labvanced logoLabVanced
Contact
    • Remote Physiological Measurements
    • Eye Tracking
    • Head & Face-Tracking
    • Emotion Detection
    • Heart Rate Detection (rPPG)
    • Generative AI
    • Audio Transcription
    • EEG & Hardware Integrations
    • Decision Making
    • Reaction Times
    • Keyboard Inputs
    • Mouse Tracking
    • Mobile / Touch
    • Questionnaires
    • Gamepad / Joystick Integration
    • Audio Recordings
    • Audio Transcription
    • Video Recordings
    • Screen Recordings
    • Photos / Snapshots
    • Video Conferencing
    • Canvas Drawings
    • Build with AI
    • Build with Spreadsheets
    • Using the Experiment Editor
    • Coding
    • Creating Questionnaires
    • Balancing & Randomization
    • UX & Website Testing
    • Single Session Studies
    • Factorial Designs
    • Longitudinal & Multi-session Studies
    • Individual & Case Studies
    • Real-time Multi-user Studies
    • Interviews & Video Calls
    • Surveys & Questionnaires
    • Experience Sampling & Diaries
    • Classroom & Group Testing
    • Interventions & Clinical Trials
    • In the Browser
    • Mobile App
    • Desktop App
    • WebBridge Chrome Extension
    • Stroop Test
    • Flanker Task
    • N-back Task
    • Implicit Association Test
    • Trail Making Test
    • Digit Span
    • Corsi Block Tapping
    • Tower of London
    • Balloon Analog Risk Task
    • Preferential Looking
    • Browse more →
    • DASS-21
    • GAD-7
    • Rosenberg Self-Esteem Scale
    • PHQ-9
    • Ten-Item Personality Inventory
    • Big Five Personality Test
    • Adult ADHD Self-Report Scale
    • Browse more →
    • Building a Multi-user Study
    • Webcam Eye Tracking with AOIs
    • Website Frame Eye Tracking
    • Conditional Eye Tracking Opt-in
    • ChatGPT Study
    • Desktop App Study with EEG
    • Between-subjects Group Balancing
    • Building a Reading Study
    • Stroop Task
    • Lexical Decision Task
    • Browse more →
    Public Experiment Library
    • Arts Research
    • Clinical Psychology & Neuropsychology Medicine
    • Cognitive Psychology
    • Developmental Psychology
    • Behavioral Economics & Decision Science
    • Educational Research & Psychology
    • HCI & Human Factors
    • Linguistics & Language Sciences
    • Consumer & Marketing Research
    • Social & Personality Psychology
    • Sport & Movement Science
    • UX & Website Testing
    • Executive Functions
    • Language & Reading
    • Decision-Making & Reasoning
    • Attention
    • Overview
    • HCI & Human Factors
    • UX & Website Testing
    • Consumer & Marketing Research
    • White-Label App
    • PageGazer
    • Webcam vs. Lab Eye Tracking in InfantsAnna Banki & Gabriela Markova
    • Eye Tracking for Influencer MarketingDr. Alexander Edeling
    • Eye Tracking Infant Word ComprehensionDr. Giulia Calignano
    • Sentence Reading and Grammar JudgmentsDr. Jonathan Mirault
    • Regulating Emotions with MusicDr. Katrin Starcke
    • Game-Based Grammar Learning in ChildrenDr. Mireia Marimon
    • Gaze Cueing and AutismMax Soares Miehstein
    • Personality and Hearing in NoiseDr. Malte Wöstmann
    • All interviews →
    • Lab Notes
    • How to Cite Labvanced
    • Labvanced Platform Paper (2017)
    • Webcam Eye Tracking Validation (2024)
    • Webcam Eye Tracking Studies
    • Cognitive Psychology Studies
    • Developmental Psychology Studies
    • Linguistics Studies
    • See all publications →
    • Getting Started
    • Guide
    • Video Tutorials
    • Walkthroughs
    • Live Chat
    • Webinars & Onboarding Calls
    • AI Assistant
    • FAQ
    • Importing Templates Guide
    • Test Templates
    • Live Eye Tracking Metrics
    • Mouse Tracking Demo
    • ChatGPT Demo
    • Audio Recording Object Demo
    • Adding Image Stimuli Demo
    • Score & Feedback Demo
    • Browse all technical demos →
    • Timing Precision
    • Stimuli Presentation
    • Headphone Checks
    • Bot Checks
    • Participant Management
    • Comparisons
    • Research Blog
    • Prolific Integration
    • CloudResearch Integration
    • Sona Systems Integration
    • BeSample Integration
    • Panelabs Integration
    • Clickworker Integration
    • Labvanced Webhook API
    • Labvanced REST API
    • About Us
    • Newsletter Archive
    • Terms & Conditions
    • Data Security & Data Privacy
    • Technical & Organisational Measures
    • Accessibility
    • W-8BEN-E Form
    • Data Processing Agreement Template
    LinkedInYouTubeDiscord
    • Individual
    • Lab
    • Department / Consortium
    • Teaching
    • Campus
    • Commercial
    Top-Ups
    • Overview
    • Study Building
    • Subject Recruitment
    • Dedicated Support
    Checkout
  • Contact
    • EN
      • 中國人
      • Deutsch
      • Français
      • Español
      • English
      • 日本語
    • Appgo to app icon
    • Loginlogin icon
    Platform
    Labvanced makes it easy to implement the most advanced study design and reliably collect your data.
    Biosignals & AI
    Remote Physiological MeasurementsEye TrackingHead & Face-TrackingEmotion DetectionHeart Rate Detection (rPPG)Generative AIAudio TranscriptionEEG & Hardware Integrations
    Behavioral Recordings
    Decision MakingReaction TimesKeyboard InputsMouse TrackingMobile / TouchQuestionnairesGamepad / Joystick Integration
    Media Recordings
    Audio RecordingsAudio TranscriptionVideo RecordingsScreen RecordingsPhotos / SnapshotsVideo ConferencingCanvas Drawings
    Implementation Techniques
    Build with AIBuild with SpreadsheetsUsing the Experiment EditorCodingCreating QuestionnairesBalancing & RandomizationUX & Website Testing
    Study Formats

