RecipeAgents / Guides
Agent recipe guideAI competitor monitoring
Competitors change prices, plans and positioning quietly. Checking their pages by hand is easy to forget. This recipe uses Visualping to detect changes, Make to pass the diff to ChatGPT, and a weekly email that tells you in three bullets what changed and why it might matter. You read one email instead of opening a dozen tabs, and you have a dated record of every change for later reference.
The prompt
Summarize what changed on {{competitor}}'s page and why it may matter to us (pricing, positioning, features). 3 bullets max. Diff: {{diff}}Step by step
- Set Visualping monitors on each competitor's pricing and changelog pages.
- On change, a webhook triggers a Make scenario that sends the diff to ChatGPT with the prompt.
- Store each summary in a sheet or Notion database.
- Once a week, email yourself (or your team) the collected summaries.
Why diffs, not whole pages
Sending only what changed keeps the model focused and cheap. It also stops the summary from restating the whole page every week. Visualping provides the change; the model explains it.
Pages worth watching
Pricing, plans and changelog pages carry most of the signal. Homepage headlines show positioning shifts. Avoid watching pages that change constantly, such as blogs, or you'll drown in noise.
Mistakes to avoid
Reacting to every change. Use the weekly digest and decide in batches.
Scraping behind logins or against a site's terms. Watch public pages only.
Forgetting to update monitors when a competitor redesigns their site.
Build it in Make, Zapier or n8n
The recipe is tool-agnostic. Every step maps to a standard building block: a trigger from the app where the data starts, an AI step that sends text to a model with the prompt, a parser that reads the JSON or text that comes back, and actions in the destination apps. Zapier is the quickest to get running for linear flows. Make makes branching and loops easier to see. n8n can be self-hosted if you want to keep data on your own infrastructure. Pick the one your team already pays for.
Test it before you trust it
Run the recipe on ten to twenty real examples before you switch it on for everything. Put the inputs and outputs side by side in a sheet and mark each one right or wrong. Where it's wrong, add one specific line to the prompt that addresses the pattern, then run the same examples again. Keep a human approval step on any action that is visible to customers or touches money until the error rate is one you'd accept from a new hire.
Watch running costs as well. Each AI step is billed by the model provider and each task or operation by the automation tool. Filtering inputs before the AI step, for example skipping newsletters or tiny files, is the easiest way to keep both down. Check current pricing on each vendor's site, since it changes often.
Before you use it
Every recipe on RecipeAgents follows the same shape: a trigger, the tools, the steps, and the exact prompt. Start with the human-approval version. Once you have watched a few dozen runs and trust the output, decide which steps can run on their own. Model and tool names change often, so check current pricing and features in each tool before you build.
Frequently asked questions
- Can AI track competitor pricing?
- Yes, by combining a change-detection tool like Visualping with an LLM that summarizes the change.
- How often should it run?
- Detection can run daily; the summary email is most useful weekly.
- Do I need Make?
- Make is used here for the webhook and routing. Zapier works too.