sales-skills/sales-researchgoat

ResearchGOAT Platform Help

ResearchGOAT (researchgoat.com) is a self-serve generative-AI qualitative research tool that runs AI-moderated, real-time voice interviews with real people and returns AI-analyzed insights. You set a research objective; its AI helps design the study (shape the objective, draft a pre-screening/screener survey, and select respondents), an AI interviewer conducts live interviews in any language (laddering and following up like a human moderator), and it synthesizes the transcripts into findings — pitched at up to ~90% lower cost than traditional moderated qual.

Its niche in the real-human AI-moderated-interview cluster (User Intuition, Strella, Voicepanel, Frank, Chikka, AskMore, Listen Labs) is being the end-to-end, voice-first, self-serve option:

• Fuller stack than the lightweight peers. It bundles AI research design + a screener + participant recruitment/selection + AI analysis into one flow — closer to a design→recruit→interview→analyze suite than to a bring-your-own-participants share-link tool (Frank, AskMore, Chikka bring their own audience).
• Voice-first and multilingual. Live AI voice interviews in any language — the depth of a spoken answer, not a written form (contrast text-first AskMore).
• Self-serve, minute-metered, with a free tier. Billing is in AI interview-minutes (free tier includes a project and free minutes/month), so a solo maker can start today — the opposite of demo-gated Listen Labs / Voicepanel.

Two things to say almost every time:

• It's real people, but a stated "I'd pay" is still not a purchase. Real interviews beat synthetic signal (genuine reasoning, objections, language) — but the willingness-to-pay go/no-go belongs to a real behavior test (pre-sale, smoke test), not an interview transcript. Route that to /sales-idea-validation.
• It's UI-only — no public API, webhooks, or MCP surfaced. Data-out is manual export. "Call the ResearchGOAT API / fire a webhook on completion" is the wrong mental model — for a real pipeline, route to /sales-userintuition.

Step 1 — Gather context

If references/learnings.md exists, read it first for accumulated platform knowledge.

Ask only what you can't infer:

1. What do you want from ResearchGOAT?
   • A) Design a study — write the objective, let the AI draft a pre-screening/screener survey, set the interview questions
   • B) Recruit / screen participants — use built-in recruitment/respondent selection, or bring your own audience
   • C) Run interviews — live AI-moderated voice interviews, any language
   • D) Read / export results — AI-synthesized insights + transcripts (there is no API/webhooks)
   • E) Pricing / minutes — free interview-minutes, plan gates, what a minute buys
   • F) Choose — ResearchGOAT vs Chikka / AskMore / User Intuition / Listen Labs / Strella
2. Is this discovery (strangers) or feedback from your own users/customers? This decides whether you lean on ResearchGOAT's recruitment or bring your own list.

Skip-ahead: if the user wants to compare research tools across the market or the validate-before-building method, that's a /sales-idea-validation question — route in Step 2.

Step 2 — Route or answer directly

| If the user's question is about… | Route to | |---|---| | Comparing research/idea/synthetic tools across the market, or the validate-before-building method | /sales-idea-validation {question} | | A REST API / webhook / MCP-native interview pipeline (ResearchGOAT has none — it's UI-only) | /sales-userintuition {question} | | Running a real behavior demand test (smoke-test page, waitlist, pre-sale) after interviews | /sales-idea-validation or /sales-funnel {question} | | Analyzing existing NPS/CSAT/VoC/interview data into themes (post-collection, not new interviews) | /sales-customer-feedback or /sales-trill {question} | | Synthetic-persona interviews (AI personas instead of real people) | /sales-syntheticusers or /sales-ditto {question} | | A text-first / async AI interviewer, or turning interviews into testimonials/case studies | /sales-askmore or /sales-chikka {question} |

When routing, give the exact command: "This is a {domain} question — run: /sales-idea-validation {original question}"

Otherwise, answer ResearchGOAT-specific questions using Step 3.

Step 3 — ResearchGOAT reference

Read references/platform-guide.md for the full reference — the module/automation-surface table (what's UI-only vs export), best-effort minute-based pricing and free-tier limits, the Project → Screener → Interview → Insights data model, the AI-research-design + recruitment workflow, the multilingual voice-interview flow, and how the AI's adaptive follow-ups work. Read references/researchgoat-api-reference.md for the automation surface — it documents that there is no public API/webhooks/MCP and inventories the actual data-out options.

Answer using only the relevant section — don't dump the full reference.

