Jev for SEO: 9 jobs that are really yes/no questions
The first SEO demo of Jev came from Distribb's founder: 586 pages read and an internal link map rebuilt in 45.1 seconds for $0.21, with 139 pages it declined to link, against Claude Opus 5 finishing 21 pages for $1.43 on the same clock. Internal linking is one of 9 SEO jobs that are classification in disguise. Ryze AI publishes this blog and does not run Jev in production yet.
Built by our community of 2,000 marketers
Free skills and prompts for paid ads and SEO
Templates for Claude, ChatGPT and Perplexity.
Clients we work withClients we
work with
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.
| # | Job | Answer type | Question Jev answers | What happens next |
|---|---|---|---|---|
| 1 | Internal link map | Noul | Is there an honest reason to link page A to page B? | Links above the threshold are inserted, the rest are skipped |
| 2 | Cannibalization | Noul | Do these two URLs answer the same search intent? | Yes pairs become the merge and redirect list |
| 3 | Thin and mass-produced page gate | Score | Score this page 1 to 10 for saying something the other pages do not | Low scores stay noindex until fixed |
| 4 | Query to page mapping | Choice | Which of these 10 URLs should rank for this query? | Mismatches feed the on-page fix list |
| 5 | Title and intent fit | Noul | Would someone searching this expect this title? | No rows go to the retitle queue, where an LLM writes 5 options and Jev picks one |
| 6 | Keep, update, merge or remove | Choice | What should happen to this URL? | A content audit as a sortable list |
| 7 | Redirect mapping in a migration | Choice | Which new URL replaces this old one? | High confidence redirects are written, the rest are reviewed |
| 8 | Search-intent labels for keyword research | Choice | Informational, commercial, transactional or navigational? | Keyword lists arrive pre-sorted by funnel stage |
| 9 | Schema and content consistency | Noul | Does the structured data describe what is visible on the page? | 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.
Quick answer: Jev for seo means using TypeSafe's decision model for the high-volume judgment steps in seo. 1) It answers pick-one, score and yes/no questions for about $0.0004 each. 2) It cannot write, explain or plan. 3) The top fit here is internal link map, then cannibalization. 4) Run it behind a confidence threshold, with an approval queue for the middle band. 5) Keep a frontier model for anything a person reads and a human on anything hard to undo. 6) Access is by waitlist as of September 2026.
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.
| Property | What TypeSafe reports |
|---|---|
| Question types | Choice (pick one option), Score (a number in a range), Noul (a yes/no probability) |
| Price | $0.042 per 1M input tokens. Output is free. Roughly $0.0004 per decision |
| Latency | 70 to 500 ms per call, all answers returned in one parallel pass |
| Structured-output errors | 0%, because the output is schema-constrained |
| Accuracy on TypeSafe's 4-workflow benchmark | Jev 67.8%, Claude Opus 5 73.1%, GPT-5.6 Sol 74.1% |
| Access | Waitlist. Early users on X report approval the same day or the next |
| What it cannot do | 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.
Get a free instant audit
Get a free, instant read on your paid ads or SEO — and fix it right away.
Paid ads audit
- Catch wasted spend & broad-match leaks
- Find account structure gaps
- Rank your quickest wins
- Spot PMax & brand-search overlap
- Check conversion-tracking health
- Benchmark CPC vs your industry
- Catch wasted spend & broad-match leaks
- Find account structure gaps
- Rank your quickest wins
- Spot PMax & brand-search overlap
- Check conversion-tracking health
- Benchmark CPC vs your industry
Free · no credit card · instant
SEO audit
- Find keyword & ranking gaps
- Catch technical SEO issues
- Rank your fastest wins
- Surface thin & duplicate pages
- Check indexing & crawl coverage
- Compare backlinks vs competitors
- Find keyword & ranking gaps
- Catch technical SEO issues
- Rank your fastest wins
- Surface thin & duplicate pages
- Check indexing & crawl coverage
- Compare backlinks vs competitors
Free · no credit card · instant
Ryze AI — Autonomous Marketing
A decision is only useful if something acts on it
- ✓Ryze AI reads the live account and makes the change
- ✓Approval queue for budgets, bids and money pages
- ✓Free to connect, flat fee for autopilot
2,000+
Marketers
$500M+
Ad spend
23
Countries
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.
