​

Conversation Intelligence

​

What the panel computes

• KPI strip. Total conversations, average messages per conversation, resolution rate, solution rate, average duration, and quality score (with a period-over-period delta when the backend has a scored prior window). Read resolution and solution side by side: resolution counts conversations marked complete (gameable — an agent that auto-closes threads drives it to 100%); solution counts only threads where the customer confirmed resolution or the workflow closed with positive sentiment. When they diverge, trust solution.
• Conversation volume area chart. Daily conversation count over the selected window — pick 24h for incident triage, 7d/30d (default)/90d/12m for trend work, or a custom calendar range.
• Sentiment distribution donut. The sentiment_distribution aggregate — how many conversations in the window the AI analyzer classified as positive, neutral, or negative. Coverage notes below.
• Channel breakdown bar chart. The channelBreakdown aggregate — how many conversations each channel (SMS, WhatsApp, email, voice) contributed to the window.
• Recent conversations table. The recent_conversations list — the latest threads across all agents and channels, each carrying the agent name, channel, status, and (when the analyzer has classified it) sentiment. Default-capped to the most recent 25 with a View all expander.
• Agent leaderboard. Agents ranked by conversation volume, resolution rate, average handle time, CSAT proxy, and average token spend — the drill-in for “which agent is generating this sentiment.”

​

Reading the sentiment donut

​

Channel breakdown

​

Recent conversations — back to the per-thread view

​

Worked example: the week-over-week sentiment dip

1. Check the channel mix. The channel bar shows WhatsApp still dominates; nothing about the mix changed — so the dip is not a channel migration.
2. Scan the agent leaderboard. One agent — Order Status Bot — moved from 92% to 61% resolution. That is where the negative rows concentrate.
3. Open Recent Conversations and filter visually. The rows tagged Order Status Bot carry red Negative badges; expanding to all rows confirms the cluster is on this one agent, not spread across the fleet.
4. Drill into the agent. Click the agent name in the leaderboard to open its detail page; the agent conversation debug guide walks the per-turn view from there.
5. Export a snapshot if you need an offline record. The Export CSV button emits a self-describing file (range header, summary KPIs, sentiment counts, per-channel counts) so the delta you found survives attaching to a ticket.

​

Picking the right surface

• Conversation Intelligence (this page). Aggregate sentiment, channel mix, and agent ranking across every channel — “how are conversations trending, and which agent is driving the trend.”
• Interaction Search. A filterable, recency-ordered list over every message conversation and every voice call — “find and audit individual threads.” Reach for it when you need a specific thread, not a trend.
• Topic Intelligence. Aggregated contact reasons — “what customers contact us about and is it rising.” Reach for it when sentiment is fine but the inbound mix is shifting.

​

API contract

curl "https://api.orbit.devotel.io/api/v1/stats/conversation-intelligence?days=30" \
  -H "X-API-Key: $ORBIT_API_KEY"

import { Orbit } from "@devotel-orbit/node";

const orbit = new Orbit({ apiKey: process.env.ORBIT_API_KEY });

// The Node SDK has no typed conversation-intelligence module — read the
// endpoint through the orbit.request() escape hatch. The generic type
// parameter gives your warehouse sync a typed payload.
type ConversationIntelligence = {
  aggregates: {
    total_conversations: number;
    avg_messages_per_conversation: number;
    avg_duration_seconds: number;
    avg_tokens: number;
    avg_cost: number;
    resolution_rate: number;
    solution_rate: number;
    csat_delta: number;
    avg_response_time_ms: number;
  };
  sentiment_distribution: { positive: number; neutral: number; negative: number };
  channel_breakdown: { channel: string; count: number; avg_tokens: number; avg_cost: number }[];
  agent_leaderboard: {
    agent_id: string; agent_name: string; conversation_count: number;
    resolution_rate: number; avg_tokens: number; avg_response_time_ms: number;
    avg_handle_time_seconds: number; csat_proxy: number;
  }[];
  time_series: { date: string; count: number }[];
  recent_conversations: {
    id: string; agent_id: string; agent_name: string; channel: string;
    message_count: number; total_tokens: number; started_at: string;
    status: string; sentiment?: string; quality_score?: number;
  }[];
  top_topics: string[];
  surging_topics: string[];
  escalation_rate: number;
  avg_quality_score: number;
};

const { data } = await orbit.request<{ data: ConversationIntelligence }>(
  "GET",
  "/stats/conversation-intelligence?days=30",
);

console.log(data.sentiment_distribution.negative);  // feeds the escalation-rate alert

from orbit_sdk import OrbitClient

client = OrbitClient.from_env()  # reads ORBIT_API_KEY

# Same read via the Python SDK's escape hatch — raw dict returned, so
# your pipeline decoder works straight off the response shape below.
result = client.request(
    "GET",
    "/stats/conversation-intelligence",
    params={"days": 30},
)

print(result["data"]["sentiment_distribution"]["negative"])