    Your study can take whatever format your research needs. Here are a few popular examples.

    Single Session StudiesFactorial DesignsLongitudinal & Multi-session StudiesIndividual & Case StudiesReal-time Multi-user StudiesInterviews & Video CallsSurveys & QuestionnairesExperience Sampling & DiariesClassroom & Group TestingInterventions & Clinical Trials
    Where Studies Run

    Run your study online in the browser, on mobile or tablet with the mobile app, or in-lab with the desktop app.

    In the BrowserMobile AppDesktop AppWebBridge Chrome Extension
    Tests
    Explore cognitive tests, questionnaires, walkthroughs, and our public experiment library: a starting point for your next study.
    Popular Cognitive Tests
    Stroop TestFlanker TaskN-back TaskImplicit Association TestTrail Making TestDigit SpanCorsi Block TappingTower of LondonBalloon Analog Risk TaskPreferential Looking
    Browse more →
    Questionnaires & Scales
    DASS-21GAD-7Rosenberg Self-Esteem ScalePHQ-9Ten-Item Personality InventoryBig Five Personality TestAdult ADHD Self-Report Scale
    Browse more →
    Public Experiment Library

    Take a look at what other researchers in the community are doing through our extensive, open catalog of shared studies.

    Open the public library →
    Walkthroughs

    Step-by-step builds of complete studies, from a blank project to a running experiment, that you can follow along or adapt.

    Building a Multi-user StudyWebcam Eye Tracking with AOIsWebsite Frame Eye TrackingConditional Eye Tracking Opt-inChatGPT StudyDesktop App Study with EEGBetween-subjects Group BalancingBuilding a Reading StudyStroop TaskLexical Decision Task
    Browse more →
    Research
    One platform for students, academics, and industry researchers studying human behavior.
    Harvard UniversityStanford UniversityCambridge UniversityUCLNYUMax Planck InstituteUCLATU Munich

    Trusted by researchers at 1,500+ universities worldwide

    Academic Research
    Arts ResearchClinical Psychology & Neuropsychology MedicineCognitive PsychologyDevelopmental PsychologyBehavioral Economics & Decision ScienceEducational Research & PsychologyHCI & Human FactorsLinguistics & Language SciencesConsumer & Marketing ResearchSocial & Personality PsychologySport & Movement ScienceUX & Website Testing
    Research Areas
    Executive FunctionsLanguage & ReadingDecision-Making & ReasoningAttention
    Industry / Commercial
    OverviewHCI & Human FactorsUX & Website TestingConsumer & Marketing ResearchWhite-Label AppPageGazer
    Researcher Interviews

    Conversations with researchers about the studies they ran with Labvanced, what worked, and what they learned.

