PR crisis monitoring agent: Slack alerts and Notion incident log

Build me a real-time PR crisis watchdog as an agent workflow. The trigger is a cron schedule running every 30 minutes.

On each tick, the agent should query NewsWhip for articles mentioning my brand, my product names, and a configurable list of competitor names. Use NewsWhip's Quick Search Articles for fast last-24-hour scans, and Search Articles (Historical) when a richer Lucene-style query with engagement sorting is needed. Focus the search on the last hour, and only consider articles with high social velocity (NewsWhip's nw_score) or fb_overperforming signals above a configurable engagement threshold so low-noise mentions stay quiet.

For each candidate article, before doing anything else, the agent must dedupe against incidents already logged in Notion. Use Notion's Query a Database operation against my Crisis Log database, matched on the article URL, and skip any article that already has an entry. This is the rule that keeps the same story from re-alerting on subsequent ticks.

For each new high-signal article that survives dedupe, the agent should assess severity by combining (1) volume spike vs. baseline, (2) sentiment of the headline and snippet, and (3) publisher reach. Map that to a response level: Monitor, Prepare Response, or Escalate.

Then it should post a structured alert to a designated Slack channel using Slack's Send a Message operation. The Slack message must include: headline, publisher, link, key engagement metrics (nw_score, fb_overperforming, total shares), the assessed severity, and the suggested response level. Format it so the on-call comms person can scan it in two seconds.

At the same time, the agent should create a new page in my Notion Crisis Log database using Notion's Create a Page operation. The page should carry the headline as the title, plus properties for publisher, article URL, first-seen timestamp, engagement metrics, severity, and suggested response level. Leave a Timeline Notes section in the body so the comms team can append updates as the story develops. This is what keeps the durable incident record auditable after the Slack ping fades.

Configurable inputs the agent should expose: brand keywords, product keywords, competitor keywords, engagement threshold (nw_score floor and/or fb_overperforming floor), Slack channel ID, and Notion Crisis Log database ID. Default the schedule to every 30 minutes but make it easy to switch to every 15 or every 60.

Integrations to use: NewsWhip (Quick Search Articles, Search Articles (Historical)), Slack (Send a Message), Notion (Query a Database for dedupe, Create a Page for the incident record).

Additional information

What does this prompt do?

Watches the news around the clock for articles mentioning your brand, products, or competitors and flags the ones picking up real social momentum.
Sends a structured alert into a chosen Slack channel with the headline, publisher, link, engagement numbers, and a suggested response level.
Creates a new entry in your Notion crisis log so the comms team has a durable, collaborative timeline of every incident.
Skips stories already logged in Notion so the same headline never pings the team twice.

What do I need to use this?

A NewsWhip account with access to Quick Search and historical article search.
A Slack workspace and the channel you want crisis alerts posted in.
A Notion workspace with a database set up as your crisis log (with columns for headline, publisher, link, severity, and timeline notes).
The brand, product, and competitor keywords you want monitored, plus an engagement threshold for what counts as a real spike.

How can I customize it?

Tighten or relax the engagement threshold so you only get pinged for real outliers, not routine mentions.
Change how often the watchdog runs (every 15 minutes for fast-moving brands, hourly for quieter ones).
Swap which Slack channel gets the ping, or route different keyword groups to different channels and DMs.
Adjust the keyword list as you launch new products, sponsor new things, or watch new competitors.
Tune the severity rubric so volume spikes, sentiment, and publisher reach map to the response levels your team actually uses.

Frequently asked questions

How fast will my team find out about a breaking story?

By default the watchdog runs every 30 minutes, so you will hear about a spiking story within half an hour of it taking off. If you need faster response times you can drop the schedule to every 15 minutes.

Will the same article get posted to Slack multiple times?

No. Before alerting on any article, the agent checks your Notion crisis log for an existing entry with the same link and skips it if one is found. Each incident is alerted exactly once.

How does it decide what counts as a crisis versus a normal mention?

It looks at NewsWhip's social engagement signals, including how fast a story is picking up shares and whether it is overperforming the publisher's typical reach. You set the threshold, so low-noise mentions stay quiet.

Can I monitor more than just my own brand?

Yes. You give it a list of keywords up front. Most teams include brand names, product names, executive names, and a handful of close competitors so they catch comparison stories too.

What does the Notion entry look like?

Each incident lands as a new page in your crisis log database with the headline, publisher, link, social engagement numbers, suggested severity, and a timeline section the comms team can update as the story develops.