add_task
ChatGPTAdd 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 add_test_block for uploaded 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_test_block
ChatGPTAdd one AI task (website or prototype), Survey, Accessibility or Card sorting block. Prefer add_task for website tasks. Follow the block schema; AI fields belong inside configuration. Omit id to generate a block ID server-side; returns blockId and the saved draft. Omit position to append. Use existing assets; never invent credentials. Returns current draft. No launch.
create_audience
ChatGPTCreate 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
ChatGPTCreate 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 generate synthetic AI tester profiles, not recruit people. Returns the created audience plus the freshly generated testers.
create_block_test
ChatGPTCreate a draft with a title and optional initial definition containing known blocks and audience. Omit definition for an empty draft. Returns the saved draft and URL. Never launches or spends test credits.
create_livepage_test
ChatGPTCreate, configure, and launch an unmoderated livepages test in the caller's Uxia workspace in a single call. Use this after picking an audience (see list_audiences) to run AI testers against a live URL. Get four fields right: scenario (who the tester is and why they are here), mission (the single concrete action they take in the product), stopCondition (the observable on-screen state that ends the session), and questions (what the researcher wants to learn afterwards — judgments, comparisons, drop-off analysis go HERE, not in mission). IMPORTANT: this launches immediately and spends real credits — each tester costs 25 credits, so the test costs (the audience's tester count) × 25 (check the audience size with get_audience and the balance with get_credits). Draft the four fields, tell the user the expected cost, and get explicit confirmation before calling this tool. Returns the new testId, a url deep link to open the test in Uxia, and a creditsMessage reporting credits used and remaining; consider sharing the url with the user as a clickable link.
get_audience
ChatGPTSummarize the AUDIENCE of the current test: how many testers took part, the gender split (how many women vs men), the age range and average, and demographic breakdowns (industry, role, country, nationality, languages, employment status, marital status, education level, tech literacy) computed over the actual testers. Also returns the originally configured audience targeting (the description and filters the test was set up with). Use this for questions about who the testers are as a GROUP — e.g. "how many testers were involved", "how many women vs men", "what are the demographics of the audience", "what's the age range". For one specific tester by name, use get_tester instead. Scoped to this test only.
get_audience
ChatGPTRead audience targeting and demographic breakdowns computed over the actual participants in this test. Use get_tester for one participant. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
get_card_sorting_results
ChatGPTRead results for a Card sorting block: categories with their cards and agreement, where each card was placed, the most related card pairs (similarity) and every participant's sort with reasons. Agreement is the share of participants who sorted a card into a category, out of everyone who sorted that card. Similar participant-created category names are grouped. participantType defaults to ai (latest run, or runId); human reads completed human sessions.
get_credits
ChatGPTReturn the caller's workspace credit balance: plan, total credits, credits used, and credits remaining (remainingCredits is null when the plan has unlimited credits). Livepages tests cost 25 credits per tester — call this to check the balance before launching a test.
get_credits
ChatGPTRead available credits and usage.
get_frame_details
ChatGPTRead one gallery frame using frameNumber from finding evidence. Includes one available image preview of the requested gallery capture, including merged captures. 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_human_navigation_summary
ChatGPTHeadline navigation KPIs for the REAL HUMAN participants (not the AI testers) — the figures shown on the product's Human Insights tab: number of human participants, task success rate, drop-off rate, misclick rate, and average session duration in seconds. Call this for any question about how the human/live/moderated/real participants performed overall, OR to report how many human participants there were. This is distinct from get_navigation_summary, which reports the AI testers.
get_human_navigation_summary
ChatGPTRead aggregate navigation metrics for human sessions. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
get_human_session
ChatGPTRead one human-participant recording session as raw data: the post-test answered questions and the talk-aloud transcript text. The ref is what list_human_sessions returns (format: 'human_session:<id>'). The answered questions are always returned in full; paginate the transcript via offset+limit (chars) if it is long.
