SEO & GEO/AEO

Verified against ChatGPT · 2026-08-10

Plan internal links from a new page into existing ones with real anchor text, not a generic 'add internal links' note

Reads a list of your existing pages and a new page's outline, then proposes specific internal links with the exact anchor text and placement in the new page — reciprocal links back included — instead of leaving link-building as an afterthought a writer skips.

ChatGPT (GPT-5.1)3 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

New page outline and a list of our existing pages. Find real internal linking opportunities between them, with exact anchor text and placement, not a vague instruction to "link to related content."

NEW PAGE OUTLINE
H1: How to Calculate Employee Overtime Pay. H2s: Federal overtime rules, State-specific exceptions, Common calculation mistakes, Overtime calculator.

EXISTING PAGES (title + URL + one-line topic)
"California Labor Law Guide" /guides/california-labor-law — covers state wage/hour rules. "Payroll Compliance Checklist" /resources/payroll-checklist — general compliance checklist, no overtime specifics.

PRIMARY KEYWORD OF THE NEW PAGE
how to calculate overtime pay

For each existing page that's genuinely relevant to a specific section of the new page's outline, propose one internal link: name the exact section of the new page it belongs in, write the actual anchor text to use (not a description of what the anchor text should convey — the literal words), and give a one-sentence reason the link is relevant there specifically, not just topically related in the abstract. Do not propose a link just because two pages share a broad category — the link has to make sense in the actual sentence a reader would be reading at that point, or skip it. Cap it at the links that would genuinely help a reader or crawler, typically 3 to 6 for a page this size — padding the list with marginal links dilutes the ones that matter and looks like link-scheme behavior rather than genuine internal linking.

Then do the reverse: for each of those same existing pages, note whether they should also get an inbound link back to the new page once it's published, and suggest where on the existing page and what anchor text — reciprocal linking from an old high-authority page into a new one is often the single highest-leverage move for getting a new page indexed and ranked, and it's the part people forget because they only think about links going out of the new page.

Flag anchor text diversity: if more than two of your proposed anchors would use the exact same phrase, vary them, since repetitive exact-match anchor text across many links is a pattern search engines can read as manipulative even when the links themselves are genuinely relevant.

OUTPUT FORMAT
Two tables. Table 1 — Outbound links from new page: Target existing page | Section of new page | Anchor text | Why relevant here. Table 2 — Suggested inbound links to add on existing pages: Existing page | Where on that page | Anchor text.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

Asked in the abstract to suggest internal links, GPT-5.1 tends to produce advice at the level of "link to related pages where relevant," which is true but not actionable — the prompt structure here forces specificity by requiring the literal anchor text string and the named section of the new page as separate required fields, which is what turns a suggestion into something a writer can paste directly rather than interpret. The reciprocal-linking step matters because internal link equity flows in both directions and a genuinely useful internal linking plan for a new page is incomplete if it only considers outbound links; a brand-new page has no accumulated authority of its own, and the single fastest way to help it get crawled and ranked is an inbound link from an already-indexed, higher-authority page on the same site — a detail that's easy for a model (and a human) to skip if only asked to think about the new page's own outbound structure. The anchor-text diversity check addresses a specific, well-documented pattern search engines evaluate: unnaturally repetitive exact-match anchor text across many links on a site can read as manipulative link architecture even when each individual link is topically legitimate, so an internal linking plan that doesn't self-check for that pattern can inadvertently recommend something that looks fine link-by-link but looks off in aggregate. Capping the count and requiring a specific in-context relevance reason for each link also prevents the model's tendency to pad a linking list with marginal, category-level matches purely because they exist on the site — a link that's topically adjacent but doesn't fit the actual sentence a reader would be in is worse than no link, because it reads as SEO scaffolding rather than a genuinely useful cross-reference.

What you get back

Outbound: Target: "California Labor Law Guide" | Section: "State-specific exceptions" | Anchor: "California's daily overtime threshold" | Why: directly explains the CA-specific rule this section only summarizes. Inbound: Existing page: "California Labor Law Guide" | Where: within its overtime-mention paragraph | Anchor: "how to calculate overtime pay step by step."

Verified against

ChatGPT GPT-5.1 · 2026-08-10

Changelog

  • 2026-08-10 Initial publish, verified against ChatGPT GPT-5.1.

Building this for real?

This is a free starting point. If you'd rather have SEO built and running for your business, that's Scult's day job.

EXPLORE SEO
All SEO & GEO/AEO prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY