Frank (hifrank.ai) platform help — an AI-moderated customer-research tool (by Prelaunch.com) that interviews your REAL customers, not synthetic personas: an AI voice/chat interviewer that adapts follow-ups and turns conversations into transcripts, themes, sentiment, quotes, and video reels across 30+ languages. Bring-your-own-customers only — no third-party panel; you share an interview link by email, chat, or in-product journey, with optional incentives. Self-serve, voice-minute-metered plans; UI-only — no public API, webhooks, Zapier, or MCP (API is Enterprise-only). Use when setting up a Frank study or discussion guide, running churn / discovery / concept-testing interviews with your own users, picking a plan by voice-minute allowance, or getting data out with no API. Do NOT use for comparing research tools or the validate-before-build method (use /sales-idea-validation), an API/webhook/MCP-native pipeline (use /sales-userintuition), or reaching strangers on a recruited panel (use /sales-respondent).
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Frank (hifrank.ai) platform help — an AI-moderated customer-research tool (by Prelaunch.com) that interviews your REAL customers, not synthetic personas: an AI voice/chat interviewer that adapts follow-ups and turns conversations into transcripts, themes, sentiment, quotes, and video reels across 30+ languages. Bring-your-own-customers only — no third-party panel; you share an interview link by email, chat, or in-product journey, with optional incentives. Self-serve, voice-minute-metered plans; UI-only — no public API, webhooks, Zapier, or MCP (API is Enterprise-only). Use when setting up a Frank study or discussion guide, running churn / discovery / concept-testing interviews with your own users, picking a plan by voice-minute allowance, or getting data out with no API. Do NOT use for comparing research tools or the validate-before-build method (use /sales-idea-validation), an API/webhook/MCP-native pipeline (use /sales-userintuition), or reaching strangers on a recruited panel (use /sales-respondent).
argument-hint
[describe what you need help with in Frank]
license
MIT
version
1.0.0
tags
["sales","idea-validation","platform"]
Frank Platform Help
Frank (hifrank.ai, built by Prelaunch.com) is an AI-moderated customer researcher that interviews
your real customers — an AI voice (and chat) interviewer that adapts its follow-ups, runs many
conversations in parallel 24/7, and turns them overnight into transcripts, themes, sentiment, key quotes,
and video reels across 30+ languages. "Talk to hundreds of real customers while you sleep."
Its defining trait in the AI-moderated-interview cluster is bring-your-own-customers (BYOC) only — it has
no third-party participant panel. You reach the people who already use (or are considering) your product
by sharing an interview link — in an email, a chat, or as a step in the user's journey inside your
product — with an optional incentive (an Amazon gift card, a discount, or nothing). That makes it the
pick when you already have customers/prospects to talk to (churn, discovery, concept/feature testing,
engagement), and the wrong pick when you need to reach strangers you don't already have.
Two things to say almost every time:
It's real humans, but a stated "I'd pay" is still not a purchase. A real interview beats a synthetic
"yes" (genuine reasoning, objections, language) — but the willingness-to-pay go/no-go belongs to a
real behavior test (pre-sale, smoke test), not a transcript. Route that to /sales-idea-validation.
Frank is UI-only for self-serve users. There is no public API, no webhooks, no Zapier, no MCP — an
"API integration" is listed only on the Enterprise tier and is undocumented. Any "pipe transcripts
into my CRM/warehouse" ask is manual export, not an integration. If the user needs an API-native
interview pipeline, the right tool is /sales-userintuition, not Frank.
Step 1 — Gather context
If references/learnings.md exists, read it first for accumulated platform knowledge.
Ask only what you can't infer:
What do you want from Frank?
A) Set up a study — write the objective/discussion guide, pick voice vs chat, set incentive
B) Distribute — get the interview link in front of your own customers (email, chat, in-product)
C) Read results — themes, sentiment, quotes, video reels — or decide whether to trust them
D) Get data out — export transcripts/reels for a deck, CRM, or warehouse (no API — manual)
E) Choose a plan — Free vs Starter vs Growth vs Business by voice-minute allowance
F) Compare — Frank vs User Intuition / Strella / Listen Labs / Voicepanel for your use case
Do you already have customers/prospects to interview? Frank has no panel — if you need to reach
strangers, it's the wrong tool (route to a panel-based peer or a recruit marketplace in Step 2).
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}
An API / webhook / MCP-native interview pipeline (Frank has none for self-serve)
/sales-userintuition {question}
Reaching strangers on a recruited panel (Frank is BYOC-only, no panel)
/sales-respondent or /sales-idea-validation{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/review feedback (post-launch, not new interviews)
/sales-customer-feedback {question}
A synthetic-persona peer (AI personas instead of real people)
/sales-syntheticusers or /sales-ditto{question}
When routing, give the exact command: "This is a {domain} question — run: /sales-idea-validation {original question}"
Otherwise, answer Frank-specific questions using Step 3.