    Webcam vs. Lab Eye Tracking in InfantsAnna Banki & Gabriela MarkovaEye Tracking for Influencer MarketingDr. Alexander EdelingEye Tracking Infant Word ComprehensionDr. Giulia CalignanoSentence Reading and Grammar JudgmentsDr. Jonathan MiraultRegulating Emotions with MusicDr. Katrin StarckeGame-Based Grammar Learning in ChildrenDr. Mireia MarimonGaze Cueing and AutismMax Soares MiehsteinPersonality and Hearing in NoiseDr. Malte Wöstmann
    All interviews →
    Our Research
    Lab NotesHow to Cite Labvanced
    Peer Reviewed Studies

    A selection of peer-reviewed work built on Labvanced: our own platform and validation papers, and studies by the research community grouped by area. Hundreds more are listed on the full publications page.

    Labvanced Platform Paper (2017)Webcam Eye Tracking Validation (2024)Webcam Eye Tracking StudiesCognitive Psychology StudiesDevelopmental Psychology StudiesLinguistics Studies
    See all publications →
    Resources
    Valuable resources to help you learn the platform, stay updated, and more.
    Documentation
    Getting StartedGuideVideo TutorialsWalkthroughs
    Support
    Live ChatWebinars & Onboarding CallsAI AssistantFAQ
    Templates & Demos

    These are a few popular examples. Browse our guide and a selection of technical demos to get started with implementation.

    Importing Templates GuideTest TemplatesLive Eye Tracking MetricsMouse Tracking DemoChatGPT DemoAudio Recording Object DemoAdding Image Stimuli DemoScore & Feedback Demo
    Browse all technical demos →
    Methodology
    Timing PrecisionStimuli PresentationHeadphone ChecksBot ChecksParticipant ManagementComparisonsResearch Blog
    Integrations & APIs
    Prolific IntegrationCloudResearch IntegrationSona Systems IntegrationBeSample IntegrationPanelabs IntegrationClickworker IntegrationLabvanced Webhook APILabvanced REST API
    Company & Legal
    About UsNewsletter ArchiveTerms & ConditionsData Security & Data PrivacyTechnical & Organisational MeasuresAccessibilityW-8BEN-E FormData Processing Agreement Template
    LinkedInYouTubeDiscord
    Pricing
    Our licenses and additional services at a glance.
    Licenses
    IndividualLabDepartment / ConsortiumTeachingCampusCommercial
    Top-Ups

    Need more recordings for your lab or your own research? Simply use one of these recording top-up packages.

    Browse top-up packages →
    Additional Services

    Hire Labvanced’s expert team to quickly bring your project to the level of rigor it needs.

    OverviewStudy BuildingSubject RecruitmentDedicated Support
    Checkout

    Ready to purchase a license or top-up? Head straight to checkout.

    Go to checkout →
    • 中國人
    • Deutsch
    • Français
    • Español
    • English
    • 日本語
    • Getting Started
    • Guide
      • GETTING STARTED

        • Task Editor
        • Frames
          • Canvas Frame
          • Page Frame
          • Website Frame
        • Trial Timeline
        • Stimulus Presentation
        • Correctness of Response
        • Objects
        • Events
        • Variables
        • Task Wizard
        • AI Assistant
        • Trial System
        • Experiment Design
          • Creating a Study
          • Importing Templates in Labvanced
          • Data Frame Patterns
          • Multi-user Experiment Design
          • Longitudinal Experiment Design
      • FEATURED TOPICS

        • Randomization & Balance
        • Eye Tracking
          • Presenting Stimuli in an Eye Tracking Task
          • How to Choose Eye Tracking Calibration Settings
          • Setting Up Eye Tracking in a Task
          • Recording and Exporting Gaze Data
          • Using Shapes as Areas of Interest (AOI) for Eye Tracking
          • The Participant Calibration Experience
        • Web Bridge
          • Selecting Website AOIs | Anchor, Adjust, and Verify AOI Tracking
          • Tracking Mouse Behavior on a Website AOI | Web Bridge Guide
        • Questionnaires
        • Desktop App
        • Sample Studies
        • Participant Recruitment
        • API Access
          • REST API
          • Webhook API
          • WebSocket API
        • Other Topics

          • Precise Stimulus Timings
          • Multi User Studies
          • Head Tracking in Labvanced | Guide
      • MAIN APP TABS

        • Overview: Main Tabs
        • Dashboard
        • My Studies
        • Shared Studies
        • My Files
        • Experiment Library
        • My Account
        • License & Services
      • STUDY TABS

