Canonical: https://botbento.com/usecases/generate-and-validate-daily-word-puzzle-boards/
Format: Markdown representation of the public HTML page.

# Generate and validate daily word-puzzle boards

[Coding](https://botbento.com/usecases/coding/) · Intermediate

Build each day's board so the answer set stays small and checkable

Each day's board needs a target word set plus a starting arrangement of lines and dots that narrows the possible answers to a small group. The bot picks candidate words, computes their line-and-dot shapes, counts how many dictionary words share that shape, and stages a week of boards climbing from short easy words to longer hard ones. It also drafts a short how-to-play note for players.

## Quick answers

**What does it do?** Build each day's board so the answer set stays small and checkable. Result: Staged board set with notes.

**What does it need?** Tools: Database, Terminal, Docs. Intermediate: some setup.

**How do I run it?** On a schedule: Nightly board build. Copy the prompt below into a bot in BotBento.

## How it works

1. On a schedule: Nightly board build
2. Then: Compute shapes and count matching words
3. Result: Staged board set with notes

## Prompt to start with

```text
You generate one board per day. Read the word list and the shape rules from the docs store, compute each candidate word's line-and-dot layout, and group words that share an identical starting configuration. Choose targets so early-week boards use only short words and later days allow longer ones, and prefer configurations that match few or no other words. Record every board with its candidate count so I can review the difficulty curve, and draft a brief how-to-play note whenever a new rule appears. Do not publish, post, send or delete anything until I approve it.
```

## Tools it uses

Database, Terminal, Docs

## Works with

BotBento

## Tags

puzzles, validation, scheduling, python, content

## Source

[Show HN: Jointter – A daily word puzzle using dots and lines](https://news.ycombinator.com/item?id=50317548) — Hacker News · checked 2026-11-13

Summarized in our own words. Any results described there are the authors’ own, not measured by BotBento.

Verified 2026-11-13: passed every automated gate and a second-model review (kimi-code/k3.1-pro). Automated, not human review. [How verification works](https://botbento.com/usecases/verification/)

By BotBento Editorial · Added 2026-11-13 · Updated 2026-11-13 · [Suggest a correction](https://botbento.com/contact/)

## Related use cases

- [Assembling Python agent execution graphs](https://botbento.com/usecases/assembling-python-agent-execution-graphs/) — Structure modular agent routines, validate tool nodes, and run automated evaluation sets.
- [Scanning workflow repos for schema errors and secrets](https://botbento.com/usecases/auditing-automation-workflow-repositories-for-schema-flaws/) — Validate automation definitions, redact exposed credentials, and stage fixes for review
- [Reverse engineering legacy game file formats](https://botbento.com/usecases/reverse-engineering-legacy-game-file-formats/) — Inspect raw binary files, identify data structures, and generate parsing code for retro games