Step 3 — Frank platform reference
Read references/platform-guide.md for the full reference — the module/automation-surface table
(what's exportable vs UI-only), best-effort pricing and the voice-minute/credit model, the
Study → Interview → Participant → Insight data model, BYOC distribution, and the no-API data-out playbook.
Frank has no public API for self-serve users, so there is no API-reference file.
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 Frank
interviews real humans (a big step up from synthetic personas — genuine reasoning, objections,
language), but a stated "I'd pay" in an interview is not observed demand. Keep the why/objections/
language and take the go/no-go from a real behavior test (smoke-test click, pre-sale) — route that
to /sales-idea-validation. When they interpret results, point them to the verbatim quotes and video
reels under each theme (the objections, hesitation, and pricing language) — not just the top-line
sentiment/theme summary, which is an index, not the finding.
Lead with BYOC: Frank has no panel. When the user asks who Frank interviews, state that it is
bring-your-own-customers only — you distribute a share link to your own customers/prospects
(email, chat, or an in-product journey step), so it fits churn/discovery/concept-testing with an audience
you already have. If they need to reach strangers, say so plainly and route to a panel-based peer
(/sales-userintuition, /sales-listenlabs) or a recruit marketplace (/sales-respondent).
Flag it as UI-only when any automation/export comes up. Frank has no public API, webhooks, Zapier,
or MCP for self-serve plans (an "API integration" appears only on the Enterprise tier and is
undocumented — verify against current docs). "Sync transcripts to HubSpot/Snowflake" is a manual
export/copy job. If the user needs a programmatic pipeline, tell them so and route to /sales-userintuition.
Recommend a plan by voice-minute allowance, not seats. Frank meters voice minutes (roughly
~15 min/interview; ~10 credits ≈ 1 voice minute or ~10 chat messages), so size the plan by how many
interviews/month they'll run, and note chat conversations are cheaper than voice. Present every
price as best-effort and point to hifrank.ai/pricing to confirm.
Keep the discussion guide tight; let the Research Agent draft it. Setup is fast (share your site +
goal, the AI drafts an outline in ~2 min). Give it a sharp objective + a few core questions and let
the adaptive moderator probe — a thin brief caps depth, but an over-long guide fatigues participants.
Set the incentive to the ask. The incentive is optional (Amazon gift card, purchase discount, or
none) — use a reward for cold/low-motivation audiences and skip it for engaged customers; it's a
response-rate lever, not a quality guarantee.
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) — Frank is new (launched ~2026-04) and its modality mix, pricing, and
(absent) API surface move fast; verify at hifrank.ai.
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 panel — BYOC only. Frank does not recruit strangers; you must already have customers/prospects
and distribute a share link. For strangers, use a panel-based peer or a recruit marketplace.
No API, no webhooks, no Zapier, no MCP (self-serve). Frank is UI-only; "API integration" is an
Enterprise-only, undocumented line item. The only data-out is manual export (transcripts, reels).
Don't design a live integration around it — route pipeline needs to /sales-userintuition.
Voice is the live modality; video + WhatsApp are newer/coming. Marketing lists voice, video, and
WhatsApp, but voice (and chat) are what's shipped — treat video/WhatsApp as best-effort until confirmed.
Plans meter voice minutes, and interviews have a max length. Free caps interview length short; paid
tiers raise it. Model cost by minutes, not by interview count, and confirm the current caps on site.
Pricing is published but moves. Monthly vs annual differ a lot (annual is far cheaper per month) —
treat any figure as best-effort and confirm at hifrank.ai/pricing.
It's built by Prelaunch.com. Frank is a distinct product from Prelaunch's concept-testing/pre-order
platform — don't conflate their feature sets or pricing.
Related skills
/sales-idea-validation — The tool-agnostic validate-before-building method + the full research/persona/validator tool landscape (use this to actually 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-userintuition — The API/webhook/MCP-native real-human interview peer — the pick when you need a programmatic pipeline Frank can't offer for self-serve (deepest developer surface in this cluster; also has a big panel Frank lacks). Install: npx skills add sales-skills/sales --skill sales-userintuition -a claude-code
/sales-strella — The other UI-only real-human AI-moderated interview peer (deterministic scripted flows, 3M+ panel via User Interviews); pick Strella when you want a panel or scripted repeatability, Frank when you're interviewing your own customers self-serve. Install: npx skills add sales-skills/sales --skill sales-strella -a claude-code
/sales-listenlabs — The enterprise/consultative real-human peer with a 30M+ panel, REST API v2 + OAuth MCP; pick it when you need a panel of strangers or an API pipeline. Install: npx skills add sales-skills/sales --skill sales-listenlabs -a claude-code
/sales-chikka — The closest analog — another self-serve, UI-only AI voice-interview tool with a free tier; its twist is a voice → marketing-asset pipeline (VoiceVerify testimonials/case studies). Pick by pricing model and whether you want testimonials out of the same interview. Install: npx skills add sales-skills/sales --skill sales-chikka -a claude-code
/sales-respondent — Participant-recruitment marketplace — recruits, screens, and pays strangers from a 4M+ B2B/professional panel; the pick when Frank's BYOC model can't reach the audience you need. Install: npx skills add sales-skills/sales --skill sales-respondent -a claude-code
/sales-customer-feedback — Real-customer NPS/CSAT/VoC strategy across tools (use to analyze existing feedback; Frank proactively runs new interviews with your own customers). Install: npx skills add sales-skills/sales --skill sales-customer-feedback -a claude-code
/sales-funnel — Build the smoke-test / fake-door landing page that turns an interview hypothesis into a real demand test. Install: npx skills add sales-skills/sales --skill sales-funnel -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 interviews said they'd pay — should I build it?"