Step 4 — Actionable guidance

• Say the caveat: a real interview is not a purchase. Whatever the user asks, make explicit that ResearchGOAT interviews real people (a big step up from synthetic personas — genuine reasoning, objections, language), but a stated "I'd pay" in an interview is not observed demand. Point the user to the transcripts and AI insights for objections and pricing language rather than trusting the top-line synthesis as a verdict, then take the go/no-go from a real behavior test (pre-sale, smoke test) — route that to /sales-idea-validation.
• Treat automation as UI-only, and don't invent endpoints. When any automation/export/integration comes up, state that ResearchGOAT has no public REST API, webhooks, or MCP server surfaced — data-out is manual export of transcripts/insights. Don't design a REST/webhook pipeline or guess endpoints; if a programmatic pipeline is a hard requirement, route to /sales-userintuition. Present the no-API finding as best-effort — the live site is a JS-rendered SPA; confirm at researchgoat.com.
• Size it by interview-minutes, not seats, and call pricing best-effort. Billing is metered in AI interview-minutes (free tier includes a project + free minutes/month, e.g. a ~360-minute allotment seen at research). Present every figure as best-effort and point to researchgoat.com/pricing to confirm the current minute allotment and plan gates, since the SPA changes and paid tiers aren't cleanly published.
• Use its design + recruitment stack, but verify the recruitment source. ResearchGOAT can draft the screener and select/recruit respondents — a real edge over bring-your-own-participants peers. Confirm live whether recruitment draws on an owned panel or a third-party source, and screen for fit before spending minutes so you don't burn the allotment on off-target respondents.
• Lean into its real edge: end-to-end, voice-first, multilingual, at self-serve price. Recommend it when the user wants the depth of a spoken answer, help designing the study, and recruitment in one self-serve tool — that's where ResearchGOAT beats both a DIY survey and a scheduling-heavy human study.

If you discover a gotcha or tip not in references/learnings.md, append it there with today's date.

Gotchas

Best-effort from research (2026-07) — the live site is a JS-rendered SPA that blocked direct fetches, so minute allotments, paid-tier prices, whether recruitment uses an owned vs third-party panel, the language list, and export options all move; verify at researchgoat.com and researchgoat.com/pricing.

• Real ≠ demand. Interviews reveal the why better than any synthetic tool, but a stated intent to pay is not a purchase — the go/no-go still belongs to a real behavior test (pre-sale, smoke test).
• No public API/webhooks/MCP surfaced — automation is manual export. Don't design a webhook-on-completion pipeline or invent endpoints; a REST/webhook pipeline is a /sales-userintuition job. Present this as best-effort (no developer docs were found anywhere at research).
• Priced in interview-minutes, not seats. The free tier includes a project + free minutes/month (a ~360-minute allotment was seen at research); past that you buy more minutes. Size a study by interview-minutes (roughly interview length × number of interviews), not seats — and confirm the current allotment at researchgoat.com/pricing.
• Recruitment source is unverified. ResearchGOAT markets participant recruitment/selection, but whether it's an owned panel or a third-party source wasn't confirmable at research. Confirm before assuming it can reach a specific hard-to-reach audience at scale.
• Voice-first / real-time, not async text. Respondents speak in a live AI-moderated interview. If the user specifically needs async written answers (survey-simple reach), that's an /sales-askmore job; for a voice → testimonial/case-study pipeline, /sales-chikka.
• "Any language" is a real strength, but check the synthesis language. Respondents can answer in their language — confirm the AI insights/report language matches what your stakeholders read, and treat translated nuance as best-effort.
• It collects + synthesizes new interviews, not data you already have. ResearchGOAT runs new studies; to theme transcripts/open-ends you already have, use /sales-trill or /sales-customer-feedback.

Related skills

• /sales-idea-validation — The tool-agnostic validate-before-building method + the full research/persona/validator tool landscape (use this to decide build-or-not; an interview "yes" is not demand). Install: npx skills add sales-skills/sales --skill sales-idea-validation -a claude-code
• /sales-chikka — The self-serve voice real-human peer (AI agent "Ava" runs multilingual voice interviews + a VoiceVerify testimonial/case-study pipeline); closest on modality — pick Chikka for marketing assets, ResearchGOAT for the built-in research-design + recruitment stack. Install: npx skills add sales-skills/sales --skill sales-chikka -a claude-code
• /sales-askmore — The text-first, async, survey-simple real-human peer (bring-your-own-participants, credit-metered); pick AskMore for survey-reach written interviews, ResearchGOAT for live voice depth + recruitment. Install: npx skills add sales-skills/sales --skill sales-askmore -a claude-code
• /sales-userintuition — The REST-API/webhook/MCP real-human interview peer — the pick when you need a programmatic pipeline ResearchGOAT's UI-only surface can't offer. Install: npx skills add sales-skills/sales --skill sales-userintuition -a claude-code
• /sales-customer-feedback — Real-customer NPS/CSAT/VoC strategy across tools (use to analyze existing feedback; ResearchGOAT proactively runs new interviews). Install: npx skills add sales-skills/sales --skill sales-customer-feedback -a claude-code
• /sales-do — Not sure which skill to use? The router matches any sales objective to the right skill. Install: npx skills add sales-skills/sales --skill sales-do -a claude-code

Examples

Example 1: "The ResearchGOAT interviews loved my idea — should I build it?"