get_human_session
ChatGPTRead a human session, task and transcript by exact ref. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
get_insight
ChatGPTGet full detail for one insight by its ref. The ref is the string returned by list_insights (format: 'insight:<number>'). Returns title, description, evidence quotes, fix suggestion, and impact fields. If insight_details are paywalled for this viewer, evidence and fix explanation will be redacted.
get_insight
ChatGPTRead 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_market_research_summary
ChatGPTRead the market research summary for a test.
get_navigation_summary
ChatGPTHeadline navigation KPIs. For clickable-prototype tests: success rate, drop-off rate, misclick rate, average attempts per step, and step counts. For live (livepages) tests: success rate, drop-off rate, and step counts (average/min/max) PLUS a per-tester step breakdown — use this to answer 'how many steps did <tester> take'; misclick and attempt metrics are not available on live tests. Call this first when the user asks broad navigation questions ('how did the test go', 'overall results').
get_navigation_summary
ChatGPTRead aggregate navigation and completion metrics. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
get_optimization_score
ChatGPTReturns the Usability Optimization Score (UoS, 0–100) for a test — Uxia's proprietary whole-flow UX score derived from the test's issues (weighted by relevance), tester count normalization, and user-satisfaction ratings — plus its qualitative label (Partial/Good/Very Good/Excellent), a breakdown of the contributing issue counts (high/medium/low) and per-area satisfaction scores, and an about field explaining what the score means, how to read the bands, and how it helps compare different flows tested with similar audiences. Call this when the user asks how the test scored overall, e.g. 'what's the optimization score', 'how usable is this', or 'what's the overall result'. This is NOT the UXIA-Q satisfaction score (0–5) — for UXIA-Q or SUS call get_satisfaction_score instead.
get_optimization_score
ChatGPTRead optimization score and contributing factors. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
get_question_responses
ChatGPTRead participant responses for a market-research question using its exact ref.
get_satisfaction_score
ChatGPTReturns the self-reported satisfaction scores for a test: the overall UXIA-Q score (0–5, the average of four pillars — usability, trust, appearance, loyalty), each pillar score, and the SUS (System Usability Scale, 0–100 with a letter grade) when computed, plus an about field explaining what these scores mean. Call this when the user asks about the UXIA-Q score, a satisfaction pillar, the SUS score, or what those scores mean (e.g. 'what's the UXIA-Q score', 'how do testers rate trust', 'what's the SUS', 'what does this score mean'). This is NOT the Usability Optimisation Score (0–100, computed from issues) — for that call get_optimization_score. If a score is null it was not computed for this test; say so rather than substituting another metric.
get_satisfaction_score
ChatGPTRead satisfaction score and contributing factors. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
get_screen_details
ChatGPTDrill into one screen by frame index: aggregated metrics, any loop activity, and a per-tester list with visits, misclicks, and their last action on that screen. Each tester entry includes a 'transcript:<id>' ref the user can click to open the full transcript. Use this after list_screen_metrics or list_dropoff_points has pointed at a specific screen.
get_screen_details
ChatGPTRead one screen and its metrics using frameIndex from navigation results. Includes one available screenshot preview of the requested screen. Prototype screen indexes are zero-based; live gallery frame numbers are one-based. 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_strengths
ChatGPTSummarise the test's strengths — the things testers responded well to, found easy, or appreciated — by analysing the testers' post-test reflections together with the test's satisfaction scores. Call this when the user asks for strong points, strengths, positives, what worked well, or what testers liked. Returns strength themes, each with a short description and the supporting testers (with a transcript reference per tester). If there are no tester reflections, it reports that none are available rather than inventing positives.
get_strengths
ChatGPTRead positive findings supported by participant evidence. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
get_success_criterion
ChatGPTRead an accessibility criterion and its evidence using scId from list_success_criteria. Includes up to three available image previews of affected accessibility 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_test
ChatGPTGet metadata for one test in the caller's workspace by its id (obtain the id from list_tests). Returns title, goal, status, type, source, creation date, a 'url' deep link to open the test in Uxia (consider sharing this 'url' with the user as a clickable link), and 'hasResults' — only when hasResults=true will the per-test analytics tools (list_insights, get_insight, etc.) return data for this test.
