Generate an audience intelligence report from comment data. Returns clusters, narratives, sentiment, spam detection, and strategic recommendations.
| Header | Required | Description |
|---|---|---|
Authorization | Yes | Bearer nawa_live_sk_xxx or Bearer nawa_test_sk_xxx |
Content-Type | Yes | application/json |
| Parameter | Type | Required | Description |
|---|---|---|---|
comments | array | Yes | Array of comment objects. Min 10, max 500. Each must have a text field. |
comments[].text | string | Yes | The comment text. |
comments[].author | string | No | Commenter handle or name. |
comments[].likes | integer | No | Number of likes on the comment. |
comments[].created_at | string | No | ISO 8601 timestamp. |
tier | string | No | basic or pro. Default: basic. Pro adds repeat commenter analysis and a content brief. |
title | string | No | Video or content title for context. |
channel_context | string | No | Brief channel description to improve recommendation quality. |
| Header | Description |
|---|---|
X-Request-Id | Unique request identifier |
X-NAWA-Provider | Model provider used (always claude) |
X-NAWA-Latency | Processing time in ms |
X-NAWA-Tier | Report tier (basic or pro) |
| Field | Type | Description |
|---|---|---|
id | string | Unique report identifier |
object | string | Always intelligence_report |
tier | string | basic or pro |
report_markdown | string | Full report in markdown format |
sections | object | Parsed report sections (see below) |
comments_analyzed | integer | Number of comments analyzed |
cost_usd | number | Cost of this report |
credits_used | integer | Credits deducted |
| Field | Tier | Description |
|---|---|---|
tldr | Both | Opening verdict. What the reader needs to know in 20 seconds. |
executive_summary | Both | Key metrics table and strategic finding. |
headline_finding | Both | The one finding that matters. The single most important takeaway. |
sentiment | Both | Sentiment breakdown with pattern notes. |
clusters | Both | Audience clusters with trajectory and sentiment. |
narratives | Both | Narrative strength map with trajectory. |
comment_types | Both | Breakdown of what fans are saying by comment type. |
top_commenters | Both | Top 10 influence leaders by likes. |
spam_detected | Both | Spam and bot detection results. |
recommendations | Both | Data-backed strategic recommendations. |
channel_health | Both | Channel health scorecard. |
repeat_commenters | Pro | Repeat commenter analysis with superfan detection. |
content_brief | Pro | Episode concepts and engagement playbook. |
COUNT: verified from the source data. The model computed this number directly from the comments you provided.ESTIMATE: analyst judgement. The model inferred this from patterns rather than counting exactly.UNVERIFIED: the model omitted a tag. Post-processing stamps UNVERIFIED on any bare percentage in a table cell so downstream consumers know the tag is missing.| Status | Type | When |
|---|---|---|
| 400 | invalid_request_error | Missing/invalid comments, wrong tier, fewer than 10 comments |
| 401 | authentication_error | Invalid or missing API key |
| 402 | insufficient_credits | Not enough credits (need 500 for Basic, 1500 for Pro) |
| 429 | rate_limit_error | Rate limit exceeded (5 reports/minute) |
| 500 | api_error | Internal or provider error |
Basic tier ($0.50)
Pro tier ($1.50)