Automate news gathering and post drafting with two agents

One agent collects and summarizes industry stories into Airtable, and a second turns those entries into draft posts for approval.

Done with Zapier Agents· Intermediate

What they did
Maddy Osman, who founded The Blogsmith, set up a two-agent Zapier workflow. The first agent runs on a morning cadence, pulls in news from Google News using a search API, screens items against her rules, summarizes each one for CMOs, and records them in Airtable. After that, a second agent looks at the newest rows, uses her uploaded style guide, and creates LinkedIn and X post drafts that are sent to Slack so she can check them.
How it went
She says the system gives her back hours each week. A client saw her demo online and later asked for a similar setup. Every post still goes through her review before publishing.
Tips
Her initial build took roughly a week, so expect some setup and tuning. Keep instructions tight, test each change as you go, and start with Zapier’s built-in connections before layering on extras.

Try it yourself with Zapier Agents

Help me build two Zapier Agents. The first should run every [day/morning], find [3-5] news items about [industry/topic] from [source], filter them using [criteria], write a short summary for [audience], and store each result in [Airtable table] with the link. The second should watch for new rows, follow my [style guide], and draft [LinkedIn/X] posts in my voice using only the stored facts. Put the drafts in [Slack/drafts folder] and stop for my approval before anything is sent, posted, submitted, or published. Do not add claims that are not in the saved summaries.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.