Ciwi
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant

Find broken links and their source pages

A crawl returns a long list of failing links, many emitted by one shared template, so repairing them one by one repeats the same edit. In this case, the immediate task is to find broken links and their source pages. The workflow should produce an error inventory with repair and verification steps, grouped by the page or template that emits each link.

Topic
Website Errors and Broken Links
Target keyword
shopify broken link checker
Copyable AI prompt

A prompt you can drop directly into Spark

First replace every [bracketed] placeholder with real store scope and constraints, then add any actual records or data you have, and paste it into your preferred AI assistant or Spark agent. Spark will follow this page's workflow to produce structured output and verification steps.

ai-prompt.txt
Act as a Shopify operations specialist.
Help me find broken links and their source pages.
My store context is [describe the business, products and target audience].

My scope is [specify the affected products, pages, customers or reporting period]. Use these inputs: [each crawl row with the link URL, its destination and the emitting page or template, plus whether the destination sits inside the store or on another domain]. Group rows by the page or shared template that emits them so one correction can close many cases, decide per group whether the source markup or the destination moved, and keep external destinations in a separate set because they can only be relabelled or removed, never repaired.
Return an error inventory with repair and verification steps, grouped by source so one edit closes several cases for the specified task.
Show the relevant evidence or before-and-after examples and explain how I can verify the result.
If essential data is missing, ask for it and mark unsupported conclusions as unknown.
Do not invent metrics, product claims or customer facts.
For any publication, message, account or store change, use only connected tools within my explicitly authorized scope and report success only after verification; otherwise provide the draft or proposed steps.
Use in Spark
How to solve

A recommended resolution workflow

Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.

01

Step 1

Take the crawl or click report rows with each link's URL, its destination URL and the page or template that emitted it, and mark whether the destination sits inside the store or on a domain the merchant does not control.

02

Step 2

Group rows by the page or shared template that emits them so one correction can close many cases, decide per group whether the source markup or the destination moved, and keep external destinations in a separate set because they can only be relabelled or removed, never repaired.

03

Step 3

Deliver an error inventory with repair and verification steps listing each group with its emitting source, the single edit proposed, the number of links it is expected to close and any external links left open with their owner named, then re-run the same crawl and confirm that the group's failing rows either clear entirely or reduce to exactly the external entries already declared unfixable.

FAQ

Common questions when running this scenario

Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.

Why record the emitting template instead of the link itself?

Because one shared section, menu or app block can emit the same failing link across every page using it, so editing occurrences one by one repeats the same fix endlessly and still misses templates not yet crawled; listing the source collapses many rows into a single edit.

Are links to other websites part of this check?

Yes, but they belong in a separate set, since a destination on somebody else's domain cannot be repaired from the store; decide for each external row whether to relabel it, drop it or raise it with the site owner, and record which of those was done.

How do you know the repair worked?

Re-run the same crawl over the same scope and compare that source's row counts, because a template fix should clear every row it produced; anything still failing means a second emitting source was missed or the destination changed again since the last check.

Related scenarios

Continue with adjacent or same-topic scenarios

Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.

Next step

Want these AI scenarios embedded directly into daily operations?

Ciwi Spark builds Shopify-native AI tools and agents around the workflows merchants actually run: research, ads, translation, and customer support. Stop rewriting the same prompts by hand.

Open Spark product pageBack to Spark scenario library