Jev for SEO: 9 jobs that are really yes/no questions

What is Jev: a 45-second explainer for marketers

ChatGPT answers a question by writing a paragraph. Jev answers by picking from a list. Ask both "is this invoice fraud?" ChatGPT types out a sentence in 8 seconds. Jev gets three options, Fraud / Clean / Review, and returns a score for each in 0.1 seconds: Clean, 88%. No writing, no explaining, just the pick. That is Jev: a model that only decides, 100x faster and far cheaper. Every job on this page is a pick from a list.

What Jev looks like on a site: demo

One recording on a sample site. Jev runs four audits in one pass and answers each one as a yes/no or a score. The counters on screen are examples, not measurements.

SEO and GEO: audit the whole site in one pass

Four checks that usually take an agency a week, run at once. Each one is a yes/no or a score, so a 500-page site costs cents.

• Titles and headings: keep or change, page by page.
• Competitor pages: which ones are worth copying, which to skip.
• Missing pages: the questions buyers ask ChatGPT that you have no page for.
• Citation odds: how likely each page is to be picked up by AI search.

The 9 jobs at a glance

A large share of SEO is a judgment applied thousands of times: does this page deserve a link from that one, do these two URLs answer the same query, is this page saying anything new. Frontier models do it well and slowly, so teams audit once a quarter. A decision model makes it a nightly job.

1. 1Internal link mapNoul

   Question Jev answers: Is there an honest reason to link page A to page B?

   What happens next: Links above the threshold are inserted, the rest are skipped

2. 2CannibalizationNoul

   Question Jev answers: Do these two URLs answer the same search intent?

   What happens next: Yes pairs become the merge and redirect list

3. 3Thin and mass-produced page gateScore

   Question Jev answers: Score this page 1 to 10 for saying something the other pages do not

   What happens next: Low scores stay noindex until fixed

4. 4Query to page mappingChoice

   Question Jev answers: Which of these 10 URLs should rank for this query?

   What happens next: Mismatches feed the on-page fix list

5. 5Title and intent fitNoul

   Question Jev answers: Would someone searching this expect this title?

   What happens next: No rows go to the retitle queue, where an LLM writes 5 options and Jev picks one

6. 6Keep, update, merge or removeChoice

   Question Jev answers: What should happen to this URL?

   What happens next: A content audit as a sortable list

7. 7Redirect mapping in a migrationChoice

   Question Jev answers: Which new URL replaces this old one?

   What happens next: High confidence redirects are written, the rest are reviewed

8. 8Search-intent labels for keyword researchChoice

   Question Jev answers: Informational, commercial, transactional or navigational?

   What happens next: Keyword lists arrive pre-sorted by funnel stage

9. 9Schema and content consistencyNoul

   Question Jev answers: Does the structured data describe what is visible on the page?

   What happens next: Mismatches are fixed before Google flags them

Every row has a known answer set, which is the test for whether a decision model fits. If the answer has to be written, it belongs to an LLM.

What Jev is, in one table

Jev is a model from TypeSafe AI, the company founded by Diogo Almeida after his work on ChatGPT at OpenAI. It opened in early access on September 15, 2026. TypeSafe calls it a System One model: you send it a block of text (the state) and a set of typed questions, and it returns typed answers with a probability attached. It does not write sentences.

1. Question types

   What TypeSafe reports: Choice (pick one option), Score (a number in a range), Noul (a yes/no probability)

2. Price

   What TypeSafe reports: $0.042 per 1M input tokens. Output is free. Roughly $0.0004 per decision

3. Latency

   What TypeSafe reports: 70 to 500 ms per call, all answers returned in one parallel pass

4. Structured-output errors

   What TypeSafe reports: 0%, because the output is schema-constrained

5. Accuracy on TypeSafe's 4-workflow benchmark

   What TypeSafe reports: Jev 67.8%, Claude Opus 5 73.1%, GPT-5.6 Sol 74.1%

6. Access

   What TypeSafe reports: Waitlist. Early users on X report approval the same day or the next

7. What it cannot do

   What TypeSafe reports: Write text, code or a rationale. It gives a number and no explanation

Two caveats belong next to those numbers. The benchmarks are vendor-reported and measure agreement with frontier models, and no large independent reproduction exists yet. And TypeSafe says itself that it cannot prove the launch price is unsubsidized. Treat the price as today's price.

The 9 jobs, one by one

1. Internal link map

Question: "Is there an honest reason to link page A to page B?" Answer type: Noul. Next: Links above the threshold are inserted, the rest are skipped.

