Let an AI agent audit your business website and ship each fix as a change you approve: titles, structured data, speed, sitemap and lead tracking, with nothing going live until you say yes: AI agent prompt
In a Nov 2, 2026 post on the Gameplan Financials blog, a small business owner described handing most of the web work to an AI agent. It audits the site the way a search engine and a first-time visitor would (page titles, search descriptions, load speed, sitemap, structured data), reads Google Analytics, and proposes a short ranked list of fixes. Every change arrives as a pull request with a written explanation; the owner reviews and approves it before anything is merged and deployed. Examples included an SEO batch, lead-event tracking on the inquiry form and an automatic sitemap. The owner shared early numbers but called one week of data a direction, not a trend.
The prompt
1. Put your website in a code repository (GitHub or similar) if it isn't already, and connect a coding agent such as Claude Code, Codex or Cursor to it. Give it read-only access to your Google Analytics if you can. 2. Ask: "Audit my site the way Google and a first-time visitor would see it: page titles, meta descriptions, load speed, whether the sitemap lists every page, structured data, broken links, and whether form submissions are tracked as leads in Analytics. Also look at which pages get visits and which get skipped. Give me a short list of specific fixes ranked by likely impact. Don't change anything yet." 3. Pick the top 2 or 3 fixes and say: "Make these changes as one pull request with a plain-English description of what changed and why. Don't merge or deploy it, and don't change prices, contact details or wording about my services without asking." 4. Read the pull request, ask questions about anything unclear, then approve and deploy it yourself. 5. A week later, ask the agent to compare visitors and lead events before and after, and to be honest if the numbers are too small to mean much.
How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (or fill in the blanks on AgentPlaybook Real Estate, which remembers your answers for the next prompt).
- Paste it into Claude Code, Codex or Cursor, GitHub and review the answer before you use it.
Works with: Claude Code, Codex or Cursor, GitHub, Google Analytics
Real-world example: gameplanfinancials.com/blog/how-i-use-an-ai-agent-to-run-my-business-w
Before you use it: what to check
Already built into this prompt
- Don't change anything yet." 3.
- Don't merge or deploy it, and don't change prices, contact details or wording about my services without asking." 4.
- Read the pull request, ask questions about anything unclear, then approve and deploy it yourself.
Check yourself
- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records. How prompt injection works →
- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it free