get_test
ChatGPTRead 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_definition
ChatGPTRead the current draft, revision, validation and editability before editing. Includes ordered blocks and audience; excludes credential secrets.
get_test_progress
ChatGPTRead run status, progress and credit usage. Omit runId for the latest run.
get_test_question_responses
ChatGPTGet one real AI tester's individual post-test answer for a single post-test question, plus that question's response/clustering context. Each individual tester answer includes a stable quote ref. Pass testerName only when it is an actual tester name returned by list_test_questions.testerNames; never pass placeholders like "all", "everyone", or "testers". For all tester responses, call list_test_questions, then call this tool once per listed testerName for each relevant question. For one tester's answers across all post-test questions, call list_test_questions, then call this tool once per listed question with testerName set to that tester. Do not use transcript tools for post-test response requests. Pass the "ref" string exactly as list_test_questions returned it; do NOT construct the ref yourself or derive it from the question number.
get_test_question_responses
ChatGPTRead typed participant answers for one Survey question, using its exact ref. Optionally filter by a real testerName returned by list_test_questions. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
get_test_report
ChatGPTRead the saved report for the whole test: introduction, study goals, audiences, task summaries, key findings, supporting surveys and selected participant quotes, or the A/B comparison report. Use when asked about the report or its conclusions. This is a generated snapshot, not fresh analysis. Does not generate or refresh a report. Does not require a blockId. If available=false, explain that no report has been generated; use evidence tools for analysis instead.
get_test_setup
ChatGPTGet the current test setup: title, goal, scenario/context shown to testers, and the configured post-test questions. Use this when the caller asks for the test scenario, test context, mission setup, goal, or configured questions for a specific test.
get_test_setup
ChatGPTGet the current test setup: title, task (the concrete action the tester performs), scenario (the situational framing shown to testers), and configured post-test questions. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
get_test_summary
ChatGPTRead a usability-results overview: test metadata, top five findings, optimization and satisfaction scores, strengths and navigation metrics. Optional runId and blockId scope the results. Missing, restricted or not-yet-ready sections are marked unavailable; ambiguous block selection returns references for follow-up. Does not launch or modify tests.
get_tester
ChatGPTFetch one AI tester's full profile by name (age, demographics, role, psychological profile) and render it as a tester card. Match is case-insensitive and partial. Use when the user asks about a specific tester by name — e.g. "tell me about Sarah", "who is tester X", "show me X's profile". Tester names come from list_insights / list_transcripts. If several testers match the name it returns candidate names to disambiguate; if none match it reports that and lists the available testers. Scoped to this test's testers only.
get_tester
ChatGPTRead a participant profile using a tester name from the results. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
get_transcript
ChatGPTRead a single tester transcript as plain text. The ref is what list_transcripts returns (format: 'transcript:<id>'). Paginate via offset+limit (chars) if the transcript is long.
get_transcript
ChatGPTRead a session transcript by exact ref from list_transcripts. Paginate long transcripts with offset and limit in characters. For post-test answers, use get_test_question_responses. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
launch_test
ChatGPTLaunch 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.
list_accessibility_tests
ChatGPTList accessibility tests with IDs and status.
list_audiences
ChatGPTList 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
ChatGPTList 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_dropoff_points
ChatGPTScreens where testers stopped progressing, ranked by how many testers dropped off there. Use this for 'where did testers drop off', 'where did people get lost', 'which screen lost the most testers'. Each point includes the absolute count, the share of all testers, and how many distinct drop-off paths end on that screen.
list_dropoff_points
ChatGPTList screens where participants stopped progressing, ranked by drop-off count, including share of all testers and distinct drop-off paths. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
list_human_sessions
ChatGPTList the real human-participant recording sessions for this test (talk-aloud transcripts + post-test answered questions). These are actual people who took the test, distinct from the AI testers covered by list_transcripts. Returns lightweight summaries; call get_human_session with a returned ref to read a session's full transcript and answers.