User says: "I ran 15 ResearchGOAT voice interviews and almost everyone said they'd use and pay for it. Green light?" Skill does: Credits the signal as real (actual people, genuine reasoning — far better than a synthetic tool), then draws the line: a stated "I'd pay" in an interview is not a purchase. Tells the user to mine the transcripts and AI insights for objections, hesitation, and pricing language (the real value), then take the go/no-go from a real behavior test (pre-sale or a "buy" click) via /sales-idea-validation. Notes minute allotments/pricing are best-effort. Result: The founder keeps the qualitative depth and runs a pre-sale before committing to build.

Example 2: "How do I pipe ResearchGOAT transcripts into my CRM/warehouse via the API?" (developer/automation)

User says: "I want a webhook to fire when a ResearchGOAT interview finishes and push the transcript to BigQuery." Skill does: States plainly that ResearchGOAT has no public REST API, webhooks, or MCP server surfaced at research — so there is no endpoint or key to build against, and it does not invent one (presenting the finding as best-effort; the live site is a JS-rendered SPA, confirm at researchgoat.com). Explains the only data-out is manual export of transcripts/insights. For a webhook-on-completion pipeline into a CRM or warehouse, routes to /sales-userintuition (REST API + HMAC-signed webhooks + MCP). Result: The user stops hunting for an API that doesn't exist and either exports manually or moves the pipeline to an API-native tool.

Example 3: "How much does ResearchGOAT cost and can it find people to interview?"

User says: "I want to interview target customers I don't already have — what will ResearchGOAT cost and does it recruit them?" Skill does: Explains billing is metered in AI interview-minutes (free tier = a project + free minutes/month, e.g. ~360 min seen at research; more minutes are paid — all best-effort, confirm at researchgoat.com/pricing), and that ResearchGOAT does offer built-in participant recruitment/selection (unlike bring-your-own peers) — but flags that whether it's an owned panel or a third-party source is unverified, so confirm it can reach your specific audience before relying on it. Suggests screening for fit before spending minutes. Result: The user sizes minutes correctly and verifies the recruitment source instead of assuming it covers a niche audience.

Troubleshooting

"Where's the ResearchGOAT REST API / webhook to sync interviews?"

Symptom: You're looking for an API key and a webhook to fire on interview completion. Cause: ResearchGOAT is UI-only — no public REST API, webhooks, or MCP server was documented anywhere at research (the live site is a JS-rendered SPA with no developer docs). Data-out is manual export. Solution: Export transcripts/insights from the UI. If a programmatic pipeline into a CRM/warehouse is a hard requirement, use an API-native tool instead — route to /sales-userintuition (REST API + HMAC-signed webhooks + MCP). Present the no-API finding as best-effort and confirm at researchgoat.com.

"How many interviews do my free minutes get me, and what happens after?"

Symptom: You're unsure what the free interview-minutes buy and when you'll have to pay. Cause: ResearchGOAT is metered in AI interview-minutes — the free tier includes a project + free minutes/month (a ~360-minute allotment was seen at research); past that you buy more. Exact allotments and paid-tier prices change and the SPA didn't expose them cleanly. Solution: Treat all figures as best-effort and confirm the current minute allotment and plan gates at researchgoat.com/pricing before planning a study; size the study by interview-minutes (interview length × number of interviews), not seats.

"Does ResearchGOAT find respondents for me, or do I bring my own?"

Symptom: You expected to know whether ResearchGOAT supplies participants or you recruit them. Cause: ResearchGOAT markets built-in participant recruitment/selection (a differentiator vs bring-your-own peers like AskMore/Chikka/Frank), but whether it draws on an owned panel or a third-party source wasn't confirmable at research. Solution: For your own users, share the study with them directly. For strangers, confirm live whether ResearchGOAT's recruitment reaches your target audience and at what cost — and screen for fit before spending minutes. If you need a specific hard-to-reach B2B panel, cross-check the panel-native options via /sales-idea-validation.