Docs
Integrate Nosie
Nosie runs brief, evidence-based micro-interviews with your customers — by phone call, SMS/chat, or email — and returns structured results: a transcript, a summary, attributes mapped to your schema, and quality signals.
There are two ways to use it: manually from the dashboard (no code), or programmatically through the REST API and webhooks so interviews start automatically when, say, a customer finishes signup. Most teams start manually and automate later — both paths share the same projects, contacts, and results.
Last updated: 6 July 2026
Using the dashboard (no code)
The full workflow takes about ten minutes end to end:
- Create a project. From the dashboard, choose New project and answer a short chat about what you want to learn. Nosie drafts a structured interview brief — objective, audience, key topics, and the exact attributes to extract — which you review and approve before anything goes live.
- Add contacts. One at a time, or by CSV import with the headers
name, phone, email, modes, timezone, country(any other column becomes a custom field). Every add requires a consent attestation — see below. - Launch. Nosie reaches each contact in their allowed modes within local calling hours, asks follow-ups when something matters, and respects opt-outs immediately and permanently.
- Read results. Each completed interview appears under the project's Results tab with its summary, attributes, and quality signals — exportable as CSV or JSON.
API quickstart
The API lives at https://nosie.app/api/v1. Authenticate every request with Authorization: Bearer <api key>. Create a key under Developers in the dashboard — it is shown once and prefixed nk_live_. Rate limit: 60 requests/minute per key.
1. Create a project with an interview brief:
curl -X POST https://nosie.app/api/v1/projects \
-H "Authorization: Bearer nk_live_..." \
-H "Content-Type: application/json" \
-d '{
"name": "New-customer onboarding research",
"brief": {
"objective": "Understand why new customers signed up and where they stall in week one",
"audience_description": "Admins who created an account in the last 14 days",
"key_topics": ["previous tool", "reason for switching", "first-week friction"],
"success_criteria": "Three specific friction points per customer",
"identity_label": "the Acme Scheduling team",
"allowed_modes": ["call", "email"],
"timebox_seconds": 180,
"output_schema": {
"previous_tool": { "type": "string", "description": "What they used before" },
"switch_trigger": { "type": "string", "description": "The moment that made them switch" },
"team_size": { "type": "number", "description": "People who will use the product" }
}
}
}'2. Add contacts — the consent attestation is mandatory:
curl -X POST https://nosie.app/api/v1/projects/PROJECT_ID/contacts \
-H "Authorization: Bearer nk_live_..." \
-H "Content-Type: application/json" \
-d '{
"contacts": [
{
"name": "Rewi Morgan",
"phone": "+64211234567",
"email": "rewi@example.co.nz",
"allowed_modes": ["call", "email"],
"timezone": "Pacific/Auckland",
"country": "NZ"
}
],
"consent": {
"attested": true,
"basis": "Ticked the research callback opt-in on our signup form",
"method": "signup_form"
}
}'3. Launch outreach:
curl -X POST https://nosie.app/api/v1/projects/PROJECT_ID/launch \
-H "Authorization: Bearer nk_live_..."4. Receive results on a webhook (see Webhooks) or poll GET /v1/contacts/{id}/result. The full endpoint list is in the API reference.
The consent rule
attested: true, a basis of at least 10 characters describing how consent was collected, and a method (signup_form, verbal, written, existing_relationship, or other). API requests without one are rejected with HTTP 422. Opt-outs are honoured immediately and can never be reversed — by anyone, including Nosie staff.Getting results out
Every completed interview produces the same structured record:
- Transcript & summary — a speaker-labelled record plus a short bullet summary.
- Attributes — answers mapped to the exact keys in your
output_schema; unknowns are omitted, never guessed. - Quality signals — engagement, coverage, duration, and outcome, so you know which results to trust.
Delivery options: webhooks (push, signed, at-least-once), REST API (pull), or CSV/JSON export from the dashboard.
For AI agents
If you are an AI agent integrating Nosie for a user, you need three URLs: https://nosie.app/api/v1/openapi.json (OpenAPI 3.1 spec), https://nosie.app/llms-full.txt (these docs as plain markdown), and the dashboard's Developers page where your user must create the API key — keys are shown once and cannot be retrieved later. Remember: contact creation always requires the consent attestation, and a real human must be able to stand behind its basis.
FAQ
- Do I need to write code to use Nosie?
- No. The dashboard covers the whole workflow: describe your project in a two-minute chat, add contacts by hand or CSV, launch, and read results. The REST API and webhooks exist for teams that want interviews triggered automatically from their own product.
- Can an AI agent integrate Nosie on my behalf?
- Yes. The API is a small, conventional REST surface (7 endpoints, bearer-key auth, JSON bodies) with a machine-readable OpenAPI 3.1 spec at /api/v1/openapi.json and full docs mirrored in /llms-full.txt. Point your agent at either file.
- Why does the API reject my contacts with a 422?
- Every contact-create request must include a consent attestation — attested: true, a basis of at least 10 characters describing how consent was collected, and a method. Requests without one are rejected with HTTP 422. This is by design and cannot be disabled.
- How do I get interview results into my system?
- Two ways: subscribe a webhook to the contact.completed event and receive the transcript summary, extracted attributes, and quality signals the moment an interview finishes, or poll GET /v1/contacts/{id}/result. CSV and JSON export are also available from the dashboard.
- What does an interview cost?
- Nosie is NZ$20/month including 10 completed interviews, then NZ$2 per additional completed interview. Voicemails, no-answers, failed attempts, and declines are never billed.
Machine-readable versions: OpenAPI spec · llms.txt · llms-full.txt. Questions? hello@nosie.app