Jev for marketing: 8 use cases and an honest list of limits
Jev launched on September 15, 2026 and X filled with demos within three days: 724 ads broken down in 40 seconds for 9 cents, 586 pages of internal links mapped in 45 seconds for 21 cents, 700 outreach messages scored for 9 cents. Here is what the model is, the 8 marketing jobs it fits, and what those demos leave out. 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.
Used by 2,000+ marketers
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.
Jev on 724 live ads in 40 seconds
Matthew Berman ran Jev on 724 live ads from 37 brands. In 40 seconds it labelled every hook, format, offer, CTA and awareness stage, and flagged the landing pages that did not match the ad, for about 9 cents of tokens. This is the job most ad teams do by hand once a quarter, if at all.
What Jev looks like on a real account: 2 demos
Two recordings on sample accounts, one for ads and one for the site. Same three steps each time: pull the data, let Jev score every row, hand the winners to an LLM. The counters on screen are examples, not measurements.
Meta Ads: find what competitors keep running, then write ads like it
Jev reads 1,600 competitor ads, works out which styles keep running, and scores new briefs in those styles. Whole run: about $0.71.
- Pull 1,600 competitor ads from the Meta Ad Library.
- Tag each ad by type (talking head, myth-buster, price anchor) and check how long it stayed live. Ads that survive 60 days are the ones making money.
- Write and score. An LLM drafts new briefs in the winning styles; Jev scores each on hook, brand fit and how likely it is to survive.
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.
Ryze AI — Autonomous Marketing
Try Jev-powered AI Marketer
- Jev makes the small decisions, Ryze AI makes the change
- Connect Google Ads, Meta, GA4 and Search Console
- Free to connect, flat fee for autopilot
2,000+
Marketers
$500M+
Ad spend
23
Countries
The 8 jobs at a glance
Marketing teams use LLMs for two different things and pay the same price for both. One is generation: copy, briefs, reports. The other is thousands of tiny decisions where nothing needs to be written: which bucket, how relevant, yes or no. Jev only does the second, and prices it as if it were a database query.
- 1Search terms and negativesChoice
Question Jev answers: Buyer, researcher, job seeker, competitor or junk?
What happens next: Auto-negative, queue or drop by confidence
- 2Ad creative taggingChoice ×4
Question Jev answers: Hook, format, offer, awareness stage?
What happens next: Performance and competitors grouped by tag
- 3Internal link mapNoul
Question Jev answers: Is there an honest reason to link this page to that one?
What happens next: Links inserted above the threshold
- 4AI citation checksNoul
Question Jev answers: Is our brand recommended in this AI answer?
What happens next: Citation share tracked across thousands of answers
- 5Lead scoring and routingScore + Choice
Question Jev answers: Score this lead against the ICP and pick the owner
What happens next: Sales gets the top band, the rest goes to nurture
- 6Review and survey themesChoice
Question Jev answers: Which of our 12 themes does this response belong to?
What happens next: A theme chart your team can trust, on every response
- 7Content QA gateNoul ×20
Question Jev answers: Does this draft meet each of the 20 points on the checklist?
What happens next: Only passing drafts reach an editor
- 8Model routingChoice
Question Jev answers: Does this task need a frontier model, a small model or no model?
What happens next: The cheapest sufficient model handles each task
| # | Job | Answer type | Question Jev answers | What happens next |
|---|---|---|---|---|
| 1 | Search terms and negatives | Choice | Buyer, researcher, job seeker, competitor or junk? | Auto-negative, queue or drop by confidence |
| 2 | Ad creative tagging | Choice ×4 | Hook, format, offer, awareness stage? | Performance and competitors grouped by tag |
| 3 | Internal link map | Noul | Is there an honest reason to link this page to that one? | Links inserted above the threshold |
| 4 | AI citation checks | Noul | Is our brand recommended in this AI answer? | Citation share tracked across thousands of answers |
| 5 | Lead scoring and routing | Score + Choice | Score this lead against the ICP and pick the owner | Sales gets the top band, the rest goes to nurture |
| 6 | Review and survey themes | Choice | Which of our 12 themes does this response belong to? | A theme chart your team can trust, on every response |
| 7 | Content QA gate | Noul ×20 | Does this draft meet each of the 20 points on the checklist? | Only passing drafts reach an editor |
| 8 | Model routing | Choice | Does this task need a frontier model, a small model or no model? | The cheapest sufficient model handles each task |
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 marketing means using TypeSafe's decision model for the high-volume judgment steps in marketing. 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 terms and negatives, then ad 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.
