---
title: "AI Recommendation Potential — per-prompt-class breakdown of how likely AI engines (ChatGPT, Claude, Gemini, Perplexity, Grok) are to recommend the entity. Projects stored Decision Survival probes onto a canonical prompt-class taxonomy (Discovery, Evaluation under pushback, Constrained final choice; hiring / learning / category leaders / risk / adjacent are framework-declared and not yet probed). Coded reducer, zero LLM cost."
method: GET
path: "/entities/{entityId}/recommendation-potential"
tags: ["Layer 1 — Profile"]
---

# AI Recommendation Potential — per-prompt-class breakdown of how likely AI engines (ChatGPT, Claude, Gemini, Perplexity, Grok) are to recommend the entity. Projects stored Decision Survival probes onto a canonical prompt-class taxonomy (Discovery, Evaluation under pushback, Constrained final choice; hiring / learning / category leaders / risk / adjacent are framework-declared and not yet probed). Coded reducer, zero LLM cost.

`GET /entities/{entityId}/recommendation-potential`

## Request

- Base URL: `https://entidex.com/api/v1`
- URL: `https://entidex.com/api/v1/entities/{entityId}/recommendation-potential`
- Auth: HTTP bearer

## Path parameters

- `entityId` string, required

## Response `200`

AI Recommendation Potential, or { available: false } when the entity has no Decision Survival probes yet.

- union
  - RecommendationPotential: Per-prompt-class breakdown of AI recommendation likelihood. Projects stored Decision Survival probes onto a canonical 8-class prompt-class taxonomy (3 measured, 5 planned). Coded reducer, zero LLM cost.
    - `entityId` string, required: Canonical entx_xxxx id.
    - `available` true, required
    - `computationVersion` string, required
    - `overallPct` integer, nullable, required: Weighted-mean recommendation rate across measured classes.
    - `trials` integer, required
    - `survived` integer, required
    - `classesEvaluated` integer, required: Number of measured classes that contributed a reading.
    - `confidence` ScoreConfidence, required: 95% Wilson confidence envelope under a Score (confidenceLayer.ts). All fields optional.
      - `interval95` number[]: [lower, upper] on the same 0..N scale as the score value.
      - `variance` number, nullable
      - `sampleSize` integer: Observations the score is computed over (enginesEvaluated for Decision Survival).
      - `probeRunIds` string[]: Contributing probe_run UUIDs (capped at 20).
      - `lastObservedAt` string, date-time
      - `version` string: Confidence-Layer scoring version.
    - `classes` PromptClassRead[], required
      - `classId` 'discovery' | 'evaluation' | 'constrained_choice' | 'hiring' | 'learning' | 'category_leader' | 'risk_assessment' | 'adjacent', required: Canonical prompt-class id (CANON Amendment 22 taxonomy).
      - `label` string, required
      - `description` string, required
      - `example` string, required: Illustrative prompt; the probes use canonical scenarios, not this string.
      - `measured` boolean, required: True when derived from stored Decision Survival probes.
      - `reading` object, nullable, required
        - `trials` integer, required
        - `survived` integer, required
        - `recommendationPct` integer, required
        - `interval95` number[]: 95% Wilson interval on 0..100.
        - `enginesEvaluated` integer, required
        - `lastObservedAt` string, date-time, nullable, required
        - `perEngine` EnginePromptClassRead[], required
          - `engine` string, required
          - `maker` string, nullable, required
          - `makerHref` string, nullable, required
          - `trials` integer, required: Replications this engine ran for the class.
          - `survived` integer, required: Trials in which the entity was still recommended at the final turn.
          - `recommendationPct` integer, nullable, required
    - `strongestClasses` PromptClassRead[], required
      - `classId` 'discovery' | 'evaluation' | 'constrained_choice' | 'hiring' | 'learning' | 'category_leader' | 'risk_assessment' | 'adjacent', required: Canonical prompt-class id (CANON Amendment 22 taxonomy).
      - `label` string, required
      - `description` string, required
      - `example` string, required: Illustrative prompt; the probes use canonical scenarios, not this string.
      - `measured` boolean, required: True when derived from stored Decision Survival probes.
      - `reading` object, nullable, required
        - `trials` integer, required
        - `survived` integer, required
        - `recommendationPct` integer, required
        - `interval95` number[]: 95% Wilson interval on 0..100.
        - `enginesEvaluated` integer, required
        - `lastObservedAt` string, date-time, nullable, required
        - `perEngine` EnginePromptClassRead[], required
          - `engine` string, required
          - `maker` string, nullable, required
          - `makerHref` string, nullable, required
          - `trials` integer, required: Replications this engine ran for the class.
          - `survived` integer, required: Trials in which the entity was still recommended at the final turn.
          - `recommendationPct` integer, nullable, required
    - `weakestClasses` PromptClassRead[], required
      - `classId` 'discovery' | 'evaluation' | 'constrained_choice' | 'hiring' | 'learning' | 'category_leader' | 'risk_assessment' | 'adjacent', required: Canonical prompt-class id (CANON Amendment 22 taxonomy).
      - `label` string, required
      - `description` string, required
      - `example` string, required: Illustrative prompt; the probes use canonical scenarios, not this string.
      - `measured` boolean, required: True when derived from stored Decision Survival probes.
      - `reading` object, nullable, required
        - `trials` integer, required
        - `survived` integer, required
        - `recommendationPct` integer, required
        - `interval95` number[]: 95% Wilson interval on 0..100.
        - `enginesEvaluated` integer, required
        - `lastObservedAt` string, date-time, nullable, required
        - `perEngine` EnginePromptClassRead[], required
          - `engine` string, required
          - `maker` string, nullable, required
          - `makerHref` string, nullable, required
          - `trials` integer, required: Replications this engine ran for the class.
          - `survived` integer, required: Trials in which the entity was still recommended at the final turn.
          - `recommendationPct` integer, nullable, required
    - `methodology` string, required
    - `provenance` object, required
      - `issuer` string, required
      - `methodologyUrl` string, uri, required
      - `note` string, required
  - RecommendationPotentialUnavailable
    - `entityId` string, required
    - `available` false, required
    - `reason` 'no_signal_yet' | 'entity_out_of_scope' | 'disabled', required

## Other responses

- `404`: Entity or resource not found.

---

[API](https://skmtc.dev/entidex/apis/entidex-api.md) · [All operations](https://skmtc.dev/entidex/apis/entidex-api/llms.txt) · [OpenAPI document](https://skmtc.dev/entidex/apis/entidex-api/revisions/86b92f21a09a?raw)