Is — and Is Not — Used
Where AI is used: chart interpretation, reading generation, compatibility narrative, cosmic digest writing, and body-reading analysis.
Where AI is NOT used: chart computation (deterministic math against the Swiss Ephemeris and Lahiri/KP/Four-Pillars rule sets), crisis-resource content (static, human-written referrals for mental-health or safety topics), legal disclaimers, and the flagging of medical, legal, or financial advice. Those flows never call the AI and cannot be influenced by prompt content.
2. How It Works
When you request a reading:
1. Your birth data (name, date, time, location) is used to compute chart positions mathematically on our servers.
2. The computed chart data (planetary positions, house placements, aspects) is assembled into a structured prompt along with tradition-specific reference guides.
3. This prompt is sent to Claude AI (via AWS Bedrock) which generates a personalized written interpretation.
4. The AI response is returned to you as your reading.
The AI has access to your chart data for the specific reading request. It does not retain or learn from your individual data between sessions.
3. Data Sent to AI
The following data is included in AI prompts:
• Name (for personalization)
• Birth date, time, and location
• Computed planetary positions and chart data
• Selected question or reading type
• Tradition-specific reference materials (these are static guides, not your data)
We do NOT send: your email address, account ID, payment information, reading history, or data from other users (except in compatibility readings where both profiles' chart data is included).
4. AI Limitations
• AI-generated readings are non-deterministic — requesting the same reading twice may produce different text
• The AI may produce inaccuracies, hallucinations, or culturally insensitive content
• Readings reflect pattern matching on training data, not genuine astrological expertise or supernatural insight
• The AI cannot verify or validate astrological claims — it presents traditional interpretive frameworks
• Extended thinking (reasoning) is used for deeper analysis but does not guarantee correctness
5. No Training on Your Data
AWS Bedrock does not use your prompts or responses to train foundation models. Your data is processed for the sole purpose of generating your reading and is not retained by the AI provider for model improvement. See AWS Bedrock's data privacy documentation for details.
6. Human Oversight
While individual readings are not reviewed, CelestKin's development team periodically audits reading quality, reviews prompt engineering, and monitors for harmful or inappropriate outputs. If you receive a reading that contains harmful, offensive, or clearly erroneous content, please report it to us.
7. Contact
AI-related questions: [email protected]