        • Overview: Study-Specific Tabs
        • Study Design
          • Tasks
          • Blocks
          • Sessions
          • Groups
        • Task Editor
          • Task Controls
          • The Trial System
          • Frame Types
          • Objects
          • Object Property Tables
          • Variables
          • System Variables Table
          • The Event System
          • Text Editor Functions
          • Eye Tracking Options in the Task Editor
          • Head Tracking in a Task
          • Multi-User Studies
        • Settings
        • Variables
        • Media
        • Texts & Translate
        • Launch & Participate
        • Subject Management
        • Dataview and Export
    • Video Tutorials
      • Video Overview
      • Getting Started in Labvanced
      • Creating Tasks
      • Element Videos
      • Events & Variables
      • Advanced Topics
    • Walkthroughs
      • Introduction
      • Stroop Task
      • Lexical Decision Task
      • Posner Gaze Cueing Task
      • Change Blindness Flicker Paradigm
      • Eye-tracking Sample Study
      • Infant Eye-tracking Study
      • Attentional Capture Study with Mouse Tracking
      • Rapid Serial Visual Presentation
      • ChatGPT Study
      • Eye Tracking Demo: SVGs as AOIs
      • Multi-User Demo: Show Subjects' Cursors
      • Gamepad / Joystick Controller- Basic Set Up
      • Desktop App Study with EEG Integration
      • Between-subjects Group Balancing and Variable Setup
      • Building a Multi-user Study
      • Website Frame Eye Tracking Walkthrough
      • Conditional Webcam Eye Tracking
      • Text Segmentation Study Building
      • Building a Study with AI
    • FAQ
      • Features
      • Support Policy & Guidelines
      • Security & Data Privacy
      • Licensing
      • Precision of Labvanced
      • Programmatic Use & API
      • Using Labvanced Offline
      • Troubleshooting
      • Study Creation Questions
    Illustration of the Labvanced AI Assistant chat in the task editor

    AI Assistant

    The AI Assistant is a chat in the task editor that answers questions about Labvanced and about your own study. It is a Labvanced specialist: it searches the documentation and inspects your study before it answers, so its answers reflect your actual frames, variables, and events. It is a beta feature and can make mistakes, so check what it tells you.

    The assistant can also make changes in the editor, such as building frames and setting up events. It does this only when you ask for a change and allow it. See Making Changes with the AI Assistant at the end of this page.

    For an overview of the feature, see Build with AI. For a worked example, see the Building a Study with the AI Assistant walkthrough.

    Table of Contents

    • Opening the AI Assistant
    • Asking Questions
      • Questions About Labvanced
      • Questions About Your Study
    • Tips for Prompting the AI Assistant
    • Tips for Handling Tool-Call Budgets
    • Making Changes with the AI Assistant
      • What the Assistant Can Build
      • Allowing AI Changes
      • Undo and Turn Off
      • Locked Studies
      • Edit with AI in the Website Code Editor
      • Tips for Building
    • Further Reading

    Opening the AI Assistant

    The assistant sits in the bottom left of the task editor, in the AI Assistant section.

    1. Open your study in the task editor.
    2. Expand the AI Assistant section in the bottom left of the task editor.
    3. Type your message in the Ask a question... field and click Send. Press Enter to send, or Shift + Enter for a new line.

    Other controls in the panel:

    • Open in separate window: the icon in the section header moves the chat into its own window. Close the window with the x in its top corner to return the chat to the panel.
    • Stop: appears in place of Send while the assistant is replying and cancels the reply.
    • New chat: leaves the current chat and starts with a fresh context. The old chat stays stored under Previous chats.
    • Previous chats: opens a list of your earlier chats in this study, with the date and message count of each. Click a chat to continue it, or click the × on a chat to delete it. Chats are saved per study, so a reload or reconnect continues the chat you were in.
    • AI tokens: a meter at the bottom of the panel shows how much of your AI token allowance is used. Hover over it to see This chat, Used, Left, and Context. The Context row shows how much of the assistant's working memory the chat fills.
    • Status dot: green when the panel is connected to the assistant.
    • Continue here: if you open the same chat in another window, the first panel shows This chat is open in another window. Click Continue here to take the chat back.

    Note: when a long chat fills the assistant's working memory, the earlier messages are condensed into a single line, Earlier messages were summarised for the assistant. Click it to see what the assistant remembers. See the prompting tips below for how to keep a chat from reaching that point.

    Asking Questions

    By default the assistant only reads. It answers from two sources and changes nothing in your study.

