Drafting meta descriptions with an LLM without losing control: a review loop in 60 lines of Python
Описание и применение
Автоматизированный процесс генерации мета‑описаний с помощью LLM, включающий проверки длины, дублирования, запрещённых фраз и подтверждения фактов, после чего человек утверждает результат перед публикацией.
Задача
Writing meta descriptions for hundreds of pages can produce long, generic, duplicated, or misleading text.
Результат
The pipeline produces 140‑155 character meta descriptions that avoid banned phrases, duplicates, and unsupported claims, with human approval ensuring quality before CMS publication.
Рабочий процесс
- Input: CSV with URL, title, H1, text
- Draft: LLM generates one description per page using only that page’s text
- Automatic checks: length, banned phrases, duplicates, grounding against source text
- Human review: spreadsheet with draft, flags, approve/edit column
- Publish: approved rows are sent to CMS
Доказательства
Writing meta descriptions for a few hundred pages is a classic task to hand to a language model.
The trick is not the prompt. It is the checks around it and a human approval step.
Length, duplicates, banned phrases, and "is every claim in the source text?".
- Дата записи: 2026-10-26T14:11:19.175Z