Generate tests from your documents. Experts approve them.
Suites of single-turn prompts, scripted and simulated multi-turn conversations, task tests with expected tool calls and outcomes, adversarial attacks, fairness pairs and language-parity tests — generated from approved knowledge or built from templates, and approved by subject-matter experts before they run.
Test design · included from the Team plan
What it does
- Generate prompts and expected answers from approved passages: factual, procedural, eligibility, out-of-scope, paraphrase, misspelling, adversarial and Spanish
- Nothing generated runs until an SME approves, edits or rejects it
- Scripted conversations with checks on every turn, and simulated users with goals, styles and languages
- Task tests: expected tool calls in order, arguments, tools it must never call, and end-state checks
- Fairness pairs that change one detail about a person and compare the answers
- A template library with prompts, expected outcomes, scoring dimensions and evaluation notes
- Import and export as CSV, Excel, JSON or YAML
Works with
- Agents & environments
Every agent, every platform, tested the same way.
- Knowledge sources
Test against the sources of truth your agents use.
See test design with your data
We’ll connect a test environment of your agent and a few of your policy documents for the demo.
Request a demo