Canonical: https://botbento.com/usecases/score-incoming-news-items-against-a-fixed/
Format: Markdown representation of the public HTML page.

# Score incoming news items against a fixed question set

[Research](https://botbento.com/usecases/research/) · Intermediate

Tag each new article on relevance, direction and affected assets at once

New articles land in a queue through the day. The bot reads each one once and answers the same short, unchanging list of business questions about it, so the reader gets a consistent view rather than a fresh summary every time. Scored items go into a sortable table, with the highest-importance ones surfaced first.

## Quick answers

**What does it do?** Tag each new article on relevance, direction and affected assets at once. Result: Ranked table plus draft digest.

**What does it need?** Tools: Google Sheets, Email, Chat. Intermediate: some setup. The prompt includes an approval step.

**How do I run it?** On a schedule: Hourly batch of new items arrives. Copy the prompt below into a bot in BotBento.

## How it works

1. On a schedule: Hourly batch of new items arrives
2. Then: Answer the fixed question set per item
3. Result: Ranked table plus draft digest

## Prompt to start with

```text
You receive batches of incoming news items. For every item, answer the same small fixed set of questions — how important it is, which way it points, and which assets it touches — reading the item once and branching to each question in turn. Include a baseline answer produced with no content attached, so the user can see the model's default lean. Write results to a table sorted by importance. Draft a short digest of the top items and hold it for the user's approval; never send, post, pay or delete anything without their explicit go-ahead.
```

## Tools it uses

Google Sheets, Email, Chat

## Works with

BotBento

## Tags

news, classification, scoring, triage

## Source

[Show HN: Spinf-serve – inference server for bulk scoring and decisions](https://news.ycombinator.com/item?id=50306815) — 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

- [Classifying incoming support tickets into structured records](https://botbento.com/usecases/classifying-incoming-support-tickets-into-structured-records/) — Extract issue types, assess priority levels, and format customer messages for downstream queues
- [Curated daily topic news briefing compiler](https://botbento.com/usecases/curated-daily-topic-news-briefing-compiler/) — Gather recent web stories on designated topics and structure them into multi-section digests
- [Curating an hourly tech news briefing](https://botbento.com/usecases/curating-an-hourly-tech-news-briefing/) — Filter top technical headlines and generate concise category summaries