list_human_sessions
ChatGPTList human sessions with exact refs and completion status. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
list_insights
ChatGPTList insights (UX issues) found in this test, sorted by severity (high → prototype). ONE call returns all severities together — do NOT call this multiple times to iterate per severity or per category. For 'top N insights' just call with the appropriate limit. Use the severity or category filters only when the user asks for a specific slice. To answer 'what did <AI tester> flag / raise as issues?', pass that tester's name in the optional testerName filter — it keeps only insights where one of the supporting quotes is attributed to that tester (case-insensitive, partial match). Omit it to list across all testers (never pass a blank value or a group word like 'human'). This covers AI testers only; for a human participant use get_human_session. If unsure of the exact tester names, call list_transcripts first. Call get_insight with a returned 'ref' for full evidence. Severity values: high | medium | low | prototype.
list_insights
ChatGPTList 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_loop_screens
ChatGPTScreens that testers came back to after navigating away — a signal of confusion, dead-ends, or testers backtracking to look for something. Use this for 'what screens caused loops', 'where did people go in circles', 'screens with backtracking'. A revisit is counted when a tester returns to a screen they had previously left.
list_loop_screens
ChatGPTList screens participants returned to after leaving, indicating backtracking or possible confusion. A revisit means returning to a previously left screen. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
list_paths
ChatGPTList the distinct paths testers took, sorted by how many testers followed each path. Use this for 'most common path', 'what paths did testers follow', 'what paths did the ones who dropped off take'. Each path is a sequence of screens/pages with completion/drop-off counts. Filter by status ('success' or 'drop-off') for drop-off-specific queries. On live (livepages) tests, paths are the page sequences testers visited (labeled by page title/URL) and misclick/attempt figures are omitted; filtering status='drop-off' shows which page sequences ended in a drop-off.
list_paths
ChatGPTList navigation paths and participant counts. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
list_screen_metrics
ChatGPTPer-screen navigation metrics (misclick rate, average attempts, total clicks, testers reached), sortable. Use this for 'which screens had the most misclicks', 'which screen was hardest to use', 'screens with the most attempts'. Pass sortBy to pick the ranking dimension; default is misclick rate descending.
list_screen_metrics
ChatGPTList per-screen misclick rate, average attempts, total clicks and testers reached. Use sortBy to select the ranking; default is misclickRate descending. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
list_success_criteria
ChatGPTList accessibility criteria, status and exact refs. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
list_test_blocks
ChatGPTList ordered blocks, statuses and exact block/run IDs for result queries.
list_test_questions
ChatGPTList post-test questions asked at the end of the study, with the count of tester responses each received and the tester names that answered each question. In this product, "tester responses", "all tester responses", "question responses", and "what did testers answer?" mean these post-test question answers by default. Each question has a 1-based "number" — the position the user sees, so the user's "question 1" / "Q1" is the item with number 1. To show tester responses, call get_test_question_responses with this tool's exact question ref and a real testerName from testerNames. For all tester responses, call get_test_question_responses once per testerName; never pass placeholders like "all", "everyone", or "testers" as testerName. Never build the ref yourself from the question number. Do not use transcript tools for response/answer requests.
list_test_questions
ChatGPTList questions in one Survey block with exact refs, types, response counts and tester names. Legacy tests return their existing post-test questions. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
list_tests
ChatGPTList usability tests in the caller's workspace, most recent first. Use this to find a test's id before calling the per-test tools (list_insights, get_insight, etc.), which require a testId. Pass 'query' to search by title (case-insensitive substring), 'status' to filter, and 'limit' to cap results. Each result includes 'hasResults' — only tests with hasResults=true can be analyzed by the per-test tools — and a 'url' deep link to open the test in Uxia (consider sharing this 'url' with the user as a clickable link).
list_tests
ChatGPTList tests in workspaces the caller can access, newest first. Optionally search titles with query, filter status, and limit results. Returns test metadata, Uxia links, result flags and the total matching count; does not return findings or session data.
