Jev for ads and SEO/GEO: 9 jobs on one decision loop
Paid ads and organic run on the same small decisions: pick one, score it, yes or no. Jev, TypeSafe's decision model, answers those for about $0.0004 each and writes nothing. Here are 9 jobs that fit one loop. Ryze AI 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
What the loop looks like: 3 simulated runs
Short screen recordings of the loop on sample accounts. They are simulated runs built by Ryze AI to show the workflow, so the counters and costs on screen are illustrative and not measured.
Jev for Meta Ads: from an Ad Library scan to scored briefs
Jev reads competitor ads from the Meta Ad Library, tags each one, and shows which creative patterns stay live past 60 days. It then scores new briefs on hook, brand fit and survival. An LLM writes the brief text.
Jev for SEO and GEO: four site audits in one pass
Four site checks at once: which SEO elements to keep or change, which competitor pages are worth copying, which buyer questions you have no page for, and how likely each page is to be cited by AI.
Jev for GEO: citation checks across ChatGPT, Claude and Gemini
About 1,450 buyer prompts run against ChatGPT, Claude and Gemini. Jev checks each answer for your brand and for who got cited instead, scores why your pages get skipped, and ends with a rewrite checklist. Code collects the answers and an LLM does the rewrites.
The 9 jobs at a glance
Paid and organic teams ask the same small questions about different data. One loop can answer all of them, and the result of one job feeds the next.
| # | Job | Channel | What Jev does |
|---|---|---|---|
| 1 | Search-term triage | Google Ads | Sorts every search term into buyer or junk, so the junk gets blocked |
| 2 | Creative tagging | Meta Ads | Labels every ad by hook, format and offer, so you see what wins |
| 3 | Landing page match | Ads + SEO | Checks the page delivers what the ad promised |
| 4 | Internal link map | SEO | Decides which pages should link to each other |
| 5 | Cannibalization | SEO | Finds two pages competing for the same search |
| 6 | Thin-page gate | SEO | Holds back pages that say nothing new |
| 7 | Citation checks | GEO | Checks if ChatGPT, Claude and Gemini recommend you |
| 8 | Who got cited instead | GEO | Names the competitor they recommended |
| 9 | Converting terms with no page | Ads → SEO/GEO | Turns the search terms that sell into the next pages to write |
Each job is a question with a fixed set of answers. If the answer has to be written, it belongs to an LLM.
Quick answer: Jev for ads and SEO/GEO means using TypeSafe's decision model for the high-volume judgment steps in ads and SEO/GEO. 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 search-term triage, then creative tagging. 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. Search-term triage
Question: "Is this query from a buyer, a researcher, a job seeker, a competitor search or junk?" Answer type: Choice. Next: Auto-negative above the threshold, approval queue in the middle band.
The highest-volume job in the ad account: 5,000 to 50,000 rows a month on a mid-size account. The buyer rows are also the input to job 9. Detail in Jev for Google Ads.
2. Creative tagging
Question: "Which hook, format, offer and awareness stage does this ad use?" Answer type: Choice ×4. Next: Performance grouped by tag, for your ads and your competitors'.
One state, four questions, one call. This is the job in the 724-ads demo. Detail in Jev for Meta Ads.
3. Landing page match
Question: "Does this page deliver what the ad or the search result promised?" Answer type: Score. Next: Low scores are fixed before spend.
The one check paid and organic share outright. The same scorer runs on ad final URLs and on the pages ranking for your top Search Console queries.
4. 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 15 candidates per page and Jev judges each pair. This is the 586-page demo. Detail in Jev for SEO.
5. Cannibalization
Question: "Do these two URLs answer the same search intent?" Answer type: Noul. Next: Yes pairs become the merge and redirect list.
Keyword overlap in Search Console finds the candidate pairs, and the intent judgment is Jev's. Merged pages also give the ads one clear final URL per intent.
6. Thin-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 pages. Run it before the sitemap, because a spam update applies the same test afterwards.
7. Citation checks
Question: "Is our brand recommended in this AI answer?" Answer type: Noul. Next: Citation share per engine, per query cluster, per week.
Collecting answers from ChatGPT, Gemini and Perplexity is an API and scraping job. Judging them is the expensive part today. At this price a 40-query tracker becomes a 4,000-query tracker. Detail in Jev for GEO.
8. Who got cited instead
Question: "Which of these competitors does the answer recommend?" Answer type: Choice. Next: A share-of-answer table by competitor.
Same state as job 7, second question, same call. Put the table next to auction insights and you see whether the competitors outbidding you are also the ones the engines recommend.
9. Converting terms with no page
Question: "Do any of our pages answer this converting search term?" Answer type: Choice (URL or none). Next: The none rows become the content calendar.
This job joins the two sides. Paid search already shows which questions lead to a sale. Each one without a matching page is a brief for organic and AI search, ranked by the conversions it has already produced.
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 |
|---|---|---|---|
| Search-term triage | 20,000 terms | ~1.6M | ~$0.07 |
| Internal link map | 586 pages × 15 candidates | ~5M | ~$0.21 (published demo) |
| Citation checks | 4,000 answers × 4 engines | ~10M | ~$0.42 |
| Converting terms with no page | 2,000 terms × 10 candidate URLs | ~0.6M | ~$0.03 |
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 ads, pages and answer-first rewrites, for diagnosing a drop once it is routed, and for every explanation a client reads. Keep a human on budgets and bids over 20%, edits to pages that make money, and any reply posted in a community.
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.
Alex M.
VP Growth
Multi-Brand Ecommerce Group
We had five channels and five people each defending their own budget. Handing allocation to Ryze AI cut blended CAC 27% in a quarter — not because the bidding got smarter, but because money finally moved to whichever channel was winning that week.”
27%
Blended CAC reduction
5
Channels automated
12 weeks
To full autonomy
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. The Ryze AI MCP for Google Ads, Meta Ads and Search Console 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.
- Simulated demos: the videos on this page are simulated runs built by Ryze AI. The counters and costs on screen are illustrative, not measured.
- Disclosure: Ryze AI publishes this blog and does not run Jev in production as of 2026-09-20.
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 ads and SEO/GEO?
Jev is a decision model from TypeSafe AI, released in early access on September 15, 2026. Used for ads and SEO/GEO, 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.
Can one Jev setup cover both paid ads and SEO/GEO?
Yes. The loop, the API and the three question types are the same for every job on this page. Only the collection step changes: the Google Ads and Meta APIs for the ad account, Search Console and a crawler for the site, and the engines' answers for GEO. Labels and thresholds are per job, so hand-label 500 rows for each one you turn on.
Which job comes first if I run both ads and SEO?
Start with search-term triage in Google Ads. It has the most rows and the clearest labels, and its output feeds the organic side: the buyer terms that convert and have no matching page become the content calendar for SEO and AI search. That gives you one labeled dataset that pays off in both channels before you add a second job.
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 ads and SEO/GEO?
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 ads and SEO/GEO, 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
