Part 1 The problemWhy teams need this
01 · THE PROBLEM
The most expensive content mistake isn't a weak paragraph. It's a whole article nobody searches for. This agent makes topic choice come from a ranked plan and real search data, not from whoever had an idea in Monday's meeting.
Part 2 How it worksWhat it does, step by step
02 · WHAT IT DOES
Once a week it takes the next keyword from your planned backlog, or finds a Google search you're almost ranking for, and turns it into a clear writing brief. It checks you haven't already covered it, then hands the brief to the next agent.
03 · HOW IT RUNS
Step by step, as built.
Take from the backlog
Fetches the top queued keyword and marks it used straight away, so two runs can never claim it.
Fall back to real data
With an empty backlog, it pulls Search Console queries ranking in positions 5 to 20, close enough to move up.
Write the brief
Claude produces the brief; a parse check stops malformed output from moving on.
Skip duplicates
If a post for this keyword already exists, the run ends without creating another.
04 · TOOLS AND APPS
Built around the systems already in the process.
05 · WHEN SOMETHING BREAKS
Failure is designed in.
- 4decision points (IF or Switch) check the data before it moves on.
- ✓Anything unhandled triggers our central error workflow, so a crash gets reported instead of failing silently.
Standard on every build
- Schema validation before downstream writes
- Retry and error routes for external API failures
- Duplicate-safe processing and idempotent updates
- Human approval where the action carries business risk
- Execution logging for support and audit review
Part 3 The impactWhat it's worth, and how we'd build yours
06 · PROJECTED IMPACT
What it should change in the business.
Projections for a typical deployment. The calculation below shows the math, and you can put in your own numbers.
07 · ROI CALCULATION
How it pays back in your business.
The starting numbers are a hypothetical deployment sized to the projections above. Change any of them to your own volumes and costs, and the math updates underneath.
- Full-time equivalent freed
- 0.1 people
- Gross value
- $6,528
- Running cost
- −$120
- Return per $1 of running cost
- $54.4
The math: 8 post briefs × 120 min × 12 months × 85% ÷ 60 = 163 hours a year × $40/hour = $6,528. Net value = gross value − $120 running cost a year.
08 · HOW WE'D BUILD YOURS
How we'd build yours.
- Discover: map the current process, systems, volumes, owners and exceptions.
- Design: define the canonical data model, approvals, retries and system boundaries.
- Build: implement credentials, nodes, validation and observable error routes.
- Prove: run controlled data through success, duplicate and failure scenarios.
- Operate: publish runbooks, ownership and measurable service levels.