    • The Labvanced documentation: how features work, which frame, element, or event to use, and how to set something up.
    • Your own study: it can list the elements on a frame, list variables, media files, and event chains, summarize the factors, levels, and trials of a task, and open another frame or task to look at it.

    Note: questions never trigger edits. Only an explicit request for a change makes the assistant ask for permission.

    Questions About Labvanced

    Ask in plain language, the way you would ask a colleague who knows the platform. For example:

    • How do I randomize the order of trials?
    • What is the difference between a canvas frame and a page frame?
    • Which event trigger should I use to react to a keypress?

    Questions About Your Study

    Name the frame, element, or variable you mean, and the assistant looks at it. For example:

    • Which variables does this task record?
    • What does the event on frame 3 do?
    • List the elements on demographics_2.
    • How many trials does this task have, and which factors does it use?

    Because the assistant reads your study directly, these questions work well for orienting yourself in a study you inherited, checking a setup before you launch, and finding out why something behaves the way it does.

    Tips for Prompting the AI Assistant

    The most useful habit is to give the assistant the vocabulary of your study. The assistant does not know your names in advance, and every name it has to look up costs it a step.

    What Matters in Practice

    • Context is the limit: a single long prompt is usually fine. The problem is a long prompt on top of a long conversation. When the context fills up, earlier content gets summarized or dropped, and the assistant can lose track of names and details from the start of the chat.
    • Short and exact beats long and loose: a 300-word prompt with exact names is faster and more reliable than a 3,000-word prompt in prose, because the assistant has to read prose carefully and often re-inspect your study to work out what you want.
    • Structure beats length: use numbered parts, one request per number, and exact element, variable, and frame names.
    • Break at natural boundaries: sending "frame 5 content" and "the event for frame 5" as separate turns is often cheaper than one giant message.
    • Start a new chat for a new project: a fresh conversation resets the context, so long prompts have full room again.
    • Summarize long documents: if the assistant needs to work from a long text such as a questionnaire or an instruction block, the gist plus the key wording is usually enough. If the full text has to be in the study, put it in the frame's content instead of the chat.

    Give the Assistant the Study's Vocabulary

    Name things exactly as they appear in your study:

    • Frames: write on demographics_2 rather than on the second page.
    • Variables: write use exp_videogames, exp_surveys, exp_eyetracking, exp_programming rather than the experience questions. You can read the names in the Variables tab.
    • Elements: write the element age rather than the age question.

    If you do not know a name, say so, and the assistant looks it up.

    Two Things to Know About Its Behavior

    • The assistant changes nothing unless you ask. Questions get answers, only explicit requests lead to edits, and the beta permission card appears once per chat.
    • Uncertainty is reported. If a step failed or could not be verified, the assistant says so. If you want to know what a sub-agent did, ask.

    Tips for Handling Tool-Call Budgets

    Each reply of the assistant can use a fixed number of tool calls, such as inspecting a frame, editing an event, or running a plan. The main chat has 10 per reply, and the sub-agents that make the edits have between 6 and 16. When a reply is nearly out of calls, the assistant is told to stop and write its summary instead of being cut off mid-sentence. The limit is separate from the AI tokens meter. In the demo study, the assistant made its edits but had no calls left to re-check the frame, so it reported the result as not verified visually.

    The Labvanced AI Assistant reporting that it used its tool-call budget before it could re-inspect the frame

    What Uses Up Calls

    Most of the budget goes into finding things out, not into making changes:

    • Inspection calls: listing frame elements, variables, media files, and event chains. On a frame the assistant has not seen, this takes several calls before any work starts.
    • Name lookups: every element, variable, and frame name it needs usually costs a lookup.
    • Long multi-part requests handled step by step instead of as one plan.

    What You Can Do

    1. Give the names you already know. This is the biggest saving. Write use the variables exp_videogames, exp_surveys, exp_eyetracking, exp_programming instead of use the experience questions.
    2. Bundle related things into one request. Requests with three or more parts run as a single plan in which each step gets its own full budget. Add frame 5, put a matrix on it, and add a keypress event is more efficient as one request than as three turns.
    3. Say what does not need checking. Don't bother inspecting, the frame is empty or just replace it lets the assistant skip to the change.
    4. Split build and verify across turns. Ask for Build X in one turn and check X and tell me what's actually there in the next. Verification uses its own calls, and a new turn resets the budget.

    If the Assistant Runs Out

    Continue in a new prompt, because the budget resets every turn. Useful follow-ups:

    • continue where you left off: the assistant picks up the remaining parts.
    • now verify frame 4: a clean, read-only check.
    • you said step 2 was skipped, do it now: the assistant completes the missing step.

