What the agent did
Scheduled agents triage issues, review search console and analytics for anomalies, write and publish blog posts, run SEO audits, flag Google Ads campaigns and post growth content. They propose tasks into a backlog.
Result, as claimed
About 60 hours a week before, about 15 to 20 hours after one month. Agents handle roughly 70% of his manual work. Organic impressions roughly doubled in a month. He shipped three features and two new MVPs in the month.
This is the result as claimed in the public source linked below. It has not been checked and is not a typical outcome.
Proof
Try it yourself
Have an AI propose this week's tasks across your products as a list you approve, instead of letting it act.
Prompt
I run these products: [name, URL, goal for each]. Here are last week's numbers for each: [visits, sign-ups, revenue, top search queries]. For each product, propose up to three tasks for this week, each with: what to do, why the numbers suggest it, time needed and risk. Mark any task that spends money, changes prices, deletes content or emails customers as NEEDS ME. Don't do any task. End with a ranked list of the five most useful tasks across all products. Return a draft only. Never send, spend, change settings or write to a live system.
Prompt: starter by Solopreneur Code
Steps
- Paste last week's numbers for each product.
- Read the proposals and strike out anything you disagree with.
- Move approved tasks to your to-do list.
- Do or delegate them. Never let the AI change budgets or prices on its own.
- Next week, tell it which proposals you approved so it learns your taste.
Watch out: The AI can read engagement signals as revenue, as Jakub found with micro-conversions, so check every claimed gain against real sales.
Starter version by Solopreneur Code