Oblique Oracle:
Algorithmic Divination as Design Research
The Idea
Most AI interactions are transactional: you ask a question, you get an answer. Oblique Oracle inverts that relationship. Instead of optimizing for the “right” answer, it deliberately introduces indeterminacy: ancient divination systems and lateral thinking prompts, then asks AI to find meaning in the collision.
The question isn't whether the oracle is “accurate.” The question is what happens to human judgment when algorithmic output is framed as wisdom rather than information.
This is not a novelty project. HCI literature has a recognized tradition of studying ambiguity as a design resource (Gaver et al.), generative constraints as creative catalysts (Le Masson, Hatchuel & Weil, 2022), and randomness-based interventions as a legitimate category within the Creativity Support Tools taxonomy. Divination artifacts appear in CHI, DIS, and C&C proceedings not as entertainment but as interactional systems that supply resources for meaning-making. The Oracle sits squarely in this research tradition.
How It Works
Three systems converge on every reading:
I Ching Hexagram Generation
Simulates the traditional coin-toss method (three coins, six throws) using yarrow stalk probabilities. Generates a primary hexagram with changing lines and a 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 streams a unified oracle response that weaves all three into a coherent reading.
The Design Question
What does it mean to design a system where the user cannot distinguish between algorithmic pattern-matching and genuine insight? The I Ching has survived three thousand years not because it predicts the future, but because it creates a structured space for reflection. Oblique Strategies work the same way: they don't solve problems, they reframe them.
AI adds a third layer: the synthesis feels authoritative because it's fluent, but fluency is not wisdom. Oblique Oracle sits at that intersection deliberately. It's a research artifact as much as a product: a way to study how people relate to algorithmic authority when the frame is explicitly non-rational.
The specific gap this project occupies, as far as I have been able to find: I have not located a peer-reviewed study that combines a classical divination system with an LLM to generate contextual, synthesized interpretations. ML-generated tarot decks exist. Web-based Oblique Strategies randomizers exist. AI prophecy devices exist. The three-system synthesis (hexagram structure + lateral provocation + interpretive AI) is something I have not found a direct precedent for in the CHI, DIS, or C&C literature I have searched. If that gap holds up under a more thorough literature review, it is what makes this a research question rather than just an app.
Interaction Design: The Ritual Frame
The interaction model is deliberately not a chat interface. The user's mental model should be “consulting an oracle,” not “using a chatbot.” That distinction shapes every design decision.
The Casting Ritual
The hexagram generation simulates the traditional three-coin method: three coins, six throws, using yarrow stalk probabilities. The user watches each line form, bottom to top, with changing lines (old yin, old yang) highlighted. This is not decoration. The pacing creates a contemplative pause between asking a question and receiving an answer. In Don Norman's terms, the affordance of the casting ritual is contemplation itself: the structure invites the user to sit with their question rather than rush to an answer.
CRT Terminal Aesthetic
The visual language is CRT green on void black: phosphor text, scanlines, monospace type (Share Tech Mono). The aesthetic is visceral in Norman's emotional design framework. It signals depth over polish, something ancient mediated through something electronic. The Eye of Providence, Elder Futhark runes, and Chinese sacred characters reinforce the ritual frame without requiring the user to understand any of the symbol systems. They create atmosphere, and atmosphere changes how people receive information.
Synthesis as Revelation, Not Generation
The AI response streams in character: terse, symbolic, second-person. The system prompt instructs the model to speak as “the Oracle” and weave the hexagram and oblique strategy into a single unified voice. The synthesis is capped at 200 words. No headers. No lists. This constraint is a design choice: the output should feel like revelation arriving, not content being generated. The pacing and presentation matter as much as the content.
Technical Architecture
Expo/React Native with TypeScript, built for web and mobile from a single codebase. The hexagram engine implements the full I Ching casting system: coin-toss simulation with correct yin/yang probabilities, trigram lookup via a reverse-mapped table of all 64 hexagrams, changing line detection, and relating hexagram derivation. All 64 hexagrams use James Legge's 1882 public domain translation. The Oblique Strategies deck is a complete implementation of Eno and Schmidt's original cards.
A web demo runs as a Next.js static site on GitHub Pages with Cloudflare. A pre-loaded bank of 110 oracle readings provides instant responses without requiring an API call. Live AI synthesis routes through Groq API via a Cloudflare Worker proxy, keeping API keys off the client. The architecture separates the deterministic systems (hexagram generation, strategy draw) from the non-deterministic system (AI synthesis) so the app works fully offline for everything except the live oracle voice.
Try It
A live web demo of the oracle is available. CRT terminal aesthetic, coin-toss hexagram generation, oblique strategy draw, and AI synthesis, all running in the browser.
What's Next
Voice/tone calibration (balancing mystical register and practical usefulness), visual hierarchy redesign, and past reading history so users can track how their questions evolve over time.
The core research question is a comparative study: 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, and the Oracle sits between those conditions: structured enough to provoke, synthesized enough to be accessible. The evaluation battery would include ideation metrics (fluency, novelty, variety), the Creativity Support Index (a validated psychometric), homogenization analysis (does the tool make everyone's output converge or diverge?), and think-aloud sessions to capture how users interpret ambiguous prompts.
This feels like a publishable research direction. The natural venues are CHI alt.chi, DIS (as a pictorial, given the visual design emphasis), or Creativity & Cognition. The next step is the literature review I have not yet done at the rigor a submission would require, then the comparative study itself. The tool exists. What remains is the work.