Jev Agent

From the Jev Agent team: we built this platform for tasks where a score against specific criteria is easier to review than another page of AI advice.

Evaluate an essay draft, compare a resume with a job description, or define your own rubric. Browser tools show the criteria; teachers can review batch results and export scores to CSV. REST API and seven hosted MCP tools support structured judgments in applications and agent workflows.

The essay grader offers three trials without an account. Further usage requires credits; authenticated API and MCP evaluations require a Jev Agent key. Jev Agent is independent of TypeSafe AI. Scores are AI estimates that need human review, especially for education and hiring decisions.

We would love feedback on the rubric editing experience and which evaluation workflows would be most useful to you.