Get User Analytics

Understand how a specific user engages with your AI across all their conversations. Track their satisfaction, identify pain points, and spot opportunities to improve their experience.

⚠️ Requires Growth+ plan or higher

Two modes available:

simple mode: Get aggregate metrics like average sentiment, frustration levels, and conversation quality. Perfect for user dashboards. No rate limiting.
insights mode (default): Access detailed patterns, recurring topics, and AI-generated recommendations specific to this user. Rate limited based on your plan’s maxAnalysesPerHour.

Returns 404 if the user doesn’t exist or has no conversations yet.

GET

users

{userId}

analytics

cURL

curl --request GET \
  --url https://www.greenflash.ai/api/v1/users/{userId}/analytics \
  --header 'Authorization: Bearer <token>'

{
  "averageUserSentiment": {
    "label": "neutral",
    "score": 0.05
  },
  "averageChangeInUserSentiment": {
    "label": "improving",
    "score": 0.12
  },
  "averageFrustration": {
    "label": "moderate",
    "score": 0.38
  },
  "averageStruggle": {
    "label": "low",
    "score": 0.2
  },
  "averageCommercialIntent": {
    "label": "low",
    "score": 0.15
  },
  "averageConversationRating": 4.2,
  "averageConversationQualityIndex": 6.8,
  "topics": [
    {
      "name": "billing",
      "count": 15
    },
    {
      "name": "account access",
      "count": 12
    },
    {
      "name": "feature questions",
      "count": 8
    }
  ],
  "keywords": [
    {
      "name": "refund",
      "count": 9
    },
    {
      "name": "login",
      "count": 7
    }
  ],
  "summary": {
    "profileSummary": "Engaged user who frequently asks about billing and account access.",
    "behavioralPatterns": [
      {
        "pattern": "Returns to ask follow-up questions within 24 hours",
        "evidence": "Across 12 conversations, started a new thread the day after resolving the prior one.",
        "frequency": "recurring"
      }
    ],
    "engagement": {
      "level": "regular",
      "trajectory": "stable",
      "description": "Consistent weekly usage with steady conversation volume over the last 30 days."
    },
    "signals": [
      {
        "type": "insight",
        "title": "Billing questions dominate",
        "description": "Roughly a third of conversations involve billing, suggesting unclear pricing surfaces.",
        "priority": "medium"
      }
    ],
    "productAlignment": {
      "summary": "Uses core support flows but rarely engages with self-serve documentation.",
      "strengths": [
        "Quick to adopt new chat features"
      ],
      "gaps": [
        "Does not discover the in-app billing FAQ"
      ]
    },
    "methodology": "Generated from 47 conversations spanning the last 90 days."
  },
  "totalConversations": 47
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

userId

string<uuid>

required

The user ID to get analytics for

Query Parameters

mode

enum<string>

default:insights

Analysis mode: "simple" returns only numeric aggregates (no rate limiting), "insights" includes topics, keywords, and recommendations (rate limited per tenant plan).

Available options:

simple,

insights

productId

string<uuid>

Filter analytics by product ID.

versionId

string<uuid>

Filter analytics by version ID.

Response

User analytics retrieved

averageUserSentiment

object

required

Average sentiment across all conversations.

Show child attributes

averageChangeInUserSentiment

object

required

Distribution of sentiment changes.

Show child attributes

averageFrustration

object

required

Average frustration level.

Show child attributes

averageStruggle

object

required

Average struggle level.

Show child attributes

averageCommercialIntent

object

required

Average commercial intent.

Show child attributes

averageConversationRating

number | null

required

Average conversation rating.

averageConversationQualityIndex

number | null

required

Average conversation quality index.

summary

object

required

Structured participant profile summary.

Show child attributes

totalConversations

number

required

Total number of conversations analyzed.

topics

object[]

Topics discussed (insights mode only).

Show child attributes

keywords

object[]

Keywords extracted (insights mode only).

