sales-skills/sales-chikka

Chikka Platform Help

Chikka (chikka.ai) runs AI voice interviews on real people — an AI agent named Ava conducts empathetic, multilingual voice conversations at scale, then turns them into transcripts, themes, insight reports AND marketing assets (quote posters, testimonials, case studies). It doubles as a research repository: upload existing audio/video/transcripts/docs and it transcribes, tags, and clusters them by theme alongside the interviews it runs. Use cases it markets: customer feedback, employee insights, market research, academic research, and post-interaction user testing.

Its niche in the real-human AI-moderated-interview cluster (User Intuition, Strella, Voicepanel, Frank, Listen Labs) is two things:

• Self-serve with a genuinely usable free tier and public pricing — the opposite of the sales-gated peers (Voicepanel is sales-quoted, Listen Labs is demo-first/annual-contract). A solo maker can sign up and run interviews today.
• A voice → marketing-asset pipeline — it doesn't stop at insights; it spins interviews into testimonials and case studies authenticated by its VoiceVerify engine. No other tool in the cluster leans this way.

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 a moderator transcript. Route that to /sales-idea-validation.
• It's UI-only — no public API, webhooks, or MCP. The only native integrations are Zoom & Microsoft Teams (Professional+); everything else is manual export. "Call the Chikka API / fire a webhook on interview 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 Chikka?
   • A) Run new voice interviews — set an objective, share a participation link (or QR/URL top-up), let Ava interview
   • B) Analyze data you already have — upload audio/video/transcripts/docs → transcribe, tag, theme-cluster (repository)
   • C) Generate marketing assets — quote posters, testimonials, case studies (VoiceVerify)
   • D) Get data out / automate — export, or the Zoom/Teams integration (there is no API/webhooks)
   • E) Choose — Chikka vs Voicepanel / Strella / User Intuition / Frank / Listen Labs
   • F) Pricing / plan gates — what the Free tier includes vs Professional/Team/Enterprise
2. Is this discovery (strangers) or feedback from your own users/customers? That changes how honest the signal is and whether you need to recruit or just share a link to people you already have.

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 (Chikka 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/review feedback into themes (post-launch, not new interviews) | /sales-customer-feedback {question} | | Synthetic-persona interviews (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 Chikka-specific questions using Step 3.

Step 3 — Chikka reference

Read references/platform-guide.md for the full reference — the module/automation-surface table (what's UI-only vs export vs Zoom/Teams), best-effort pricing and plan gates (Free/Professional/Team/ Enterprise + top-ups), the Project → Interview/Session → Insight data model, the VoiceVerify / marketing-asset workflow, and the research-repository (upload existing data) workflow. Read references/chikka-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 Chikka 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. Keep the why/objections/language and 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 Chikka has no public REST API, webhooks, or MCP server — the only native integrations are Zoom & Microsoft Teams (Professional+, for pulling meetings in), and the only data-out is manual export (transcripts, reports, assets). Don't design a REST/webhook pipeline or guess endpoints; if a programmatic pipeline is a hard requirement, route to /sales-userintuition.
• Lead solo makers to the free tier, but name its limits. Chikka's edge over the sales-gated peers is that it's self-serve with a real free plan — recommend it as the low-friction way to start, but say the Free tier is tight (best-effort ~5 AI-hosted interviews, 1 project, ~45 min transcription/month, ~1 insight report/month), and running-new-interviews at volume, cross-interview pattern detection, team workspaces, and the Zoom/Teams integrations sit on Professional/Team. Present every figure as best-effort and point to chikka.ai/pricing to confirm.
• Explain what VoiceVerify does and does NOT prove, and require consent. VoiceVerify authenticates that a testimonial came from a real human voice (anti-fabrication / credibility) — it does not verify that the claim is true, that the speaker is a paying customer, or that results are typical. Before turning any interview into a public testimonial/quote poster/case study, tell the user to get explicit consent to use the person's voice, name, and words (a privacy/consent step, not a Chikka feature) and to avoid presenting a stated opinion as a verified outcome.
• Match the job to the mode. Ava runs new interviews (share a link to your own users, or use a URL/QR top-up for outside respondents); the upload/repository side analyzes data you already have (past calls, sales recordings, open-ends). For strangers at scale on a large recruited panel, Chikka is thinner than panel-first peers — say so and point to /sales-idea-validation for the tool map.