The decide-then-act loop
- Collect the rows with code or an API: search terms, ads, pages, AI answers. No model needed.
- Shortlist with rules or embeddings, so Jev sees 10 to 15 candidates per item and not the whole account.
- Ask Jev one bounded question per row: a Choice, a Score or a Noul. Every answer comes back with a probability.
- Apply a threshold. High confidence is applied automatically. The middle band goes to an approval queue. Low confidence is dropped.
- Write with an LLM only where text is needed: the new ad, the new title, the one-line reason a client will read.
- Verify the LLM's output with Jev again before it ships.
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.
| Job | Rows | Approx. input tokens | Cost at $0.042 per 1M |
|---|---|---|---|
| Internal link map | 586 pages × 15 candidates | ~5M | ~$0.21 (published demo) |
| Thin-page gate | 10,000 pages | ~12M | ~$0.50 |
| Intent labels | 50,000 keywords | ~2.5M | ~$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.
Elena R.
Head of Growth
DTC Home Goods
We had a 900-item SEO backlog and no engineering time to clear it. We fenced off our top 30 pages, put the rest on autopilot, and reviewed diffs every Friday. Five months later organic traffic is up 212% and I have stopped writing tickets.”
212%
Organic traffic growth
1,400
Pages optimized
5 months
To full results
1,000+ marketers use Ryze
Automating hundreds of agencies
How to start before you have access
Jev is in early access. There is no public self-serve signup yet.
1. Join the waitlist
Request access at typesafe.ai. Early users report approval the same day or within a day, but TypeSafe publishes no guarantee.
2. Label a sample first
Before you have a key, hand-label 500 rows of the job you care about. That set is how you will pick thresholds, and it works for any model.
3. Build the loop on a model you can call today
The decide-then-act loop runs on Claude Haiku 4.5 or Gemini Flash-Lite with structured outputs. It costs more per call, and the code does not change when you swap Jev in.
4. Connect the account data
The rows have to come from somewhere. Ryze AI SEO gives Claude, ChatGPT, Cursor and Grok live access to the account, so the collect step is one prompt.
Sources and how this page was written
What is verified and what is not
- Verified from TypeSafe's launch post: the price, early access and the System One definition.
- Vendor-reported, not reproduced: latency, error rates and the benchmark scores.
- Third-party claims from X, not reproduced by us: the 724-ads, 586-pages and 700-leads demos.
- Our own arithmetic: every cost in the cost table, at the list price.
- Disclosure: Ryze AI publishes this blog and does not run Jev in production as of 2026-09-19.
Sources
- Introducing System One Models & Jev — TypeSafe AI, Sep 15, 2026Launch post: pricing ($0.042 per 1M input tokens, output free), early access and the System One definition.
- Jev: TypeSafe's System One Model — DataCampAPI shape, the three question types, vendor benchmark table and the stated weaknesses.
- AINews: Jev, a System One model that only decides, classifies, routes and scores — Latent SpaceIndependent summary of the launch and the open questions about the benchmarks.
- awesome-jev-by-typesafe — GitHubCommunity patterns (retrieve candidates, then judge) and the operational limits reported by early users.
Frequently asked questions
What is Jev for seo?
Jev is a decision model from TypeSafe AI, released in early access on September 15, 2026. Used for seo, it answers bounded questions about rows of account or site data: pick one option, give a score, or return a yes/no probability. It costs about $0.0004 per decision at list price and cannot write text, so it handles the sorting and an LLM handles the writing.
How much does Jev cost in 2026?
