10 Practical ChatGPT Prompts for Sanity CMS Content Teams

Content teams often know what they want from Sanity CMS but not the exact GROQ query, document structure or sequence of checks required to get there. When ChatGPT is connected to an authorized Sanity project, a clear natural-language prompt can turn that editorial goal into a focused content operation.

The quality and safety of the result depend heavily on the prompt. A useful request should identify the project context, dataset, document type, content perspective, expected output and whether changes are allowed.

This guide provides ten practical, copy-ready prompts for common Sanity CMS tasks. Replace the values inside square brackets with your actual project details before using them.

A Simple Formula for Better Sanity Prompts

A strong Sanity prompt usually contains six elements:

1. Target: the project, dataset and workspace.
2. Scope: the document type, category, IDs or date range.
3. Perspective: published content, drafts, raw documents or a release.
4. Task: the exact question or operation.
5. Output: the fields, grouping or format you want returned.
6. Boundary: actions ChatGPT must not take.

For example, “check my blogs” is vague. A safer version is: “In the [production] dataset, inspect published post documents and return the ID, title and slug of posts missing a meta description. Report only; do not modify anything.”

Prompt 1: Create a Content Inventory

When to use it

Use this prompt when you need a clear overview of what exists in a dataset before starting an audit, migration or editorial plan.

Copy-ready prompt

“In the [production] dataset, inspect published documents and create a content inventory grouped by document type. For each type, show the document count, the latest update date and three example titles. Report only. Do not create, update, publish, unpublish or delete anything.”

Expected result

• Counts grouped by document type.
• Recent activity for each type.
• A small sample that helps editors understand the content model.

Why this prompt is safe

It explicitly requests published content, limits the sample and prohibits all write actions.

Prompt 2: Find Drafts Waiting for Review

When to use it

Use this before an editorial meeting or publishing session to identify unfinished work and unpublished changes.

Copy-ready prompt

“In the [production] dataset, list all post drafts. Show the draft ID, title, slug, author, last updated time and whether a published version exists. Sort by most recently updated. Do not publish or modify any document.”

Expected result

• Draft-only posts.
• Published posts with pending draft changes.
• Review-ready details without opening every document manually.

Useful follow-up

“Group these drafts by author and mark drafts not updated in the last [30] days. Keep the task read-only.”

Prompt 3: Audit Missing SEO Fields

When to use it

Use this to identify published pages that may have incomplete search or social metadata.

Copy-ready prompt

“Inspect the current post schema first. Then audit published post documents in the [production] dataset for missing title, slug, meta title, meta description, main image, Open Graph fields, Twitter fields, canonical configuration and robots settings. Return the document ID, title, slug and exact missing fields. Report only and do not change content.”

Expected result

• A document-level SEO issue list.
• The exact fields missing from each post.
• A schema-aware report rather than a generic SEO checklist.

Useful follow-up

“Group the findings into critical, high, medium and optional priorities. Explain the priority without editing any document.”

Prompt 4: Detect Duplicate Slugs, Titles and Metadata

When to use it

Use this when content has grown quickly, multiple editors publish independently or a migration may have introduced duplicate values.

Copy-ready prompt

“In the [production] dataset, inspect all post documents and identify duplicate slug values, exact duplicate titles, duplicate meta titles and duplicate meta descriptions. Group matching documents together and include their IDs, publication status and last updated dates. Do not make changes.”

Expected result

• Duplicate route risks.
• Repeated metadata that may weaken search differentiation.
• Document groups ready for editorial review.

Important limitation

A duplicate report does not automatically mean one article should be removed. Editors must compare search intent, audience and page purpose before merging or redirecting content.

Prompt 5: Find Stale Content That Needs Review

When to use it

Use this to plan content refreshes around older articles, changing products, outdated screenshots or time-sensitive claims.

Copy-ready prompt

“Find published post documents whose lastReviewedAt date is missing or older than [six months]. Return the ID, title, slug, author, publishedAt, lastReviewedAt, category and any year mentioned in the title. Sort the oldest review date first. Report only.”

Expected result

• A prioritized review queue.
• Older pages without a freshness signal.
• Time-sensitive titles that may require attention.

Useful follow-up

“For the first [10] results, summarize the main topic and list factual statements that appear time-sensitive. Do not rewrite or update the posts.”

Prompt 6: Validate Categories, Tags and References

When to use it

Use this when navigation feels inconsistent, filters do not behave as expected or editors suspect broken document relationships.

Copy-ready prompt

“Audit published post documents in the [production] dataset for missing categories, unresolved category or subcategory references, subcategories that do not belong to the selected parent category, empty tags and inconsistent tag capitalization. Return the document ID, title, current values and issue. Do not patch any reference.”