Question types
- What TypeSafe reports
- Choice (pick one option), Score (a number in a range), Noul (a yes/no probability)
Price
- What TypeSafe reports
- $0.042 per 1M input tokens. Output is free. Roughly $0.0004 per decision
Latency
- What TypeSafe reports
- 70 to 500 ms per call, all answers returned in one parallel pass
Structured-output errors
- What TypeSafe reports
- 0%, because the output is schema-constrained
Accuracy on TypeSafe's 4-workflow benchmark
- What TypeSafe reports
- Jev 67.8%, Claude Opus 5 73.1%, GPT-5.6 Sol 74.1%
Access
- What TypeSafe reports
- Waitlist. Early users on X report approval the same day or the next
What it cannot do
- What TypeSafe reports
- Write text, code or a rationale. It gives a number and no explanation
| 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 8 jobs, one by one
1. Search terms and negatives
Question: "Buyer, researcher, job seeker, competitor or junk?" Answer type: Choice. Next: Auto-negative, queue or drop by confidence.
Paid search. Detail in Jev for Google Ads.
2. Ad creative tagging
Question: "Hook, format, offer, awareness stage?" Answer type: Choice ×4. Next: Performance and competitors grouped by tag.
Paid social. Detail in Jev for Meta Ads.
3. Internal link map
Question: "Is there an honest reason to link this page to that one?" Answer type: Noul. Next: Links inserted above the threshold.
SEO. This is the 586-page demo from Distribb's founder. Detail in Jev for SEO.
4. AI citation checks
Question: "Is our brand recommended in this AI answer?" Answer type: Noul. Next: Citation share tracked across thousands of answers.
GEO. Detail in Jev for GEO.
5. Lead scoring and routing
Question: "Score this lead against the ICP and pick the owner" Answer type: Score + Choice. Next: Sales gets the top band, the rest goes to nurture.
The 700-lead demo on X is this job. Two questions in one call.
6. Review and survey themes
Question: "Which of our 12 themes does this response belong to?" Answer type: Choice. Next: A theme chart your team can trust, on every response.
Most teams sample 200 responses. At this price you read all of them.
7. Content QA gate
Question: "Does this draft meet each of the 20 points on the checklist?" Answer type: Noul ×20. Next: Only passing drafts reach an editor.
A verification layer on AI-written content: claims supported, no placeholder text, answers the query.
8. Model routing
Question: "Does this task need a frontier model, a small model or no model?" Answer type: Choice. Next: The cheapest sufficient model handles each task.
A decision about decisions. It is where most of the savings in an agent stack come from.
Free SEO/GEO audit
- Surface technical SEO issues
- Spot quick wins
- Find duplicate and thin pages
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.
Search-term triage
- Rows
- 20,000 terms
- Approx. input tokens
- ~1.6M
- Cost at $0.042 per 1M
- ~$0.07
Survey themes
- Rows
- 10,000 responses
- Approx. input tokens
- ~1M
- Cost at $0.042 per 1M
- ~$0.04
Content QA
- Rows
- 200 drafts × 20 checks
- Approx. input tokens
- ~0.6M
- Cost at $0.042 per 1M
- ~$0.03
| Job | Rows | Approx. input tokens | Cost at $0.042 per 1M |
|---|---|---|---|
| Search-term triage | 20,000 terms | ~1.6M | ~$0.07 |
| Survey themes | 10,000 responses | ~1M | ~$0.04 |
| Content QA | 200 drafts × 20 checks | ~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 anything a person reads: ads, pages, briefs, client reports and the reason behind a change. Keep people on budgets, pricing, positioning and anything that is hard to undo.
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 gives Claude, ChatGPT, Cursor and Grok live access to the account, so the collect step is one prompt.
If you want the documentation behind this, the Ryze help center has pages on what Ryze AI is and AI ad management across Google, Meta, TikTok and LinkedIn.
