Oblique Oracle: Algorithmic Divination as Design Research
The iPhone app is in beta testing through TestFlight. Try the web demo or read the privacy policy.
The Idea
Oblique Oracle draws a hexagram and a card at random, then asks an AI to relate them to the question.
The test is whether a visibly ambiguous prompt changes how a person frames a problem and judges the AI reading.
The idea draws on three lines of research: ambiguity as a design resource, constraints in creative work, and divination objects as aids to interpretation.
How It Works
Every reading has three parts:
I Ching Hexagram Generation
Simulates the three-coin method: three fair coin draws for each of six lines. The public demo therefore uses coin-method probabilities, not yarrow-stalk probabilities. It generates a primary hexagram and, when lines change, the relating hexagram. All 64 hexagrams use James Legge's 1882 public domain translation.
Oblique Strategies
Draws a random card from Brian Eno and Peter Schmidt's creative prompt deck: lateral thinking tools originally designed to break creative blocks in the recording studio.
AI Synthesis
The AI receives the user's question, the hexagram interpretation, and the oblique strategy, then writes one short reading from all three.
The iPhone App
I rebuilt the prototype as a native iPhone app. You type a question, watch six coin casts build the hexagram, then read the hexagrams, the card and the Oracle's reading on one screen.
The Design Question
The I Ching gives a question a structure to interpret. Oblique Strategies reframe a creative problem through an outside constraint. This prototype adds a fluent AI reading and asks what the combination does to judgment.
Fluent AI writing can read as authority.
Related work includes AI-assisted tarot divination, tarot as a design method, Oblique Strategies as a condition in creativity-support studies, and ideation with language models. My question is narrower: what changes when an I Ching hexagram, an Oblique Strategies card, and a fluent AI reading are presented as one ritual? In July 2026 I searched the ACM Digital Library, Google Scholar, and the papers cited below. The search was not exhaustive.
Interaction Design: The Ritual
The interaction is a ritual rather than a chat window. The person is meant to feel they are consulting an oracle, and that choice shapes the pacing, language, and symbols.
The Casting Ritual
The user watches each line form, bottom to top, with changing lines (old yin, old yang) highlighted. The pacing is meant to create a pause between asking a question and receiving an answer. I have not tested whether it does.
CRT Terminal Aesthetic
The visual language is CRT green on black: phosphor text, scanlines, monospace type (Share Tech Mono). The iPhone app uses the orange from this site for text and keeps green for labels and changing lines. The look aims at the visceral level in Don Norman's emotional design framework. The Eye of Providence, Elder Futhark runes, and Chinese sacred characters support the ritual. The user does not need to understand any of them.
The Oracle's Voice
The AI response streams in character: terse, symbolic, second-person. The system prompt instructs the model to speak as “the Oracle” and combine the hexagram and oblique strategy in one voice. The reading is capped at 200 words, with no headers or lists.
Technical Architecture
The iPhone app is built in SwiftUI, and the web demo in Next.js. The web demo has the coin-toss simulation, a lookup table from each cast to its King Wen number, changing line detection, and Legge's translation for both hexagrams.
The web demo runs as a static site on GitHub Pages with Cloudflare. AI requests go through a Cloudflare Worker, which keeps the API key off the phone and out of the browser. The hexagram and card draws run separately from the AI, so the hexagrams and the card still appear when the AI is unavailable.
Readings come from gpt-oss-120b, an open-weight model from OpenAI, on Groq's free API tier. The free tier allows 1,000 requests a day for this model, enough for a prototype. The Worker sets the model's reasoning effort to low and keeps its reasoning out of the stream, so only the reading reaches the screen. The app first used Llama 3.3 70B, which Groq retired in August 2026.
Try It
◎ OBLIQUE ORACLE
The web demo runs the same casting, hexagram text and AI reading as the iPhone app. It draws from a selection of the Oblique Strategies cards.
▸ CAST THE COINSStatus
The iPhone app is in beta testing through TestFlight.
Links:PrivacyFigma design file
Not Done Yet
Still to do: tune the Oracle's voice between mystical and practical, redesign the visual hierarchy, and add a history of past readings so users can see how their questions change.
The study I want to run is comparative: does the Oracle change how people reflect compared to a raw I Ching reading, a standalone Oblique Strategy, or a freeform ChatGPT prompt? Recent work on creativity-support tools has found that constraint-based prompts like Oblique Strategies can be perceived as more challenging but also more rewarding and engaging than open-ended LLM prompting for creative ideation. The Oracle sits between those conditions. The measures would be ideation metrics (fluency, novelty, variety), the Creativity Support Index (a validated questionnaire), homogenization analysis (does the tool make everyone's output converge or diverge?), and think-aloud sessions to capture how users interpret ambiguous prompts.
I may write this up as a paper after a fuller literature review, an ethics and risk review, and the study. CHI alt.chi, DIS, or Creativity & Cognition are possible venues.
Research Sources
Related writing: Reflections on C&C 2024 and Working With Clarence.
- Gaver, Beaver, and Benford (2003), Ambiguity as a Resource for Design
- Le Masson, Hatchuel, and Weil (2022), Solving the Paradox of Constraints in Creativity
- Worlding with Tarot: Design, Divination, and the Technological Imagination (DIS 2024)
- Interpretive Cultures: AI-Assisted Tarot Divination (CHI 2026)
- Homogenization Effects of Large Language Models on Human Creative Ideation (C&C 2024)
- Cherry and Latulipe (2014), Creativity Support Index