The Dictionary, with AI.
Two tools sit on top of the 29 reviewed entries. They help you find the right word and flag biased language in any piece of writing. Every suggestion links back to a named-editor entry.
Nothing on this page autopublishes. The AI is a starting point; the dictionary is the source of truth.
Ask the dictionary.
Type a question, a phrase, or just a word. The AI searches the dictionary's entries and surfaces matches.
- Works on natural-language questions, not just keywords.
- Falls back to the closest theme if nothing matches.
- Every result links to a named-editor entry.
Bias rewrite.
Paste any paragraph. The tool scans it against the dictionary and flags terms that need rethinking — with alternatives sourced from the entry.
- Highlights flagged terms in place.
- Lists suggested replacements with editor context.
- Useful for editors, comms teams, and educators.
How this AI is built.
Plain-English. No black box.
Reviewed entries only
The AI never invents content. It surfaces from the entries the editorial board has already reviewed.
Locked prompt
The AI prompt is fixed server-side. Submitters can't inject their own instructions. Prompt injection is structurally impossible.
Cost-capped
AI spend is structurally capped. If a flood of queries hits, the AI auto-rate-limits; the dictionary stays up.
Privacy-clean
Your queries are never used to train AI provider models. The dictionary's commercial API tier excludes training opt-in.
The AI can't add new entries.
Only a named editor can.
If the dictionary doesn't know a word, send it in. An editor reads every submission.