Stop letting LLMs hallucinate dates — a tool for AI agents

A developer has released `whenis`, an open-source tool that moves date interpretation out of LLMs and into deterministic parsing, addressing the common problem of AI agents hallucinating weekday-to-date mappings and range errors. The tool uses a four-layer pipeline with independently testable components, supporting multiple locales and plugins for domain-specific date handling. Currently shipping with Ukrainian and English locales plus a booking plugin, `whenis` is available on GitHub under an MIT license.

If you're building an AI agent that touches dates — booking flows, scheduling bots, "remind me on Friday" assistants — you've probably noticed: LLMs are terrible at dates. They hallucinate weekday-to-date mappings. They fencepost-error ranges. They forget what "next Friday" means in Ukrainian vs English. Asking the model to "be careful" doesn't fix it — what fixes it is moving date interpretation out of the model and into a deterministic tool. That's what whenis is. Define a resolveDate expression, reference tool that calls whenis . Let the model invoke it instead of guessing. js import { createParser } from '@whenis/core'; import { uk } from '@whenis/locale-uk'; import { booking } from '@whenis/booking'; const parser = createParser { locales: uk , plugins: booking , options: { preferFuture: true }, } ; const ref = new Date '2026-05-28' ; parser.parse "наступної п'ятниці", { reference: ref } ; // → { type: 'date', date: '2026-06-05', confidence: 1 } parser.parse 'з 5 по 10 червня', { reference: ref } ; // → { type: 'range', start: '2026-06-05', end: '2026-06-11', nights: 6 } parser.parse 'після свят', { reference: ref } ; // → { type: 'fuzzy', reason: 'holiday ref', // metadata: { suggest next month: true } } English works the same way: js import { en } from '@whenis/locale-en'; const parser = createParser { locales: en , options: { preferFuture: true } } ; parser.parse 'next Friday', { reference: new Date '2026-05-28' } ; // → { type: 'date', date: '2026-06-05', confidence: 1 } @whenis/booking , not the core. Build your own plugin for your domain.Duckling-style 4-layer pipeline: input ↓ preprocess → tokenize + tag → rule engine → resolver ↓ ParseResult Each layer is independently testable. The rule engine is iterative and compositional — rules match tokens or previously emitted IR nodes, looping until fixpoint. The output is a ParseResult with matches .candidates — each candidate has a type , ISO dates, optional nights , a confidence score, a human-readable reason , and a metadata bag plugins can extend. ESM + CJS dual builds, strict TypeScript, Node ≥18, zero DOM dependencies. npm i @whenis/core @whenis/locale-uk @whenis/booking or just core + the locale you need npm i @whenis/core @whenis/locale-en @whenis/core is a peer dependency of every locale and plugin — install it explicitly so you control the version in one place. v0.1 ships UA + EN locales and the booking plugin. v0.2 backlog: ISO passthrough rule, DD.MM numeric forms, Ukrainian word-numerals, до кінця тижня/місяця window, more English coverage. Issues and PRs welcome. Repo: github.com/norens/whenis https://github.com/norens/whenis · MIT