How we use AI

What model

Anthropic's Claude (the Opus and Sonnet tiers, depending on the draft phase). Not ChatGPT, not Gemini, not Grok. Claude was chosen because in our own testing it produces less hallucinated chart data and more grounded prose for long-form reflective writing. We may add other models if they out-perform on specific tasks; we will name them here if/when we do.

What the AI sees

The model sees, for each reading draft:

• The chart math output (planet positions, aspects, house cusps - computed deterministically by Swiss Ephemeris equivalents, not by the AI)
• Your free-text "why interested" and any context you submitted at intake
• A library of practitioner-authored reference passages keyed to chart configurations
• The practitioner's voice samples (5-10 prior readings on similar configurations, redacted of identifying info)

What the AI does NOT see

• Your email, name, or birth location precise to street level
• Any history of previous readings you've had elsewhere
• Any third-party data we don't have ourselves (no social media scraping; no astrology-database lookups)
• Other House Call users' charts or readings
• Your account password (never; it's bcrypt-hashed before storage)

What the AI is asked to do

The model is given the chart math + your context + the practitioner voice and asked to draft 1-2 paragraphs per chart configuration. The practitioner then reads those drafts, throws out ~40% of what the model wrote, edits the remaining 60% heavily, and adds the structural insights the model never reaches.

For some sections (the "short answer" callouts, the practical "what to do at the next gate" lists), the practitioner writes from scratch and uses the model only as a sounding board, not a drafter.

What happens when AI gets it wrong

It does. Routinely. Specifically:

• Hallucinated transits. The model occasionally claims a transit is happening when it isn't. The practitioner cross-checks every named transit against the chart math output before it ships.
• Generic horoscope drift. The model sometimes slides into "Capricorns are practical and ambitious" - true and useless. Edits cut these.
• False certainty. The model writes confident prose even when the chart is ambiguous. The practitioner downgrades to "the chart suggests" or "one possible reading" when warranted.
• Wrong sign. Rare but it has happened - model writes about Saturn in Capricorn for a chart where Saturn is actually in Sagittarius. Always caught by the practitioner re-reading against the chart math.

We log these patterns and tune the prompts. The peer-review step between tradition specialists (Western reads BaZi's draft, etc) catches what the authoring practitioner missed.

What you can do if you find an error

Email the practitioner. Every reading carries a feedback channel; we credit any error you flag with a revision and a follow-up section addressing the underlying chart configuration in greater depth. Errors are not embarrassing - they're how the practice gets sharper.

Why we use AI at all

Honestly? Speed and consistency on the first draft. A practitioner writing every paragraph from scratch produces ~3,000 words a day before quality starts to drop. With AI on the first draft, the practitioner can ship 10,000-15,000 words of edited, peer-reviewed reading per chart in the 5-14 day turnaround window. Without AI, the same reading would take 4-6 weeks and cost 3x.

The trade is real: AI speeds the first draft and the practitioner uses the recovered hours on the structural synthesis, the peer review, and the "short answer" callouts that make a reading actually decision-useful. If the trade ever stops working - if AI quality regresses, or if the model's hallucination rate climbs - we'll change it and name it here.