Start a Voxli AI chat from Home or any page without linking anything first. Your question can name an agent, scenario, folder, date, metric, personality, or a value your agent reports in a tool call or event, such as the model it used. Voxli AI finds the matching runs, tests, and comparisons in your workspace and links them to the chat. It can also put two agents side by side on the tests they both ran and rank results to answer questions such as which agent is fastest.
Home now shows Recent: the three latest runs and the three comparisons you opened most recently, newest first. Below it, type a question to open the Voxli AI panel with your question already sent. The agent picker and scenario score cards are no longer on Home; run history stays in Results.
When a test ends in Error because its conversation couldn't run, its page now shows the reason, such as the HTTP status your agent returned, a reply timeout, or an agent Voxli couldn't reach. GitHub and Local runners still report their own failures, though a GitHub workflow that can't start now shows its HTTP status. Voxli AI sees the same reason. In Voxli MCP, get_run and get_test_results return it as error, and so does GET /test-results/{id} in the API. When you step through a run's tests, these tests now sort with the failures instead of after the passes.
Voxli MCP's new list_runs tool pages through runs newest first, filtered by scenario, agent, creator, or status. Each item is one scenario and personality within a run, with its score, who started it, and the run_group_id to pass to get_run_group. Scheduled runs stay out unless include_scheduled is true. To wait on a run, get_run_group with status_only=true returns only run_group_id, done, and pending_results, so your assistant can check every 15 to 30 seconds.
Run actions open a New run page, filled in from your scenario, test, previous run, or comparison. Turn on Advanced to pick several scenarios, choose tests and personalities, repeat each test up to 10 times, or compare up to 6 agents. The start bar shows how many tests and conversations will run.
Run a test
Save a setup in New run so anyone in your workspace can reuse its scenarios, tests, personalities, and repeats. Workspace members can rename, update, or archive presets. Pick an agent each time you start it.
Compare puts up to 6 runs side by side against a base you choose. Add existing runs or start new ones, then reorder or remove columns; the picker leaves out scheduled runs. Save for team keeps the comparison in Saved comparisons; use Copy link to share it with your workspace. Comparisons can also be renamed or duplicated.
Compare agents
In test conversations, the tester follows your instructions more consistently, including when you choose a personality. This reduces early endings and replies that include things your instructions prohibit.
In the API, GET /runs/ accepts a scenario filter and multiple comma-separated status values. Use changedSince with an ISO 8601 timestamp to retrieve runs started after that time together with unfinished runs, narrowed by your other filters.
In test conversations, the tester answers when your agent asks for missing information, instead of skipping to the next step. Tester-written replies follow the personality selected for the run; exact scripted lines stay unchanged.
Through Voxli MCP, your AI assistant can get guides for writing and improving tests, writing assertions, interpreting results, and setting up local testing. Use get_voxli_guide(topic) without installing the separate Voxli skill.
Connect your assistant through Voxli MCPThrough Voxli MCP, use try_test_assertions(result_id, assertions) to try up to 10 new assertions against a completed test's conversation. Try Test Assertions returns a pass or fail with an explanation for each, without changing the saved test or recorded result.
Use Retry in a Test results row's menu to retry a test in a canceled run or one stuck as pending or running. A retry starts a fresh conversation for the same test case; a canceled run reopens until the replacement finishes.
In a scenario's advanced launch options, select multiple personalities to create a separate run for each one. The dialog opens the first run; Results lists the rest.
Voxli MCP's Retry Test Results replaces retry_test_result(test_result_id) with retry_test_results(result_ids) for batches from one run and agent. The retried response maps each result_id to its new_result_id.
Cancel run in Test results stops pending and running tests for every agent type. A conversation already in progress ends at the next turn.
Retry in a Test results row's menu works for Running and Pending results too. Results in a canceled run can't be retried.
From Compare, New comparison opens a full page with searchable scenarios and a folder tree. With the search cleared, check a folder to include all its scenarios.
In a test result's Hallucinations section, Ask Voxli AI about this claim prepares a question you can edit and send. The chat includes the claim's verdict and available evidence, including supported and rule-dropped claims.
Claims in Hallucinations better preserve the chatbot's uncertainty, approximations, and conditions. Hallucination checks also recognize buttons, links, and cards rendered in the same reply as evidence for claims about those elements.
In a test result's Hallucinations section, expand an Unsupported claim to see why it was flagged. New flags can include the reason for the verdict; claims without a saved reason get an explanation when you expand them. The explanation is also available through Voxli MCP's get_test_results with claims included.
Tests follow your instructions more closely when a run uses a personality. Personality changes apply to the tester's voice while the behavior being checked stays the same.
Read the Personalities guideThe sidebar separates My scenarios from Shared folders. From a scenario's Organize & share dialog, use Shared folder in New folder or Edit folder to list a folder for the workspace.
Read the Folders guide
Every workspace can start and continue interactive tests through Voxli MCP. Use run_interactive_test, send_interactive_test_message, get_interactive_test, and invoke_interactive_test_action to run a session, send messages, read it, and invoke actions.
In Settings, Credits counts 1 credit per Voxli AI message and per interactive message to a demo agent. Voxli AI messages use a credit even if the reply ends in an error.
Use Copy link to chat in Voxli AI to share a transcript with anyone in your workspace who has the link. They can choose Continue chat to make their own copy.
On Results, use Started by anyone to pick a teammate, or uncheck Show scheduled runs to hide scheduled runs. Share or bookmark the URL to keep that filtered view.
In Settings > Metrics, enable Hallucination rate or Hedged hallucinations under Metrics strip and Result lists. The rate measures flagged claims as a share of checked claims after exclusion rules; the hedged count tracks flagged claims phrased with uncertainty.
Claim lists include a Hedged label for flagged claims phrased with uncertainty. New detection and re-grounding add these labels; earlier results aren't labeled automatically.
On completed runs and comparisons, choose Detect hallucinations to check the agent's claims. Manage Exclusion rules in Settings > Hallucinations.
Read the Hallucination Detection guideOpen Voxli AI from the top bar to ask about runs, comparisons, and test results, and pin context while navigating. Connect your own assistant in the panel gives you an MCP prompt for the selected context or helps set up the connection.
See Voxli AI on the product pageGetting started walks you through Connect an agent, Create a scenario, and Run a test. Admins can use Run smoke test to check their agent's connection with a Connection check scenario.
Create your first scenarioThe new Scenarios page lists active scenarios with Run history and Last activity. Use the folder chips to browse, search by scenario or folder name, and click a row to open a scenario.
Open Local agents in the top bar to see which agents are Online or Offline. Select an online agent to open its runs, or an offline one for recovery help.
Before the conversation ends, set completionMode to manual on a client-driven test result to attach metrics, tool calls, or events afterward. Call POST /test-results/{id}/finish when it's ready to score.
See the manual completion stepsUse a recorded message's id to update its metadata or insert another conversation message through the API. Make these writes before scoring starts; they can't add or change recorded actions.
Update and insert messagesOpen a test result or edit a test from a scenario, run report, or Compare report without leaving the page underneath. Closing returns to the same scroll position and expanded rows.
Through Voxli MCP, Get Compare and Get Run show test repeat outcomes, failed assertions with explanations, and metrics for a comparison or a single run. The reports leave unevaluated repeats unscored and omit metrics with no data.
Connect your assistant through Voxli MCP