> ## Documentation Index > Fetch the complete documentation index at: https://docs.noxus.ai/llms.txt > Use this file to discover all available pages before exploring further. # Agent Tests > Check how an agent handles the conversations that matter, version by version The **Tests** tab of an agent holds scripted conversations the agent must handle, each with the checks its reply must pass. Run them on a saved version before you publish it, and see at a glance whether a change helped or broke something. ## Where tests come from Most tests start from a real conversation. * **From a past chat.** Open a chat in **Past chats**, then click **Test this reply** under any agent reply. The chat before that message becomes the test's context, the message becomes the test's first user message, and the reply itself is never copied into the test. Add the checks that say what the agent should have done, pick a test set (it starts on the set you last opened on this agent, or **New test set**), and save. * **With Genie.** On an agent with no tests and at least one chat, **Ask Genie to set up tests** opens Genie with a request for tests from the agent's recent and thumbs-down chats already written. Send it, and approve what Genie asks to approve. * **By hand.** **New test** on a test set opens an empty test. Write the user messages in order, save, then add its checks. ## The Tests page The Tests page is a table of the agent's test sets. Each row shows the set's score (the pass rate of its latest run), the change in pass rate against the version it ran on before, how many tests regressed (passed before, not now), its number of tests, the average time and cost of a test, and when and on which version it last ran. A regression shows in red, so a set that got worse stands out. Cost shows only to members who can see conversation costs. Click a row to open the set. **Run** on a row runs it, and the row's menu has **Ask Genie why it fails** and **Delete**. ## Comparing two versions A set opens on a comparison: a **Baseline** version and a **Candidate** version. The candidate is the latest run and the baseline the run before it on another version; pick any other run in either picker. The choice stays in the address, so a reload or a shared link shows the same comparison. Under the pickers, a summary shows the candidate's pass rate, average time and average cost per test, each with its change against the baseline, and a verdict: how many tests regressed and improved. **Show** filters the tests to those that regressed, improved, stayed the same or are failing; regressed tests come first. Each test row shows its outcome on both versions, its time and its cost (each with its change against the baseline; the cost only for members who can see conversation costs), and its first failing check; click it to open the test, and use its **...** menu to run, duplicate or delete it. Below it, **History** lists each version with its pass rate on its newest complete run, oldest first; hover a version to read its changelog, and click it to compare it with the version before. ## A test A test opens in two columns, under the same two pickers as its set. * **On the left, the conversation.** Each user message and the agent's reply on the candidate version, rendered as a chat. **Side by side** in the test's toolbar puts the baseline's conversation beside it. A test made from a past chat shows that chat above the first message, and **Open the chat** opens the source. **Edit messages**, in the toolbar's **...** menu, lets you add, remove, reorder and rewrite the user messages; leaving with unsaved changes asks first. * **On the right, the checks.** Each check of this test with its result on both versions and the candidate's reason (the judge's reason for a judge check). A failed check offers **Ask Genie why it failed**. **Add a check** opens the catalogue, and each check can be edited or removed on its own. A check is named from what it checks (for example **Mentions bank transfer**); rewrite its **Name** in the form to call it something else, and that name shows on the set and in results. The checks grade the whole conversation once, after the last reply. Every check belongs to one test: changing or removing it never touches another test, and a test can hold the same kind of check twice with different values. **Run this test** runs it alone on the current version. The replies and results fill in as it runs, and the new run becomes the candidate. ## Checks Fourteen checks in four groups: | Group | Checks | | - | - | | Response | Meets expectation (an AI judge), Says / does not say, Similar to reference answer, Correct against expected answer | | Knowledge | Grounded in knowledge base, Had enough evidence, Refuses when it should, Cites its sources, Retrieved the required documents, Searched the right knowledge base | | Tools | Tool called / not called, With these arguments, Used the tool result correctly | | Combine | Any of / All of | Tool names and arguments come from the tools the agent's model sees. Knowledge base checks use the agent's knowledge bases; a required document that is no longer in its knowledge base gives "could not evaluate", never a failure. ## Running a set **Run** on a set opens a dialog to pick the version (the current version or a saved one). It counts the tests and user messages that will run, names any test that has no check yet, estimates the run's cost from the last run's average cost per test, and reminds you that the agent's tools run for real. After you start it, the set opens with the new run as the candidate, and its results fill in as each test finishes. ## Genie Where Genie is available, it is offered on the thing it can help with: **Ask Genie to set up tests** on an agent with chats but no tests, **Ask Genie why it fails** on a set whose latest run has a failing test, and **Ask Genie why it failed** on a failed check. Each opens Genie with the request already written, naming the set, the test or the check and the versions; send it when you are ready. ## Outcomes | Outcome | Meaning | | - | - | | Passed | Every check passed | | Failed | At least one check failed | | Could not evaluate | A check or the agent errored | | Not applicable | No check applied | This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.