​

Response envelope — a realistic window

{
  "data": {
    "aggregates": {
      "total_conversations": 1432,
      "avg_messages_per_conversation": 4.2,
      "avg_duration_seconds": 918.4,
      "avg_tokens": 1210.6,
      "avg_cost": 0.0024,
      "resolution_rate": 0.87,
      "solution_rate": 0.71,
      "csat_delta": 0.03,
      "avg_response_time_ms": 1450
    },
    "sentiment_distribution": { "positive": 841, "neutral": 402, "negative": 189 },
    "channel_breakdown": [
      { "channel": "whatsapp", "count": 610, "avg_tokens": 980.2, "avg_cost": 0.0019 },
      { "channel": "sms", "count": 512, "avg_tokens": 1340.1, "avg_cost": 0.0026 },
      { "channel": "voice", "count": 310, "avg_tokens": 1410.0, "avg_cost": 0.0029 }
    ],
    "agent_leaderboard": [
      {
        "agent_id": "agent_ord_26", "agent_name": "Order Status Bot",
        "conversation_count": 402, "resolution_rate": 0.92, "avg_tokens": 970.2,
        "avg_response_time_ms": 800,
        "avg_handle_time_seconds": 640.5, "csat_proxy": 0.88
      }
    ],
    "time_series": [
      { "date": "2026-09-21", "count": 192 },
      { "date": "2026-09-22", "count": 207 }
    ],
    "recent_conversations": [
      {
        "id": "conv_9f2c1a", "agent_id": "agent_ord_26", "agent_name": "Order Status Bot",
        "channel": "whatsapp", "message_count": 7, "total_tokens": 1820,
        "started_at": "2026-09-28T09:14:12.000Z",
        "status": "completed", "sentiment": "negative", "quality_score": 0.42
      }
    ],
    "top_topics": ["delivery status", "refund policy"],
    "surging_topics": ["refund policy"],
    "escalation_rate": 0.13,
    "avg_quality_score": 0.81
  },
  "meta": { "request_id": "req_01kgtw7n8", "timestamp": "2026-09-28T09:20:31.000Z" }
}

​

Fresh tenants — zeroed aggregate 200, never an error

{
  "data": {
    "aggregates": {
      "total_conversations": 0,
      "avg_messages_per_conversation": 0,
      "avg_duration_seconds": 0,
      "avg_tokens": 0,
      "avg_cost": 0,
      "resolution_rate": 0,
      "solution_rate": 0,
      "csat_delta": 0,
      "avg_response_time_ms": 0
    },
    "sentiment_distribution": { "positive": 0, "neutral": 0, "negative": 0 },
    "channel_breakdown": [],
    "agent_leaderboard": [],
    "time_series": [],
    "recent_conversations": [],
    "top_topics": [],
    "surging_topics": [],
    "escalation_rate": 0,
    "avg_quality_score": 0
  },
  "meta": { "request_id": "req_01kgtw81a", "timestamp": "2026-09-28T09:21:04.000Z" }
}

​

Errors

{
  "error": {
    "code": "INSUFFICIENT_SCOPE",
    "message": "API key missing required scope. Needs one of: analytics:read. Re-issue this key with the required scope from Settings → API Keys.",
    "status": 403
  },
  "meta": { "request_id": "req_01kgr2cx2", "timestamp": "2026-09-28T09:22:11.000Z" }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "Authentication required.",
    "status": 401
  },
  "meta": { "request_id": "req_01kgr2hbs", "timestamp": "2026-09-28T09:22:16.000Z" }
}

​

Field reference

​

See also

• Topic Intelligence — aggregated contact reasons across channels.
• Interaction Search — the unified per-thread list across messaging and voice.
• Agent conversation debug — per-turn agent behavior once a leaderboard row is implicated.
• Insights dashboards — the catalog of every other Insights surface.
• Sentiment portfolio — the how-customers-feel counterpart when sentiment itself is the question.