User Intuition

Search the panel targeting catalog by name or category. Use its qualification and option IDs when configuring a panel study. The full study response also resolves saved targeting to readable labels; age bands can be approximate.

List bounded delivery attempts, status codes, and coarse failure reasons without payloads.

List account webhooks and their study scopes. Signing secrets are never included.

Pause a study while preserving its panel survey, target cycle, progress, and reward hold.

Queue one research-design turn that may fetch a researcher-provided concept URL and use an external analysis model. A 2026 Tasks client receives a durable task and polls tasks/get; other clients receive a job ID and poll get_customize_study_job. Then call get_study and show the full saved plan for human review. Reuse an idempotency_key after an uncertain response. Native concept images require the synchronous customize_study tool.

Queue an editable PowerPoint deck from the latest saved report. Common text identifiers are masked by default. Poll get_report_slide_job for a private download URL, which expires after 15 minutes. The export is retained for seven days.

Queue a chat turn immediately. For study findings, feedback, comparisons and quotations, use this tool with primary File Search and verified quotations. Resolve ambiguous study names first. Reuse the selected Hub session; if absent create one with create_research_session and a stable retry key, inspect sources and add only missing requested studies. Do not resync unchanged sources or broaden the session silently. After completion always call view_research_answer to display the answer and clickable quote/recording cards inside this conversation, without redirecting to a dashboard; preserve the answer and citation labels. Poll inspect_research_session view=job. Set parent_job_id for a follow-up in the same session. Reuse the same idempotency_key and prompt after a timeout; sync and async share the job.

Use report_video for Highlights: generate one retained MP4 from the studies' default reports, with branded logo bookends, learning-goal chapters and their cited Quotes. Repeated requests return the saved video. No evidence selection is needed. Also supports an editable PowerPoint, an individual audio clip or a legacy audio reel ZIP from a completed/partial Hub run. Use exact evidence_ids returned by get_research_analysis highlights; presentations include all findings. Audio requires explicit export instruction. Text masking defaults on. Poll get_research_deliverable or tasks/get for Tasks clients. Private links last 15 minutes; temporary audio and presentation files expire in seven days; report videos are retained while their source remains available. Reuse the idempotency key after a timeout.

Replace the external-panel entry token for an owned BYOP study. The old provider link stops working immediately; update the provider with the returned entry_url. Supply a unique idempotency_key and reuse it after an uncertain response; inspect the current link with get_external_panel if the replay is stale.

Remove one source from a Hub session by the opaque ID returned by inspect_research_session. The underlying study or uploaded file is not deleted.

Remove one study source from a Hub session; the underlying study remains available in User Intuition.

Rename an existing Studio output in its session. Default reports cannot be renamed. Read the output first.

Rename one organization Hub session without changing its sources or analysis.

Resume a paused or partial durable analysis run with an additional call allowance. Poll get_research_analysis for the updated result.

Resume a paused study and continue its preserved panel recruitment.

Open an interactive, read-only view of the saved study plan and current fielding progress. The view does not approve a plan or launch recruitment. Ask the human for approval separately before fieldwork.

Replace a webhook signing secret. The new secret is shown only in this response; update the receiver before relying on further deliveries.

Search one or more studies. Results are grouped under studies[] with each study_id, index_status (ready, updating, or not_indexed), latest_report_id, indexed_report_id, and matching canonical content. No generated prose is returned. Pass next_cursor back with the same query, filters, and limit to continue; stop when it is null.

Send the configured incentive to a BYOP participant when the human requests it. No separate MCP App approval is required. Reuse idempotency_key on uncertain retries; the backend prevents duplicate rewards for an already-paid participant.

Start a durable analysis across the session sources. exhaustive processes every eligible interview; quick retrieves verified evidence through File Search; aggregate computes exact counts; explore runs bounded computation. Poll get_research_analysis. Prefer chat_research_session or queue_research_chat for questions and generate_research_output for saved outputs. Completed or partial runs can produce presentations, clips or reels; retain coverage and limitations. Reuse the idempotency key on uncertain retries.

Stop panel recruitment, close the target cycle, and settle/release the active reward hold. Call only after the human explicitly chooses to end this study's fieldwork.

Submit a low-incidence, large, or specialized audience for manual feasibility review when direct panel launch is unavailable. This creates a review request, not a paid launch. Provide the target audience, target count, and incidence rate in percentage points; optionally link an accessible study. Use list_feasibility_requests or get_feasibility_request to follow its status.

Add or resync one study in a Hub session. Inspect existing sources and add only the study the user requested.

Send a signed test event containing no participant or study data. This makes an outbound request to the registered URL.

Change the email or CRM fields on one BYOP invitation with PATCH. Call get_participant first to verify the intended participant. Send email=null only when the user explicitly wants to clear it. Pass only fields to change.

PATCH ordinary study metadata only. Use customize_study—not this tool—for the research plan, audience targeting, screener questions, concept links, or concept images. Only supplied fields change. Active panel studies must be paused or stopped first. Call get_study first.

Attach external evidence to an organization Hub session: TXT, Markdown, CSV, JSON, text PDF or DOCX, up to 10 MB. Send user-provided file bytes as base64. Uploading again creates another source; list sources after an uncertain response before retrying.

Upload a template up to 5 MB: report Markdown/TXT/DOCX with {{title}} and/or {{findings}} placeholders; presentation 16:9 PPTX theme/layout. Send raw file bytes as base64; pass the returned template id to generate_research_output. Repeated uploads create separate templates.

Show the full answer in this MCP chat with clickable verified quotes and original recordings. Always use this App after research chat; never substitute an external dashboard link. Use after chat_research_session or queue_research_chat; pending jobs can be checked here. Keep session_id and job_id for follow-ups. Set reference_label to read one cited quotation and its transcript/recording context. Preserves backend citation labels; never invent sources.