Screen scraped event listings before they go live
Jev checks each scraped event listing and either keeps it or names why it should be excluded, such as venue hire or a cancelled event.
Author's figure: Author reports 48/50 correct for Jev on the main test set, versus 43 and 42 for the two LLMs, at about $0.04 per 1,000 decisions; not deployed in production.. Reported by the builder, not measured by us.
The use case
Local event sites and listing directories scrape pages that are not real public events: venue hire offers, product pages, private sessions, cancelled or online-only items. Jev reads the listing title and description and picks one category: keep, or a specific reason to exclude. Excluded items are held back. The author's test did not cover dates, addresses or extraction quality, so those still need normal checks. An editor reviews held-back listings and anything with a low probability before it is published or dropped.
Example workflow
- Scrape listings and run deterministic checks (dates, duplicates)
- Send title and description to Jev as a choice question: keep or a named exclusion reason
- Publish confident keeps; hold confident exclusions
- Queue low-probability results for an editor
- Editor reviews held items weekly and updates the reason list
Tools
- Jev (TypeSafe AI)
- Web scraper (e.g. Firecrawl or Apify)
- Postgres or Airtable
Risks and guardrails
- Valid events wrongly rejected lose organisers' trust
- Exclusion categories need tuning for each site
- Does not catch wrong dates or venues
Sources
Written by Agents Lookup. Credits and official pages for the tools this use case names:
- Near Here blog: Jev vs Mistral Small and Gemini Flash-Lite: nearhere.events/blog/typesafe-jev-mistral-gemini-event-validation
- Hacker News submission: news.ycombinator.com/item
- Apify MCP server (official page): github.com/apify/apify-mcp-server (checked 2026-11-09)
- Airtable MCP server (official page): support.airtable.com/articles/9897799762-using-the-airtable-mcp-server (checked 2026-11-09)