Expected result

• Missing or broken taxonomy references.
• Parent-child inconsistencies.
• Tag variations that need editorial standardization.

Why references need review

Structured references should use verified document IDs. ChatGPT should never invent or guess category IDs while fixing taxonomy.

Prompt 7: Create a Complete Blog Draft

When to use it

Use this after the topic, author, audience and editorial direction are approved.

Copy-ready prompt

“Create one English blog draft titled ‘[TITLE]’ in the [production] dataset. First inspect the complete post schema and review relevant existing posts, categories and image assets. Use author ‘[AUTHOR]’. Fill every applicable content, FAQ, SEO, social and AI-search field. Check that the slug is unique. Create a draft only—do not publish it, do not modify existing documents and verify the new draft after creation.”

Expected result

• One schema-compatible draft.
• A verified category and unique slug.
• Structured body content and supporting metadata.
• No changes to existing documents.

Editorial review checklist

• Verify every factual claim and link.
• Check brand voice and formatting.
• Confirm the image is suitable and properly cropped.
• Preview the draft before publication.

Prompt 8: Improve Metadata for Selected Drafts

When to use it

Use this when specific drafts have weak or missing metadata and the exact documents have already been approved for editing.

Copy-ready prompt

“For only these draft IDs: [ID 1], [ID 2] and [ID 3], read the title and body and propose a meta title, meta description, Open Graph title, Open Graph description, Twitter title and Twitter description. Show the proposed values first. Do not write them until I approve, and do not change any other fields.”

Expected result

• Metadata grounded in the article content.
• A preview of every proposed field.
• A clear approval checkpoint before any write.

Safe follow-up after approval

“Apply exactly the approved values to those three draft IDs using their current revisions. Change no other fields, keep them as drafts and query the documents afterward to verify the update.”

Prompt 9: Identify Content Gaps and Topic Clusters

When to use it

Use this during editorial planning to understand which questions are already covered and where the site may need supporting articles.

Copy-ready prompt

“Analyze published posts in the [Sanity CMS] category. Group them into topic clusters, summarize the search intent covered by each cluster and identify useful questions that are not answered by any existing post. Cite the existing titles used for your analysis. Do not create new documents.”

Expected result

• Current topic clusters.
• Overlapping articles that may compete.
• Genuine content gaps tied to the existing library.

Useful follow-up

“Rank the proposed topics by audience value, relevance to our services and how naturally they can link to existing posts. Keep this as a planning report.”

Prompt 10: Run a Pre-Publish Quality Check

When to use it

Use this immediately before an editor decides whether a draft is ready to publish.

Copy-ready prompt

“Perform a read-only pre-publish review of draft [DRAFT ID]. Inspect the current post schema and check required fields, title and slug, category references, author, dates, body structure, image references, SEO metadata, social metadata, canonical URL, robots settings, FAQs, direct answers and AI-search fields. Return Pass, Warning or Fail for each check with a short explanation. Do not modify or publish the document.”

Expected result

• A structured quality report.
• Clear blockers separated from optional improvements.
• A final human review checkpoint.

Publishing remains separate

Passing the checklist should not automatically publish the document. Publishing is a distinct, high-impact action that should be explicitly requested after review.

How to Adapt These Prompts

The examples are intentionally specific, but teams should adjust them for their schema and workflow.

• Replace post with another document type such as servicePage, caseStudy or product.
• Use a category, language, author or date range to narrow large audits.
• Choose published, drafts or raw perspective deliberately.
• Request document IDs and current revisions before approved patches.
• Add “report only” whenever no write should occur.
• State “do not publish” when draft creation or editing is allowed.

Common Prompting Mistakes

• Not naming the target dataset or document type.
• Mixing analysis, bulk editing and publication in one request.
• Requesting changes without reviewing the affected document list.
• Allowing ChatGPT to guess references, URLs or business facts.
• Using “fix everything” without defining fields or approval boundaries.
• Publishing generated content without a human preview.

A Reusable Safety Suffix

You can add this sentence to many Sanity prompts:

“Report the result first. Do not create, patch, publish, unpublish, delete or change project settings unless I explicitly approve the exact action and target documents.”

This suffix does not replace permissions, but it makes the conversational boundary clear and reduces ambiguity.

Conclusion

ChatGPT can help Sanity CMS content teams move faster when prompts define the target, scope, perspective, output and allowed actions. The best prompts are not merely descriptive—they create an operational boundary.

Begin with content inventories and audits, review the results and introduce controlled draft operations only where they add value. With schema inspection, verified references and explicit approval points, conversational content management can remain both practical and safe.