MARKETING
Weekly Creative Refresh from Trend Research, Scored and Logged
Each week, researches current trends for your category with Perplexity, generates fresh trend-aligned variants on Replicate, scores them, and logs the winners to a Postgres…
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly scheduled refresh
- ActionResearch category trends with PerplexityPerplexity
- LogicSelect trends and draft prompts, then score outputs
- ActionRender trend-aligned variants on ReplicateReplicate
- OutputLog scored winners to Postgres performance tablePostgres
What it does
Keeps your creative from going stale. On a weekly cadence it pulls fresh trend signals for your product category, turns the most relevant ones into image prompts, renders new variants on Replicate, scores them against your brand rubric, and records the top performers in a Postgres table you can query over time.
When to use it
Run this for always-on campaigns where ad fatigue is real and you want a steady drip of new, trend-aware creative without manually chasing what is hot each week.
How it works
- 1A weekly schedule starts the run.
- 2Perplexity researches current trends and talking points for your category.
- 3A logic step selects the most relevant trends and drafts an image prompt for each.
- 4Replicate renders a variant per prompt, and each is scored against the brand rubric.
- 5The scored winners are inserted into a Postgres performance table for tracking and historical comparison.
Set it up
What you configure once, before turning it on.
- 1Connect PerplexitySearch-grounded answers with citations.
- 2Connect ReplicateImage, video, and model inference.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Marketing workflows
Agentic UTM Taxonomy Steward: Detect, Explain, and Propose Fixes
An agent reviews the full backlog of campaign links in Airtable, reasons about taxonomy drift beyond rigid rules, drafts standardized replacements for malformed UTMs.
Slack UTM Check: Paste a Link, Get an Instant Verdict
Lets marketers drop a tracking URL into a Slack channel and get an immediate threaded reply that says whether the UTMs are valid, what is wrong, and a corrected suggestion.
Backlink Outreach Drafter for Verified Mentions
Picks verified, high-authority unlinked mentions from Airtable, drafts a personalized backlink-request email for each.
Source-Authority Verifier for Mention Provenance
Takes a queue of detected brand mentions and runs an agent that verifies whether each source is a legitimate, authoritative publisher versus a scraper or syndication copy.
Unlinked Brand-Mention Detector with Authority Scoring
Scans the web for fresh brand mentions, filters to ones that name you without linking back, scores the publishing domain's authority.
Weekly Brand-Mention Provenance Digest to Notion
Aggregates the week's tracked mentions from Airtable into a single summarized report covering new opportunities, authority distribution, and outreach progress.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.