# Convrgent.ai Rapport Health Scorer

> Convrgent.ai Rapport Health Scorer is a paid API for AI agents from convrgent.ai, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-15).

Scores the health of a conversation relationship in real time, returning trust trajectory, warmth signals, rapport breaks, engagement trend, and repair suggestions from conversation history.

## Facts

- Endpoint: POST https://convrgent.ai/api/blah/rapport
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/convrgent-ai-445e71e9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_3AlTWIx7P3EFqMxqrvVBB

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability convrgent-ai-445e71e9 -d '<json body>'
```

Example prompt: Score the relationship health of my last 10 messages with this user — I want to see the trust trajectory, any warmth signals, whether there's been a rapport break, the engagement trend, and what repair steps I should take if things have gone cold.

## When to prefer this

Use this endpoint when you need a lightweight, real-time signal on conversation relationship quality — especially when running an AI agent that manages ongoing human interactions and needs to adapt tone or strategy based on how the relationship is trending. Prefer this over a full psychological profile endpoint when you only need conversational health signals, not deep personality modeling, and when cost per call matters (at $0.01 it's designed to be called frequently).

## Known failure modes

- Empty or too-short conversation history — insufficient signal to score rapport
- Malformed conversation history format — returns validation error
- Payment not attached or insufficient USDC balance — 402 payment required
- Rate limiting if called excessively in rapid succession
- Ambiguous speaker attribution in transcript causing skewed scores

## How this service works

Real-time relationship health scoring from conversation history. Trust trajectory, warmth signals, rapport breaks, engagement trend, and repair suggestions. Cheap enough to call every few turns.

## Output

Returns a structured rapport health assessment including a numeric or categorical health score, trust trajectory (rising/falling/stable), warmth signal indicators, detected rapport breaks, engagement trend, and actionable repair suggestions — cheap enough to re-call every few conversation turns.

## Request schema (JSON Schema)

```json
{
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "type": "string",
     "enum": [
      "POST"
     ]
    },
    "bodyType": {
     "type": "string",
     "enum": [
      "json",
      "form-data",
      "text"
     ]
    },
    "body": {
     "properties": {
      "history": {
       "type": "array",
       "items": {
        "type": "object"
       },
       "minItems": 2,
       "maxItems": 50
      },
      "domain": {
       "type": "string"
      },
      "relationship_type": {
       "type": "string",
       "enum": [
        "new",
        "established",
        "professional",
        "support",
        "sales"
       ]
      },
      "kyh_profile": {
       "type": "object"
      }
     },
     "required": [
      "history"
     ]
    }
   },
   "required": [
    "type",
    "bodyType",
    "body",
    "method"
   ],
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   },
   "required": [
    "type"
   ]
  }
 },
 "required": [
  "input"
 ]
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "mode": "contextual",
  "trend": "stable",
  "signals": [
   {
    "turn": 2,
    "type": "positive",
    "signal": "Direct questions about specifics",
    "evidence": "What's your uptime guarantee?"
   },
   {
    "turn": 6,
    "type": "neutral",
    "signal": "Minimal response to pricing",
    "evidence": "Send it over."
   }
  ],
  "trust_level": 0.55,
  "warmth_level": 0.4,
  "rapport_score": 0.58,
  "rapport_breaks": [],
  "engagement_level": 0.65,
  "repair_suggestions": [
   "Add a personal touch — ask about their current setup",
   "Show curiosity about their evaluation criteria"
  ],
  "trajectory_summary": "Transactional but not cold. The human is in evaluation mode — engaged but guarded. No rapport breaks, but also no warmth building. Opportunity to deepen before the formal quote."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/convrgent-ai-445e71e9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from convrgent.ai](https://www.zero.xyz/host/convrgent.ai/llms.txt)