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) — pricing (Free/Professional/Team/Enterprise tiers, top-up packs), interview/transcription limits, the language count, and the integration list all move; verify at chikka.ai and chikka.ai/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 — automation is manual export + Zoom/Teams. Don't design a webhook-on-completion pipeline or invent endpoints; a REST/webhook pipeline is a /sales-userintuition job.
• The Free tier is a trial-grade taste, not a workhorse. ~5 AI interviews / 1 project / ~45 min transcription / ~1 report per month (best-effort) — real programs need Professional or Team.
• VoiceVerify authenticates the voice, not the claim. It fights fabricated/AI-faked testimonials; it does not make a subjective claim true or a speaker a verified customer. Don't oversell it.
• Get consent before publishing anyone's voice/quote. Turning an interview into a public testimonial/case study needs explicit permission for the person's voice, name, and words.
• "Ava" also powers a free MBTI demo (talktoava.app). That consumer demo is a lead magnet, not the research product — don't confuse its limits/pricing with the Chikka workspace.
• Panel/respondent reach is limited vs panel-first peers. For recruiting strangers at scale, a panel-native tool (see /sales-idea-validation) or a recruit marketplace is the better instrument.

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-userintuition — The REST-API/webhook/MCP real-human interview peer — the pick when you need a programmatic pipeline Chikka's UI-only surface can't offer. Install: npx skills add sales-skills/sales --skill sales-userintuition -a claude-code
• /sales-voicepanel — The broadest-format, MCP-first real-human voice-interview peer (voice/video/chat/phone + usability tasks); sales-gated pricing vs Chikka's self-serve free tier. Install: npx skills add sales-skills/sales --skill sales-voicepanel -a claude-code
• /sales-frank — The bring-your-own-customers, self-serve, UI-only voice-interview peer (closest analog); pick by panel need and pricing model. Install: npx skills add sales-skills/sales --skill sales-frank -a claude-code
• /sales-researchgoat — The end-to-end, voice-first self-serve peer (researchgoat.com) that adds AI research design + a screener + built-in participant recruitment + AI synthesis around the interview; pick ResearchGOAT for the design/recruit stack, Chikka for VoiceVerify marketing assets. Install: npx skills add sales-skills/sales --skill sales-researchgoat -a claude-code
• /sales-customer-feedback — Real-customer NPS/CSAT/VoC strategy across tools (use to analyze existing feedback; Chikka proactively runs new interviews and generates testimonials). 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 Chikka interviews loved my idea — should I build it?"

User says: "I ran 15 Ava 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 themes 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 pricing/limits 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 Chikka transcripts into my CRM/warehouse via the API?" (developer/automation)

User says: "I want a webhook to fire when an interview finishes and push the transcript to BigQuery." Skill does: States plainly that Chikka has no public REST API, webhooks, or MCP server — so there is no endpoint or key to build against, and it does not invent one. Explains the only native integrations are Zoom & Microsoft Teams (Professional+, meetings in), and the only data-out is manual export of transcripts/reports/assets. 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: "Can I generate authenticated testimonials on the free plan?"

User says: "I want VoiceVerify testimonials from customer interviews — how many interviews does Free give me?" Skill does: Gives best-effort Free-tier limits (~5 AI interviews / 1 project / ~45 min transcription / ~1 report per month) and notes that volume, cross-interview patterns, team workspaces, and Zoom/Teams sit on Professional/Team — all best-effort, confirm at chikka.ai/pricing. Explains VoiceVerify authenticates that the testimonial came from a real human voice (anti-fabrication) but does not prove the claim is true or the speaker is a paying customer — and reminds the user to get explicit consent before publishing someone's voice, name, and words. Result: The user sizes the right plan and uses testimonials honestly and with consent.

Troubleshooting

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

Symptom: You're looking for an API key and a webhook to fire on interview completion. Cause: Chikka is UI-only — no public REST API, webhooks, or MCP server. Its only native integrations are Zoom & Microsoft Teams (Professional+), and data-out is manual export. Solution: Export transcripts/reports/assets from the UI, or use the Zoom/Teams integration to bring meetings in. 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).

"I ran out of interviews / transcription minutes almost immediately"

Symptom: The Free plan blocks you after a handful of interviews or ~45 minutes of transcription. Cause: The Free tier is trial-grade (best-effort ~5 AI interviews, 1 project, ~45 min transcription, ~1 report per month) — it's a taste, not a workhorse. Solution: Move to Professional (more interviews + transcription + Zoom/Teams + Chat-with-Data) or Team (cross-interview patterns, workspaces, roles) for real volume, or use a top-up pack for extra respondents via a share link/QR. Treat all limits as best-effort and confirm at chikka.ai/pricing.

"Can I trust a VoiceVerify testimonial as proof my product works?"

Symptom: You want to publish interview quotes as validated results. Cause: VoiceVerify authenticates the voice is a real human (anti-fabrication) — it does not verify the claim is true, that the speaker is a paying customer, or that results are typical. Solution: Use testimonials as credible opinions, not proof of outcomes; get explicit consent to use each person's voice/name/words; and take any build-or-not or "it works" go/no-go from a real behavior test, not a quote (route to /sales-idea-validation).