← Back to Overview
The Generator · Python · OpenAI & Gemini

The Puzzle Generator

An autonomous Python pipeline that constructs 15×15 crossword grids, generates professional clues via OpenAI or Gemini, enforces a strict 7 point quality standard, and auto deploys validated puzzles, with zero manual intervention.

2LLM Providers
7 PointQA Validation
10,000+Puzzle Capacity
AutonomousNo Intervention Required

Dual LLM, Vendor Agnostic Architecture

The clue generation layer is completely provider independent. Switch between AI vendors with a single environment variable, zero code changes required.

AI
OpenAI (GPT 4o mini)

Default production provider. Cost optimised with a clue caching layer, identical words are never clued twice, cutting API spend dramatically on large runs.

G
Google Gemini (Vertex AI)

Fully integrated as a hot swap alternative. Uses the OpenAI compatible Gemini endpoint, the same prompt and validation stack applies to both providers.

The pipeline stops and reports gracefully when API credit is exhausted, protecting against runaway costs and leaving no partial puzzles in the output.

7 Point Quality Gate

Every grid is interrogated against seven hard constraints before it proceeds to clueing. Failures are discarded, not patched.

#CheckThresholdWhy It Matters
01Minimum Word Count≥ 40 wordsEnsures standard puzzle density.
02Zero Duplicates0 allowedNo repeated answers within one puzzle.
03Short Word Cap≤ 25% 3 letter wordsEliminates cheap filler grids.
04Letter Diversity≥ 18 unique lettersGuarantees a healthy alphabet spread.
05Intersection Integrity100% matchEvery Across/Down crossing must agree.
06Word Length Bounds3 to 15 charactersClassic crossword conventions enforced.
07Clue Self Reference Block0 allowedNo clue may contain its own answer.

From Blank Grid to Published Puzzle

Every puzzle flows through this automated workflow before it reaches a player's device.

Template Selection 15×15 grid with 180°
rotational symmetry
Grid Filling Algorithmic fill from a
300K+ validated word list
7 Point QA Gate Reject or proceed ,
no partial passes
AI Clue Generation OpenAI or Gemini,
with clue caching
Metadata & Deploy Difficulty tagged. Published
to GCS & served via CDN

Smart Metadata & Bulk Scale

The pipeline classifies, names, and deploys puzzles, and is engineered to run unattended for days on a cloud server.

  • Auto Difficulty Classifier

    Easy / Medium / Hard is assigned automatically based on average word length and obscurity density. No manual tagging ever required.

  • AI Puzzle Titling

    The LLM analyses answer themes and generates a creative title per puzzle, e.g., "Grocery Store Groove," "Lunar Legends," "Sleigh Trackers."

  • Resume Safe Bulk Mode

    Scans existing files for the last puzzle ID and continues from there, after any interruption (timeout, credit exhaustion, server restart), with no data loss.

  • Incremental Cloud Sync

    Each puzzle is written to disk and synced to GCS immediately. The master index regenerates automatically, live app installs discover new puzzles on their next load.

Browse Real Puzzles From the Library

These are actual puzzles produced by the generator, grids filled algorithmically, clues written by AI, quality validated through the pipeline.

Interested in the Generator?

The generator is included in the full acquisition. Reach out to discuss terms.

← Return to Overview