    Nothing is lost when the assistant runs out. Whatever already succeeded is saved in your study, and the only risk is that the last part of a multi-part request did not happen, which the assistant flags when it does. Do not over-bundle either: a request with a dozen unrelated items can still run long, and a partial result is reported if the last steps fail.

    Making Changes with the AI Assistant

    When you ask for a change and allow it, the assistant builds directly in the editor. This is a side capability next to the question-and-answer role described above, and it is in beta.

    What the Assistant Can Build

    • Create tasks and set up the frame sequence
    • Build canvas frames, page frames, and custom website frames
    • Add and edit elements, such as text, questions, shapes, and navigation
    • Create variables and events, including events that run JavaScript
    • Set up factors, trial counts, and randomization

    Allowing AI Changes

    1. Ask for a change, for example add a text element with the study instructions and a Next button.
    2. Read the assistant's plan.
    3. Review the Allow AI changes? card, which repeats the change in one sentence and carries the beta badge.
    4. Click Allow AI changes (beta).
    The Allow AI changes beta permission card in the Labvanced AI Assistant panel

    The permission applies to the current chat. After you allow changes, the card shows AI changes allowed in this chat. and a bar above the input reads AI changes allowed.

    Note: questions never trigger edits. Only an explicit request for a change makes the assistant ask for permission.

    Undo and Turn Off

    • Undo: reverts the most recent AI change. Every change the assistant makes goes through the editor's own snapshot system.
    • Turn off: ends write access for the chat. The assistant returns to read-only mode.

    After Turn off, the bar still shows The last AI change can be undone and the Undo button while an AI change can be reverted.

    Locked Studies

    If the study is locked, the editor normally asks for confirmation on every save, which would repeat many times during an AI build. For a locked study, the permission card offers two buttons:

    • Allow AI changes and save anyway (beta): allows changes and saves each one without asking again.
    • Copy study and edit the copy: leaves the locked study untouched and lets the assistant edit a copy.

    Edit with AI in the Website Code Editor

    The Website Code Editor has an Edit with AI button. It opens the same AI Assistant chat beside the code editor, and clicking it counts as your request to change the website code, so it grants write access for that chat. See the Website Frame guide for the editor itself.

    Tips for Building

    These tips apply when you ask the assistant to make changes. The general prompting tips above apply here as well.

    Say What Kind of Thing It Is

    Labvanced has a few distinctions that decide how something is built, and getting them wrong produces the wrong mechanism:

    • Fixed per trial or known at run time: show a red stimulus in the red condition is a modification. show the participant their score is an event. If you are not sure, describe the goal and the assistant picks.
    • Frame type: a Canvas Frame allows free positioning, a Page Frame is a questionnaire-style stack, and a Website Frame holds your own HTML, CSS, and JavaScript. If you want a document-like page, say page frame, otherwise the assistant may build a canvas frame.
    • Recording type: I want every gaze sample and I want the final answer lead to different variable types.

    Describe the Purpose, Not Just the Parts

    Add a text box is ambiguous. Add a text element with the study instructions and a Next button so participants can proceed gives the layout, the content, and the navigation in one request. A stated goal also lets the assistant fill sensible gaps such as labels, required flags, and minimum and maximum values, instead of asking.

    Number Multi-Part Requests

    A request with three or more distinct parts is handled as one plan, and each step gets its own full allowance. Numbered lists map onto that. Three to six related parts per turn is a comfortable size, and a dozen unrelated items risks a partial result at the end.

    Say What Not to Do

    Waive checks you do not need: don't inspect first, the frame is empty, replace whatever is there, I don't care, or just the event, don't touch the layout. This saves steps and gets you to the change faster.

    Check the Result Yourself When It Matters

    When the assistant reports a verified state, it re-read the frame. When it says a step is unverified, it ran out of steps before checking. For anything scientifically load-bearing, such as a scoring formula, a randomization setting, or a recorded variable, open it in the editor, or ask the assistant to verify it in a fresh turn.

    Further Reading

    Illustration of the walkthrough for building a study with the AI Assistant

    Building a Study with AI

    A four-frame study built prompt by prompt.

    Illustration of the task editor in Labvanced

    Task Editor

    The editor the assistant builds in.

    Illustration of working with variables in Labvanced

    Working with Variables

    The names to give the assistant in your prompts.

    Prev
    Task Wizard
    Next
    Trial System