Use free Jev to decide where a support ticket belongs, how urgent it is, or how frustrated the customer sounds—then take the same judgment into your code.
A support ticket needs a destination. With Choice, you define the possible answers and Jev returns a judgment across those options. The result gives your code a named answer to work with instead of a paragraph to interpret.
Read the probabilities alongside the selected answer. They show how the model weighs the available answers for this question and input. They do not certify that a ticket belongs to a particular team. A vague question or overlapping categories can still lead to an unhelpful decision.
Keep the raw response when you want to inspect exactly what was returned. Jev evaluates text; it does not write a reply to the customer or explain its reasoning. You decide what your application does next, including when a person should review the judgment.
Try Jev online with the same message and three different questions. You can see what changes when you ask for a category, a yes/no judgment, or a score without learning a new scenario each time.
Which team should handle this support ticket?
Ask which team should handle the message. Use Billing, Technical, and Account as the possible destinations, with a short definition for each. This is useful when your next step depends on a specific category.
Does this message describe a problem that needs attention today?
A deadline can matter even when the message sounds polite. Ask about urgency separately from the team assignment so your code can treat the two decisions differently. The probability describes the model's judgment about this question; it is not permission to escalate automatically.
How frustrated does the customer sound?
Use a defined scale when a degree is more useful than a category. Read the score against those definitions, rather than treating it as an objective measurement of the customer.
Each example asks a separate question about the same fictional ticket. Output formats shown for illustration.
Follow a fictional support ticket from input to judgment. Each published example includes its question and the actual response from a FreeJev run, so you can inspect what the model returned.
Run the ticket above to inspect your own result. Published examples here pair a fictional input with its question and a recorded Jev response.
No recorded judgments are available yet. Your inputs and responses are not published by default.
The ticket is a starting point. Try free Jev with a task where you already know the answers your software can act on. Define the question and categories in terms that make sense for your workflow.
Your feedback list mixes bug reports, feature requests, and general comments. Ask which kind of feedback a message contains, with a definition for each category. Your code can use the answer to suggest a destination for review.
You have a reading list and a specific topic in mind. Ask how relevant an article is to that topic on a defined scale. Use the judgment to help prioritize what you read, then inspect the source before relying on it.
Your application receives requests that belong in different flows. Define the handlers as answer options and ask which one fits the input. Keep the model's classification separate from your code's checks and permission to act.
Illustrative workflows · Not recorded judgments
Once a question makes sense in the Jev playground, keep its definition. Export the configuration or copy the corresponding API example, then use a FreeJev key to connect your own environment.
Start with an example, then edit the text, question, and answer definitions for your task.
Reuse the question and output definition instead of rewriting them for every entry point.
Sign in to create a key for calls from your code or Agent.
Follow the API, CLI, MCP, or skill instructions for the environment you use.
{
"format": "freejev-design-draft-v1",
"type": "Choice",
"question": "Which team should handle this support ticket?",
"outputDefinition": {
"kind": "Choice",
"options": [
{
"label": "Billing",
"definition": "Invoices, payments, subscriptions, or refunds."
},
{
"label": "Technical",
"definition": "Errors or product features that are not working."
},
{
"label": "Account",
"definition": "Login, access, or account settings."
}
]
}
}Use the API from an application.
Developer access is not available yet. Published endpoints and setup instructions will appear when access is ready.
The CLI, MCP, and skill clients are open source. They share the same judgment configuration and account allowance, so changing how you call Jev does not create a separate quota. Reusing a configuration also does not promise an identical answer on every run.
Use your Jev playground configuration with the API, CLI, MCP, and skill →FreeJev lets you try Jev on text judgments in your browser. Ask for a category, a yes/no decision, or a score, inspect the response, and reuse the configuration in your own development workflow. Start with the support ticket if you want to see the input, question, and answer definition together.
No. Jev makes structured judgments; it does not generate free-form text or reasoning explanations. Use Choice for named alternatives, Yes/No for a binary question, and Score for a defined scale. Your application decides what to do with the returned judgment.
No. A probability expresses the model’s judgment for the supplied input and question. It is not a correctness guarantee. Inspect ambiguous cases, keep your own permission checks, and decide when human review is needed before connecting a result to an action.
Without signing in, you get 50 playground runs per day. A signed-in account gets 1,000,000 input tokens per day, shared across its API, CLI, MCP, and skill calls. Input tokens measure text sent to the model; they are not a fixed number of runs. Allowances reset daily on a UTC schedule. Creating another key does not add quota. If you use the allowance, wait for its next reset. Free access is offered with these limits, without a promise of permanent free access.
You do not need either to run the anonymous playground. Sign in and create a FreeJev key when you want to call from your own code, CLI, or Agent. Keep that key private. Installing the skill alone does not authenticate your calls.
Yes. Export the judgment configuration or copy its API example, then follow the developer instructions. The same question and output definition carry into your workflow. The CLI, MCP, and skill clients are open source; your account and shared usage allowance still apply to calls made through them.
Your inputs and responses are not published by default. The example judgments use fictional inputs selected for demonstration. Jev calls use a remote model service, so do not treat the playground as local-only processing. Leave out secrets and private customer information, and review the Privacy Policy before submitting sensitive text.
No. FreeJev is an independent third-party tool, not the official TypeSafe or OpenRouter service. It provides its own playground and developer access under its stated limits. Review the Terms for the rules that apply to using FreeJev.
Try free Jev with the support ticket or your own text, inspect the result, and keep the configuration for your workflow.
Run Jev50 free runs a day without signing in. No credit card required.