SEO internal linking

Decide whether one page should honestly link to another — the pairwise call behind rebuilding a 586-page internal link map.

586 pages · 45.1s · $0.21@borjafat

Borja had Jev read all 586 pages on his site and rebuild the internal link map in 45.1 seconds for $0.21 — 584 links placed, 139 pages left unlinked because nothing honestly fit. A frontier chat model on the same pages, same clock, got through 21. SEO automation isn't rewriting every page; it's making thousands of honest link decisions fast.

Try it live

This is the real thing, not a mockup. Edit the input, hit Run, and Jev returns every typed answer in one round trip — free, no signup. Now picture the same call fired across thousands of items in parallel.

POST api.typesafe.ai/v1/systemone

state — the input software gives Jev307c

questions — the typed decisions you want back

noulshould_link

Should the source page place an in-content internal link to the target page, only if it genuinely helps the reader?

→ probability 0.0 … 1.0

scorerelevance

How topically relevant is the target to the source?

→ 0…3 · 4 levels

choicerelationship

What is the best structural relationship for the link?

→ one of: supporting, sibling, tangential, unrelated

real API · free · no signup

Typed, calibrated output appears here.
Pick a demo, tweak the input, and hit Run Jev.

Get an API key →← All use cases

The decisions Jev makes

In a single call, Jev evaluates each of these — in parallel, against the same input:

noulshould_link

Should the source page place an in-content internal link to the target page, only if it genuinely helps the reader?

returns a calibrated yes/no probability.

scorerelevance

How topically relevant is the target to the source?

rates it on an ordered scale:

unrelated
loosely related
related
highly relevant / same intent

choicerelationship

What is the best structural relationship for the link?

picks one of these options:

supporting — target adds depth to a subtopic of the source
sibling — same topic cluster, peer page
tangential — only loosely connected
unrelated — no honest connection

The exact request

This is the real payload behind the live demo — copy it, change the state, and you're building:

{
  "model": "jev-latest",
  "state": "SOURCE PAGE\nTitle: \"How to cold email investors (2026 playbook)\"\nSummary: tactical guide to writing cold emails to VCs — subject lines, follow-ups, what to attach.\n\nCANDIDATE TARGET PAGE\nTitle: \"The best CRMs for solo founders\"\nSummary: comparison of CRM tools for one-person startups, pricing and features.",
  "questions": {
    "should_link": {
      "type": "noul",
      "instructions": "Should the source page place an in-content internal link to the target page, only if it genuinely helps the reader?"
    },
    "relevance": {
      "type": "score",
      "instructions": "How topically relevant is the target to the source?",
      "criteria": [
        "unrelated",
        "loosely related",
        "related",
        "highly relevant / same intent"
      ]
    },
    "relationship": {
      "type": "choice",
      "instructions": "What is the best structural relationship for the link?",
      "criteria": {
        "supporting": "target adds depth to a subtopic of the source",
        "sibling": "same topic cluster, peer page",
        "tangential": "only loosely connected",
        "unrelated": "no honest connection"
      }
    }
  }
}

Wire it into your code

Read the typed answers and branch in plain code — no parsing. Auto-handle the high-confidence cases and route the uncertain ones to a bigger model or a human. It's one API call and output is free, so ask every question you need at once.

Build your own

Every scenario above is a single API call. Try any of them free in the playground, then get a hosted key to ship it in minutes.

Run this demo ▶Get an API key →