Skip to main content
Sometimes you want more than a single blast but less than a forever-running automation. A product launch is the classic case: an announcement, a follow-up two days later, but only to people who didn’t open the first one. That’s a flow, not an email. It just needs to run once, against an audience you choose, at a moment you choose. That’s exactly what a manual-audience automation is for. You build a normal flow (sends, waits, filters, splits) but instead of listening for an event forever, it runs your saved audience through the graph when you launch it. Treat it as a one-off, not a live automation. This recipe builds a two-stage launch sequence. The same pattern works for event invites, seasonal promos, or any send where the follow-up depends on what happened in the first email.
Before you start. You need a verified sending domain and at least one saved audience.

1. Save the Audience

Go to Audience in the sidebar and build the segment you want to hit: filter by plan, activity, custom fields, whatever defines the group. Click Save as Audience and give it a clear name. The automation’s trigger node will show this audience, its filter query, and the live contact count, so you can sanity-check who’s in scope before anything sends.

2. Generate the Flow

Open Home and describe the sequence, making the one-off intent explicit:
Build a one-off launch flow I can run manually against my "Newsletter
subscribers" audience.

Email 1: announce [feature]. What it does, why it matters, one CTA to try it.
Wait 2 days.
Filter: only contacts who did NOT open email 1.
Email 2: shorter follow-up. Different subject line, same CTA. Casual tone:
"in case you missed it," not a re-send.
Brew opens the flow on its own canvas with the trigger, both emails, the wait, and the filter in place. If the trigger isn’t already set to your audience, click the trigger node and use Change trigger to switch it to the right one.

3. Review the Emails

Click each Send Email node to review and refine, either in chat (“Tighten the follow-up subject line”) or by editing the email directly. Personalize with {{{firstName | there}}} as usual. The filter node is what makes this a flow instead of two blasts: contacts who opened email 1 exit quietly, and only non-openers get the nudge.

4. Test the Run

Click Test automation, enter your own email address, and fire the test. Brew runs the entire graph: waits fast-forward, the filter evaluates, and every send lands in your inbox only. Real contacts are never hit on test runs.

5. Run It

When it looks right, launch the run. There’s no publish step: a manual-audience automation has nothing to leave running in the background. While contacts are moving through the flow, the automation shows Sending in the Automations list; when the run completes, it shows Sent.
Every send in the run counts toward your monthly send limit, so check the contact count on the trigger node before launching. From the API you can also pass dry_run: true to preview the exact recipient count without sending, or scheduledAt to launch the run later.

6. Reuse It Next Time

The flow stays in your Automations list after the run. For the next launch, open it, swap the email content in chat (“Update this for the [new feature] launch”), point Change trigger at a different audience if needed, and run it again. Each run is tracked separately, so the history of past launches stays intact.

Need help?

Our team is ready to support you at every step of your journey with Brew. Choose the option that works best for you:

Search Documentation

Type in the “Ask any question” search bar at the top left to instantly find relevant documentation pages.

ChatGPT/Claude Integration

Click “Open in ChatGPT” at the top right of any page to analyze documentation with ChatGPT or Claude for deeper insights.