← WebMCP Directory

livevariant.com

livevariant.com

live Unverified (seed import) Productivity & Business 9 tools imperative implementation

Adaptive A/B testing where the entire test lives in a URL. Traffic shifts toward the winner while the test runs, several elements are optimized as one combination, and no raw visitor data is stored.…

First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com

Answer 3 · Act 5 · Transact 1 · Score: Not yet scored

Tool inspector

generate_priors

act imperative

Takes YOUR estimate of how each variant will perform and converts it into the prior the model starts from, so a test does not spend its first visitors rediscovering what you already suspect. You supply the guess; this does the arithmetic and the capping. That capping is the point: a prior is expressed as pseudo-observations, and it is deliberately held weak enough that real data overrides it quickly. The response says exactly how many real visitors per variant it takes to wash your guess out, so you can judge whether you have been too confident. Being wrong here costs a little early traffic, not the test. Priors are outside the identity hash, so the test keeps its id, its URLs and any history it already has. Pass `when` to make the belief hold for ONE segment only ("image B is the one for the blue segment"). Without it the belief is about every visitor, which is a different and much stronger claim.

Page: /

Input schema

PropertyTypeRequiredDescription
test string no The test: an encoded config, or any LiveVariant URL containing one (serve, click, pixel, manage), or a query-parameter serve URL. Paste whatever you have.
config string no Alias for `test`: the same value under the name build_test returns it as (`config`). Pass one or the other.
when object no Context this belief is limited to, as dimension key to value (e.g. {"color": "blauw"}). The keys must be dimensions the test declares. Omit it for a belief about every visitor.
beliefs array yes —
confidence — no How much your guess is worth in observations. low=5, medium=15, high=30, or give a number directly. Higher means the test trusts you for longer before the data takes over.
Raw JSON schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "test": {
      "type": "string",
      "minLength": 1,
      "description": "The test: an encoded config, or any LiveVariant URL containing one (serve, click, pixel, manage), or a query-parameter serve URL. Paste whatever you have."
    },
    "config": {
      "type": "string",
      "minLength": 1,
      "description": "Alias for `test`: the same value under the name build_test returns it as (`config`). Pass one or the other."
    },
    "when": {
      "description": "Context this belief is limited to, as dimension key to value (e.g. {\"color\": \"blauw\"}). The keys must be dimensions the test declares. Omit it for a belief about every visitor.",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {
        "type": "string"
      }
    },
    "beliefs": {
      "minItems": 1,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "slot": {
            "description": "Which slot the variant belongs to. Optional for single-slot tests.",
            "type": "string"
          },
          "variant": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "integer",
                "minimum": -9007199254740991,
                "maximum": 9007199254740991
              }
            ],
            "description": "Variant name or index within its slot."
          },
          "rate": {
            "type": "number",
            "minimum": 0,
            "maximum": 1,
            "description": "Your estimate of its conversion rate, e.g. 0.04 for 4%."
          }
        },
        "required": [
          "variant",
          "rate"
        ]
      }
    },
    "confidence": {
      "default": "medium",
      "description": "How much your guess is worth in observations. low=5, medium=15, high=30, or give a number directly. Higher means the test trusts you for longer before the data takes over.",
      "anyOf": [
        {
          "type": "string",
          "enum": [
            "low",
            "medium",
            "high"
          ]
        },
        {
          "type": "number",
          "exclusiveMinimum": 0
        }
      ]
    }
  },
  "required": [
    "beliefs"
  ],
  "oneOf": [
    {
      "required": [
        "test"
      ]
    },
    {
      "required": [
        "config"
      ]
    }
  ]
}

Similar websites

econsor.de

econsor.de

German digital agency building portals, e-commerce sites and online marketing, combining strategy, design and AI to grow clients' visibility and customer base.

live Unverified Productivity & Business Transact tools
143 tools A0 / Act142 / T1 Not yet scored Seen 2026-11-05
econsor_click_search econsor_click_image econsor_click_menu econsor_click_burger_menu_icon econsor_click_previous_button
Inspect tools
inkframe-eta.vercel.app

inkframe-eta.vercel.app

Browser-native Elah video editor for 9:16 and 16:9 exports

live Unverified Productivity & Business Transact tools
87 tools A12 / Act71 / T4 Not yet scored Seen 2026-11-05
get_capabilities list_templates navigate_workspace open_template editor_inspect_video_moments
Inspect tools
agentdesk-demo.vercel.app

agentdesk-demo.vercel.app

Meridian Ops

live Unverified Productivity & Business Transact tools
83 tools A43 / Act24 / T16 Not yet scored Seen 2026-11-05
find_capabilities invoke_capability get_context get_action_status search_customers
Inspect tools
eworker.ca

eworker.ca

E-Worker is business infrastructure powered by AI, with focused apps and connected business work.

live Unverified Productivity & Business
73 tools A10 / Act63 / T0 Not yet scored Seen 2026-11-05
eworker_site_status eworker_list_apps eworker_resolve_app eworker_open_app ewdoc_status
Inspect tools

Related on Influzer