discoveredlabs.com
AEO/GEO agency that helps B2B companies get recommended in AI search results when customers ask AI assistants for suggestions.
First seen 2026-10-12 · Last seen 2026-10-12 · Source: webmcp.com
Answer 0 · Act 1 · Transact 1 · Score: Not yet scored
Tool inspector
calculate_eval_sample_size
Calculate the statistically valid number of prompts and API calls for an LLM brand-mention evaluation. Call when planning an eval; pass confidence (default 95), margin_of_error_pct (default 2), resamples_per_prompt (default 3), var_between and var_within. Returns unique_prompts and total_api_calls.
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
confidence |
number | no | Statistical confidence level as a percentage (default 95) |
margin_of_error_pct |
number | no | Acceptable margin of error as a percentage (default 2) |
resamples_per_prompt |
number | no | Number of times to resample each prompt to reduce within-question noise (default 3) |
var_between |
number | no | Between-question variance — how much brand mention rates differ across different questions (default 0.02) |
var_within |
number | no | Within-question variance — how much the model wobbles when answering the same question (default 0.05) |
Raw JSON schema
{
"type": "object",
"properties": {
"confidence": {
"type": "number",
"description": "Statistical confidence level as a percentage (default 95)",
"minimum": 80,
"maximum": 99,
"default": 95
},
"margin_of_error_pct": {
"type": "number",
"description": "Acceptable margin of error as a percentage (default 2)",
"minimum": 0.5,
"maximum": 5,
"default": 2
},
"resamples_per_prompt": {
"type": "number",
"description": "Number of times to resample each prompt to reduce within-question noise (default 3)",
"minimum": 1,
"maximum": 20,
"default": 3
},
"var_between": {
"type": "number",
"description": "Between-question variance — how much brand mention rates differ across different questions (default 0.02)",
"minimum": 0,
"maximum": 0.1,
"default": 0.02
},
"var_within": {
"type": "number",
"description": "Within-question variance — how much the model wobbles when answering the same question (default 0.05)",
"minimum": 0,
"maximum": 0.2,
"default": 0.05
}
},
"required": []
}
Similar websites
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.
eworker.ca
E-Worker is business infrastructure powered by AI, with focused apps and connected business work.
laydyne.com
Describe your space and workflow to AI. Build layouts, adapt process scenarios, and compare simulations through MCP or the built-in assistant.
takemeup.cv
Free CV builder: make a polished, ATS-friendly CV in minutes. No watermarks, no sign-up. Import from LinkedIn, tailor to any job, export PDF.