TypeSafe lists Jev at $0.042 per 1 million input tokens with output tokens free, which it describes as roughly $0.0004 per decision. That is the early access launch price from September 2026. TypeSafe itself says it cannot prove the price is unsubsidized, so budget on it as today's price and re-check before you scale a job.
How accurate is Jev compared with Claude and GPT?
On TypeSafe's own four-workflow benchmark Jev scores 67.8%, against 73.1% for Claude Opus 5 and 74.1% for GPT-5.6 Sol. The benchmark measures agreement with frontier models and nobody has independently reproduced it yet. Treat Jev as triage-grade: run it behind a confidence threshold and test it against human labels on your own data first.
Is the 586 pages for $0.21 result verified?
It is a first-hand claim posted on X by Distribb's founder in Jev's launch week in September 2026: 586 pages read and an internal link map rebuilt in 45.1 seconds for $0.21, against Claude Opus 5 finishing 21 pages for $1.43 on the same clock. It has not been independently reproduced, and Ryze AI has not run it.
Can Jev write meta titles or content?
No. Jev cannot generate text of any kind, including meta titles, descriptions or page copy. The working pattern for SEO is to pair it with a language model: the LLM writes five title options and Jev selects the one that best matches the search intent, or Jev flags the pages that need work and the LLM rewrites them.
Is Jev an LLM?
TypeSafe says no. It calls Jev a System One model: a new architecture with a parallel sampler that returns every typed answer in a single pass, trained with a method named Reinforcement Learning for Calibrated Decisions. In practice the difference is simple. An LLM produces text token by token, and Jev returns a choice, a number or a probability and nothing else.
What are Choice, Score and Noul in Jev?
They are Jev's three question types. Choice picks one option from a list you provide, for example buyer, researcher or junk. Score returns a number inside a range you set, such as 0 to 100. Noul returns a yes/no probability. Every answer arrives with a calibrated confidence, which is what lets you auto-apply the confident ones and queue the rest.
How do I get access to Jev?
Jev is in early access behind a waitlist at typesafe.ai, with no general availability date as of September 2026. Early users on X report being approved the same day or within a day. You do not need to wait to start: label a sample of your data and build the same loop on Claude Haiku 4.5 or Gemini Flash-Lite, then swap the model.
Can Jev hallucinate?
Jev cannot produce malformed output, because its answers are constrained to the schema you define, and TypeSafe reports a 0% structured-output error rate. It can still be wrong. It may pick the wrong option or give a confident yes where the truth is no. That is why every workflow here uses a confidence threshold and a human approval queue for the middle band.
What can Jev not do?
Jev cannot write text, code, ad copy, page content or an explanation of its own answer. It cannot browse, call tools or read an account by itself, and it only works when the possible answers are known in advance. Strategy, diagnosis, copywriting and anything a client will read still belong to a frontier model or a person.
Does Ryze AI use Jev?
Not in production as of September 2026, because Jev is waitlist-only. Ryze AI runs the same decide-then-act loop on models that are available today: code collects the rows, a model judges them, small reversible changes are applied and larger ones wait for approval. The design lets the decision step be swapped to Jev when access opens.
What is the best way to start using Jev for seo?
Pick one high-volume job from this page, hand-label 500 rows of it, and build the loop on a model you can call today with structured outputs. Set the auto-apply threshold from your labels, not from a vendor benchmark. Connect live account data first, since a decision model is only useful when something can act on its answers.
Should a decision model replace my frontier model?
No. The two do different jobs. A decision model such as Jev takes the thousands of small, bounded calls in seo, which is where most of the token bill goes. A frontier model keeps the work that needs language: writing, rewriting, diagnosing and explaining. Most of the saving comes from routing each task to the cheapest model that can do it.
Related guides
Ryze AI — Autonomous Marketing
Put the decisions to work on a live account
- ✓Connect Google Ads, Meta, GA4 and Search Console
- ✓Let the agent apply the safe changes
- ✓Review the rest in one queue
2,000+
Marketers
$500M+
Ad spend
23
Countries