Show child attributes

Stream ChatStart a streaming chat session with the Greenflash AI agent. **Requires a Growth or Enterprise plan.** The response is a Server-Sent Events (SSE) stream (`Content-Type: text/event-stream`). Each event follows the format: ``` event: <type> data: <json> ``` **Event types:** - `tool_call` — The agent is invoking a tool. Data: `{"step": 1, "toolName": "...", "displayName": "..."}` - `tool_result` — A tool returned its result. Data: `{"step": 1, "toolName": "...", "displayName": "..."}`. For `draftTicket` and `createTicket`, the event also includes an `output` field with the tool's payload (see *Ticket creation* below). - `text_delta` — A chunk of the agent's text response. Concatenate all deltas to build the full message. Data: `{"text": "..."}` - `done` — The stream completed successfully. Data: `{"conversationId": "...", "status": "complete", "usage": {"toolCalls": N, "tools": ["..."]}}` - `error` — An error occurred during processing. Data: `{"error": "...", "code": "..."}` **Multi-turn conversations:** Pass previous messages in the `messages` array and reuse the `conversationId` returned in the `done` event. **Rate limits:** This endpoint is rate-limited per tenant (requests/hour) and subject to token usage limits. ### Ticket creation (two-step draft → confirm) When the tenant has an active ticket-provider connection (e.g. Linear), the agent may emit a `draftTicket` tool call. The `tool_result` event includes an `output` field shaped like: ```json { "step": 2, "toolName": "draftTicket", "displayName": "Drafting ticket", "output": { "draft": { "provider": "linear", "title": "Billing page 500 for enterprise users", "description": "...", "target": { "teamId": "t_123", "teamName": "Core", "teamKey": "CORE" }, "labelIds": ["lbl_bug"], "source": { "type": "conversation", "conversationId": "conv-abc-123" } }, "availableLabels": [ { "id": "lbl_bug", "name": "bug", "color": "#f00" } ], "dedupWarning": null } } ``` API consumers should render this draft to the end user. To confirm (optionally with edits), send a follow-up user message asking the agent to call `createTicket` with the final payload. The `createTicket` `tool_result` event contains: ```json { "step": 3, "toolName": "createTicket", "displayName": "Creating ticket", "output": { "status": "created", "providerIdentifier": "LIN-99", "providerTicketUrl": "https://linear.app/acme/issue/LIN-99" } } ``` `status` is `"created"` on success, `"already_exists"` when deduplication matched an existing ticket (the existing `providerIdentifier` / `providerTicketUrl` are returned), or the event may carry an `error` field (e.g. `"provider_needs_setup"`).

cURL

curl --request GET \
  --url https://www.greenflash.ai/api/v1/users/{userId}/analytics \
  --header 'Authorization: Bearer <token>'

{
  "averageUserSentiment": {
    "label": "neutral",
    "score": 0.05
  },
  "averageChangeInUserSentiment": {
    "label": "improving",
    "score": 0.12
  },
  "averageFrustration": {
    "label": "moderate",
    "score": 0.38
  },
  "averageStruggle": {
    "label": "low",
    "score": 0.2
  },
  "averageCommercialIntent": {
    "label": "low",
    "score": 0.15
  },
  "averageConversationRating": 4.2,
  "averageConversationQualityIndex": 6.8,
  "topics": [
    {
      "name": "billing",
      "count": 15
    },
    {
      "name": "account access",
      "count": 12
    },
    {
      "name": "feature questions",
      "count": 8
    }
  ],
  "keywords": [
    {
      "name": "refund",
      "count": 9
    },
    {
      "name": "login",
      "count": 7
    }
  ],
  "summary": {
    "profileSummary": "Engaged user who frequently asks about billing and account access.",
    "behavioralPatterns": [
      {
        "pattern": "Returns to ask follow-up questions within 24 hours",
        "evidence": "Across 12 conversations, started a new thread the day after resolving the prior one.",
        "frequency": "recurring"
      }
    ],
    "engagement": {
      "level": "regular",
      "trajectory": "stable",
      "description": "Consistent weekly usage with steady conversation volume over the last 30 days."
    },
    "signals": [
      {
        "type": "insight",
        "title": "Billing questions dominate",
        "description": "Roughly a third of conversations involve billing, suggesting unclear pricing surfaces.",
        "priority": "medium"
      }
    ],
    "productAlignment": {
      "summary": "Uses core support flows but rarely engages with self-serve documentation.",
      "strengths": [
        "Quick to adopt new chat features"
      ],
      "gaps": [
        "Does not discover the in-app billing FAQ"
      ]
    },
    "methodology": "Generated from 47 conversations spanning the last 90 days."
  },
  "totalConversations": 47
}