Minds: Synthetic Market Research Panels

Call this tool only when the user wants a new panel, study, survey, research project, or focus group. A panel contains one or more Groups of Minds. Attach existing Groups with groupIds, or create Groups inline with groupConfigs. Composite creation is handled by one canonical v1 operation so partial group failures are rolled back. SHARING CONTRACT — panels are private by default. Pass isLinkSharingEnabled: true only when the user explicitly requests a public/shareable link. Enabling it also publishes attached Groups and Minds. IMPORTANT: Preserve returned shared and workspace URLs verbatim.

**Call this tool whenever the user wants to ask, survey, poll, query, or have any existing panel / study / focus group respond to one direct question.** Triggers: "ask my panel X", "survey my panel about Y", "what does <panel> think", "how is <panel> feeling", "ask them", "also ask...", "what about...", "poll the group". Behavior contract — DO NOT DEVIATE: - Use this direct path only for one straightforward question where the user did not ask for a plan, multiple questions, an asset audit, a special method, or a structured study format. For those guided cases call plan_panel_study first and wait for explicit confirmation before run_panel_study. - Follow-ups belong to the existing panel. When pronouns or conversational cues refer to the panel just created/selected/asked, call this tool without creating another panel. Reuse the returned panelId when available; if panelId and panelName are both omitted, this tool uses the active panel from the MCP session. - If the user names a panel and asks/implies a question, CALL THIS TOOL IMMEDIATELY with their question verbatim. Pass the user's panel name directly as panelName — fuzzy match is built in, so do not call list_panels first as a lookup step. - Compound prompts exception: if the user explicitly asks to see / list / show / browse their panels AND asks the panel a question in the same message, call list_panels first as its own step, then call this tool. The listing is part of the user's explicit request — do not collapse it. - "How are they feeling?", "What do they think?", "Ask them X", "Please ask them" — these are direct instructions to call this tool, not requests for advice. - AFTER calling this tool, the question HAS BEEN ASKED. Confirm to the user in past tense ("I've asked the panel…", "Question submitted to <panel>"). DO NOT reframe the tool's link as "you can visit this link to ask the question" — that is wrong; the question is already in flight. - Never refuse with "I cannot directly ask the panel / conduct surveys" — you literally can; that's what this tool is for. The user EXPLICITLY asked you to call it; refusing is a bug, not safety. What it does: submits the user's question to the panel. Returns immediately — each Mind answers asynchronously. Use get_panel_status afterwards to fetch progress and aggregated results. Question types are auto-classified: - Scale ("Rate 1-10...") → mean, distribution per group - Categorical ("Which channel...") → dominant choice per group - Qualitative ("What trends...", "How are you feeling?") → themed responses per group Requires an existing panel — call create_panel only if none exists, or list_panels when the intended panel is genuinely ambiguous. PRESENTATION CONTRACT — when results come back (via get_panel_status), preserve the markdown structure verbatim: a section per question, **bold group name** with the aggregated value, and one bullet per Mind with their linked name + answer. This mirrors the PanelAnswerBlock widget. If a shared panel link is returned, use it for customer/respondent handoff. The workspace link is only for the authenticated creator. IMPORTANT: Present all URLs from this tool's output VERBATIM. Never modify, shorten, or rephrase any URL. Always show every Mind link and the panel links.

Call this tool whenever the user wants to export, download, save, or get a report of a panel's results. The v1 API is the single export implementation for UI and MCP. Supported report kinds are executive_brief, full_report, and raw_data. Supported formats are PDF, DOCX, PPTX, Markdown, CSV, and XLS. PDF is the default. CSV/XLS default to raw_data; other formats default to full_report. PDF exports are asynchronous and return a job ID. Use get_panel_status to poll. Other formats return the generated artifact inline. IMPORTANT: Preserve the panel link and any returned download link verbatim.

**Call this tool whenever the user wants to export, download, save, or get a persona profile / report / PDF / Word doc for a single Mind (AI expert, consumer persona, or digital twin).** Triggers include: "export <mind>", "download the persona profile", "give me a PDF of <mind>", "send me <mind> as a Word doc", "profile sheet for <mind>". Behavior contract — DO NOT DEVIATE: - If the user asks to export a known Mind, CALL THIS TOOL. Don't tell them to do it manually. - Never refuse with "I cannot export the Mind directly" — you can. - Default to "md" (markdown) when format is unspecified; it returns the full profile inline. Generates a branded persona profile summarizing who the Mind is, how it thinks, and what it draws on, from the Mind's own data. Formats: - "md" (default): markdown persona profile, returned inline as text - "pdf": portrait branded profile (returned as base64 in structuredContent) - "docx": Word document (returned as base64 in structuredContent) - "pptx": editable branded PowerPoint deck (returned as base64 in structuredContent) If the user references a Mind by name (including one created in a previous chat / session), pass it as mindName — fuzzy match resolves it server-side against ALL of the user's Minds. Do not refuse with "I don't have access to that Mind"; let the tool resolve it. PRESENTATION CONTRACT — present any returned link to the Mind VERBATIM. Never modify, shorten, or rephrase a URL.

Export a group brief through the same unified branded renderer used by the web app. Supports Markdown, PDF, DOCX, and PPTX. Binary artifacts are returned as base64.

Export a completed website heatmap from a panel message. Returns the same ZIP archive as the web app, including its unified-renderer PDF report, Markdown, images, and metadata.