list_transcripts
ChatGPTList AI-tester task-session transcripts (one per tester) with step counts. This is for session steps, clicks, reasoning, expectations, and screen-by-screen behavior — NOT post-test question answers. For "tester responses", "all tester responses", "question responses", or "what did testers answer?", use list_test_questions and get_test_question_responses instead. Pass the optional testerName filter (case-insensitive, partial) to narrow to a single tester — e.g. 'why did Carlos click X' is { testerName: 'Carlos' }; omit it to list every tester. Use get_transcript with a returned ref to read the full text.
list_transcripts
ChatGPTList AI-tester session transcripts with exact refs and step counts for clicks, reasoning and screen-by-screen behavior. For post-test answers, use list_test_questions and get_test_question_responses. testerName is an optional case-insensitive partial-name filter; omit to list all testers. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
prepare_test_block
ChatGPTCollect up to two missing wording fields for an existing task. Uses forms when supported; otherwise ask returned questions in chat and report that no form appeared. Read-only: save accepted wording with update_task. Never include secrets or treat answers as launch approval.
preview_test_launch
ChatGPTPreview the saved revision’s sequence, participants, costs and blockers. Present costs for explicit approval before launch_test. Any edit requires a new preview and approval.
remove_test_block
ChatGPTRemove a draft block by ID. Clear dependent browser continuations first. Preserves other blocks and audience. No launch.
reorder_test_blocks
ChatGPTReorder using every block ID exactly once. Order controls execution and survey scope. Invalid browser continuations are rejected. No launch.
review_test
ChatGPTOpen the draft review card. Retained for existing clients; get_test_definition also includes this card. Reads the saved draft without edits or launch.
search_quotes
ChatGPTSearch the AI testers' quotes (the automated testers that ran the flow) across all insights and any standalone user_quotes, for a substring (case-insensitive). AI TESTERS ONLY: this does NOT cover human-participant sessions — for anything a human/real participant said, use get_human_session, never this tool. query is the TOPIC only — what was said (e.g. 'payment gateway', 'CTA'); do NOT put a tester's name in query. To restrict results to one AI tester, pass their name in the separate optional testerName filter (case-insensitive, partial); omit it to search across all testers (never pass a blank value or a group word like 'human'). So 'what did Jaime say about the payment gateway?' is { query: 'payment gateway', testerName: 'Jaime' }. Returns matched quotes with the source insight ref where applicable.
search_quotes
ChatGPTSearch participant quotes; preserve attribution and wording. Use IDs from list_test_blocks to target a block/run; omission uses the documented defaults. Legacy tests also supported.
set_block_continuation
ChatGPTResume a task from the nearest preceding website task with the same URL. Use null to clear. Both blocks must exist in this draft; cannot join separate tests or launched runs.
set_survey
ChatGPTAdd or replace a Survey block’s questions. Omit blockId to append with a server-assigned ID, or use an existing Survey ID to edit. Returns blockId for new surveys. Other blocks are preserved. No launch.
set_test_audience
ChatGPTReplace shared audience selections and participant counts; null clears. Use existing audience/tester IDs. Preserves blocks. No launch.
set_test_construction
ChatGPTRecord pending wording or user-supplied/delegated decisions. Set surveyChoice=no_questions when requested. Accept proposals with matching wording in update_test_block. Not launch approval; never include secrets.
update_task
ChatGPTEdit task/scenario/stopCondition wording by blockId. Only supplied fields change; all other settings are preserved. Empty strings clear wording. Use update_test_block for experience or credential changes. 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.
update_test_block
ChatGPTAdvanced: replace one complete block, preserving its ID, type and all unchanged settings. Prefer update_task for task wording. Read get_test_definition first. Other blocks are preserved. No launch.
update_test_definition
ChatGPTAdvanced: replace the COMPLETE definition. Preserve unchanged blocks, IDs, audience and browserContinuation.fromBlockId. Prefer targeted edits. No launch.
