Content Strategy Agent
Approval-gated editorial pipeline with automated SEO enrichment.
Overview
Paul was running a manual editorial queue on top of Inoreader. Duplicates were bleeding through, DataForSEO credits were burning on articles that would never get published, and basic AI prompts were returning keyword slop instead of real terms from the article body.
The challenge
Manual editorial queue on Inoreader. Duplicates bled through, DataForSEO credits burned on rejected articles, and AI prompts returned keyword slop. Backlog passed 300 articles with no triage by search value.
The approach
Four-stage Make.com pipeline on an Airtable source of truth. Inoreader feeds a deduplicated Pending queue. Operator approval is the only trigger releasing a row into paid enrichment. Keywords are extracted from article body and checked against a Keyword Master before DataForSEO fires. Outline generation pulls AI Score 5+ sources and returns an H1 to H3 outline in under ten minutes.
The results
- ✓Four-table Airtable state machine governs article lifecycle from Pending to publishable outline.
- ✓Approval gate blocks DataForSEO calls on rejected articles, collapsing credit burn to near zero.
- ✓Keyword Master dedup layer reuses prior enrichment across campaigns, so cost compounds downward.
- ✓AI Score (1 to 10) filters weak sources before outline generation, so only rank-worthy inputs reach GPT.
System snapshots
Let's map the system that moves your number.
Twenty-minute discovery call. We map the agent, the metric it moves, and what shipping it would actually cost.
Book a discovery call ↗