User says: "I ran 30 Frank interviews with my waitlist and most said they'd pay. Green light?"
Skill does: Credits the signal as real (actual humans, genuine reasoning — far better than a
synthetic tool), then draws the line: a stated "I'd pay" is not a purchase. Tells the user to open the
verbatims and video reels and mine objections, hesitation, and pricing language, then take the go/no-go
from a real behavior test (a pre-sale or a "buy" click) via /sales-idea-validation. Flags pricing as
best-effort and points to hifrank.ai/pricing.
Result: The founder keeps the qualitative depth and runs a pre-sale before committing to the build.
Example 2: "How do I get Frank transcripts into HubSpot automatically?" (developer/automation)
User says: "I want every completed Frank interview transcript to land on the HubSpot contact."
Skill does: States plainly that Frank is UI-only for self-serve — no public API, webhooks, Zapier, or
MCP (an "API integration" is an Enterprise-only, undocumented line item), so there's no automated path;
the only data-out is a manual export of transcripts/reels. If a live pipeline is a hard requirement,
routes to /sales-userintuition (REST API + HMAC webhooks + MCP) as the API-native alternative, noting the
trade-off (Frank's edge is fast, cheap self-serve interviews with your own customers).
Result: The user stops hunting for an API that doesn't exist and either exports manually or switches
tools for the pipeline.
Example 3: "Which plan do I need, and how do I reach people to interview?"
User says: "I want ~25 customer interviews a month. Which Frank plan, and where do the participants come from?"
Skill does: Explains Frank is BYOC — no panel: you share an interview link with your own
customers/prospects (email, chat, or in-product journey), with an optional incentive. Sizes the plan by
voice-minute allowance (~15 min/interview → ~25 interviews needs a mid tier's minute pool; chat is
cheaper than voice), flags monthly-vs-annual pricing as best-effort → hifrank.ai/pricing, and notes that if
they need to reach strangers they don't already have, Frank can't — route to /sales-respondent or a
panel-based peer.
Result: The user picks a plan by minutes and understands they must supply their own audience.
Troubleshooting
"Who does Frank interview — where's the panel?"
Symptom: The user expects Frank to recruit participants like a panel tool.
Cause: Frank is bring-your-own-customers only — it has no third-party panel. It interviews the
people you already have a way to reach.
Solution: Distribute the interview link to your own customers/prospects (email, chat, or an
in-product journey step), with an optional incentive (Amazon gift card / discount / none). If you need to
reach strangers, Frank is the wrong tool — recruit via /sales-respondent or use a panel-based peer
(/sales-userintuition, /sales-listenlabs).
"How do I automate exports / connect Frank to my stack?"
Symptom: You want transcripts, reels, or insights flowing into a CRM, warehouse, or Slack.
Cause: Frank has no public API, webhooks, Zapier, or MCP for self-serve plans — it's UI-only (an
"API integration" appears only on the Enterprise tier and is undocumented; verify against current docs).
Solution: Use the built-in manual export (transcripts / video reels / summaries) for decks and
ad-hoc handoff. If an automated, programmatic pipeline is a requirement, use an API-native interview tool
instead — route to /sales-userintuition (REST API + HMAC-signed webhooks + MCP server).
"Which plan, and why did I run out of interviews so fast?"
Symptom: The user is unsure which tier to buy, or hit a limit sooner than expected.
Cause: Frank meters voice minutes (roughly ~15 min/interview; ~10 credits ≈ 1 voice minute or
~10 chat messages) and caps interview length by tier — so cost tracks minutes, not interview count, and a
few long voice interviews burn a small plan.
Solution: Size the plan by monthly voice-minute allowance for your expected interview count, prefer
chat where voice depth isn't needed (it's cheaper), and watch the per-tier max interview length.
Treat every figure as best-effort and confirm at hifrank.ai/pricing.
