Uxia

Add a website task or empty task to an existing draft. Omit blockId; the server generates and returns it. Use the returned ID for later edits. Flat fields; no configuration object. Omit wording only for an intentionally incomplete draft. Supply url for a website task; isPrototype defaults to false for a regular website. Set isPrototype=true for a prototype website. stopCondition requires url. Use find_operations for prototypes or advanced settings. No launch. The concrete action the tester performs in the product. When drafting or suggesting wording, write one short sentence, usually 10–25 words: [action verb] + [single concrete target] + [essential method or constraint]. Describe one coherent goal; naturally paired actions are fine, but split independent goals into separate tasks. If multiple items could match, identify one by name or position; avoid "any item". Name the in-app mechanism when needed. Keep motivation and backstory in scenario, observable completion criteria in stopCondition, and judgments or research objectives in follow-up survey questions. Omit step-by-step navigation and unnecessary detail. Example: "Book a table for 2 at Bar Mut for tonight at 8:00 PM." Preserve supplied or accepted wording unless the user requests a rewrite or delegates wording choices. When drafting or suggesting scenario wording, write 1–3 short sentences in second person, present tense ("You are…", "You have…"). Describe a believable situation and a concrete triggering moment explaining why the tester needs to act now. Keep the action in the task; do not repeat it here. Example: "It is Friday evening, you are exhausted from work, and you do not want to cook tonight." Preserve supplied or accepted wording unless the user requests a rewrite or delegates wording choices. When drafting or suggesting stopCondition wording, write one short sentence starting with "Stop when". Name one observable on-screen state detectable from a screenshot or DOM that marks the task’s natural completion. Avoid alternative endings, user feelings and off-screen events such as receiving an email; do not stop mid-flow. Example: "Stop when the order confirmation page displays the order number and total amount." Preserve supplied or accepted wording unless the user requests a rewrite or delegates wording choices.

add_task

Create a new audience in the caller's Uxia workspace and synchronously generate AI testers for it. An audience defines targeting filters (age, gender, geography, demographics) used to recruit testers. Returns the created audience plus the freshly generated testers.

create_audience

Create an empty draft from a title; then add_task and set_test_audience. Returns the draft revision and app URL. No launch.

create_block_test

Read a finding by exact ref from list_insights, including evidence quotes, impact and fix suggestions with recommendations, acceptance criteria and coding-agent prompts when available. Paywalled details may be redacted. Includes up to three available screenshot previews of referenced frames. Use get_frame_details for additional frames. Images may be unavailable. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.

get_insight

Read metadata for one accessible test using testId from list_tests: title, goal, status, type, source, creation date, version, result flag and Uxia link. Does not return findings, screenshots or session data; use result tools for those.

get_test

Read the current draft, revision, validation and editability before editing. Includes ordered blocks and audience; excludes credential secrets.

get_test_definition

Read run status, progress and credit usage. Omit runId for the latest run.

get_test_progress

Launch the previewed revision and spend credits. Requires explicit approval of preview_test_launch costs; maximumCharge is that approved amount. Cost changes require new approval. Locks the definition. On success, show a clickable link using the returned url; do not display backend run/test IDs.

launch_test

List up to 10 audiences in the caller's Uxia workspace. Use this to discover existing audiences before creating a new one, to reference an audience by id in another action, or to summarize the workspace's targeting setup.

list_audiences

List findings ranked by severity. Omit blockId for top insights across all AI task blocks; limit applies globally. Supply blockId for one task. Keep returned block/run IDs with evidence. One call includes all severities; do not iterate per severity or category. Use severity/category filters only when requested. testerName filters AI-tester evidence by name; use list_transcripts for names and get_human_session for human participants. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.

list_insights