Embeddings shortlist the 15 closest pages, Jev judges each pair, and a Choice picks an anchor phrase already in the copy. 586 pages × 15 candidates is 8,790 calls, which matches the published demo.

2. Cannibalization

Question: "Do these two URLs answer the same search intent?" Answer type: Noul. Next: Yes pairs become the merge and redirect list.

Pairs come from pages ranking for the same queries in Search Console. The judgment is whether the intent is the same, which keyword overlap alone cannot tell you.

3. Thin and mass-produced page gate

Question: "Score this page 1 to 10 for saying something the other pages do not" Answer type: Score. Next: Low scores stay noindex until fixed.

The publish gate for programmatic SEO. It belongs before the sitemap, because a spam update applies the same test afterwards.

4. Query to page mapping

Question: "Which of these 10 URLs should rank for this query?" Answer type: Choice. Next: Mismatches feed the on-page fix list.

Run on the top queries from Search Console. When the page Google picked differs from the page Jev picks, you have a relevance problem worth a look.

5. Title and intent fit

Question: "Would someone searching this expect this title?" Answer type: Noul. Next: No rows go to the retitle queue, where an LLM writes 5 options and Jev picks one.

Two models, each doing what it is good at: generation, then selection.

6. Keep, update, merge or remove

Question: "What should happen to this URL?" Answer type: Choice. Next: A content audit as a sortable list.

One Choice per URL with traffic, age and links in the state. It turns a six-week audit into a column.

7. Redirect mapping in a migration

Question: "Which new URL replaces this old one?" Answer type: Choice. Next: High confidence redirects are written, the rest are reviewed.

Search shortlists 10 candidates per old URL. The threshold decides how much of the map a human has to check.

8. Search-intent labels for keyword research

Question: "Informational, commercial, transactional or navigational?" Answer type: Choice. Next: Keyword lists arrive pre-sorted by funnel stage.

A 50,000-keyword export labeled for a few cents, which changes how much research you bother to do.

9. Schema and content consistency

Question: "Does the structured data describe what is visible on the page?" Answer type: Noul. Next: Mismatches are fixed before Google flags them.

Validators check syntax. This checks whether the markup is true.

The pattern behind every use case

Every use case on this page follows one architecture. Code finds the candidates, Jev judges them, a threshold decides what happens, and a frontier model writes only what passed.

This is the same split Ryze AI already uses between changes it makes on its own and changes that wait for approval. A cheap decision model widens the first group without touching the rule for the second.

What it costs at the list price

These are arithmetic at TypeSafe's published price of $0.042 per 1M input tokens with free output. They are not measured runs, and token counts depend on how much context you put in each state.

1. Internal link map

   Rows: 586 pages × 15 candidates

   Approx. input tokens: ~5M

   Cost at $0.042 per 1M: ~$0.21 (published demo)

2. Thin-page gate

   Rows: 10,000 pages

   Approx. input tokens: ~12M

   Cost at $0.042 per 1M: ~$0.50

3. Intent labels

   Rows: 50,000 keywords

   Approx. input tokens: ~2.5M

   Cost at $0.042 per 1M: ~$0.11

The point of the table is the order of magnitude. Jobs that cost tens of dollars per run on a frontier model, and therefore run monthly, cost cents and can run nightly.

What Jev cannot do

Jev is narrow by design, and the narrow part matters as much as the price.

• No rationale. You get 0.91, never a sentence explaining it. Anything a client or a finance team will read still needs a frontier model to write the reason.
• Bounded answers only. If the set of possible answers is not known up front, it is the wrong tool. Strategy, copy and diagnosis stay with an LLM.
• Accuracy is triage-grade. 67.8% agreement on the vendor's own benchmark is fine behind a confidence threshold and wrong for auto-applying a budget change.
• "Cannot hallucinate" means it cannot break the schema. It can still pick the wrong option. Measure it against human labels on your own data before trusting a threshold.
• Waitlist and pricing risk. There is no general availability date, and the price may move.

Keep the frontier model for writing and rewriting pages, for briefs, and for explaining an audit to a client. Keep a human on edits to pages that make money, on redirects below the threshold, and on anything in the theme or templates.

Where to go deeper on each job

A decision model only sorts. The guides below cover the work around it: getting the data, writing the rules, and making the changes.

• Internal linking patterns
• Automated internal linking
• Keyword cannibalization
• Programmatic SEO tools
• A programmatic SEO pipeline
• The 2026 spam update
• Claude skills for SEO
• A keyword research agent

How to start before you have access

Jev is in early access. There is no public self-serve signup yet.