Website RAG Readiness Audit Report

Buyable first run

Use this Actor when AI builders, documentation teams, support teams, and technical marketers need to decide whether public website pages are clean and complete enough for RAG ingestion. It is positioned as a report, not a raw scraper.

• Entry report: $9 / website_rag_snapshot_report. $9 checks public pages for volume, structure, noise, and basic RAG risk.
• Premium report: $29 / website_rag_readiness_report. $29 adds chunking risk, retrieval QA actions, coverage gaps, and cleanup priorities.
• Public price surface is entry and premium only. High-tier/watch events are held until real paid proof exists.
• Safety cap: maxChargeUsd is the hard budget limit.
• Why it is worth paying for: Avoids embedding public website content that is too thin, noisy, or poorly structured for retrieval.

Recommended first paid run:

{
  "demoMode": false,
  "dryRun": false,
  "reportTier": "snapshot",
  "maxChargeUsd": 9,
  "maxReports": 1,
  "maxPages": 2,
  "urls": [
    "https://docs.apify.com/platform/actors"
  ],
  "seedQuestions": [
    "Can this documentation answer onboarding and troubleshooting questions?",
    "What content cleanup is needed before embedding?"
  ]
}

This Actor does not promise rankings, revenue, conversion lifts, or sales outcomes. It returns source-backed summaries, warnings, and prioritized actions.

What It Does

Website RAG Readiness Audit Report fetches public pages you provide, extracts visible text signals, and returns a decision-ready report for whether the pages are suitable for retrieval-augmented generation workflows.

It focuses on:

• content volume and thin-page risk
• navigation boilerplate and chunking risk
• source URL coverage and blocked pages
• missing answer coverage for your seed questions
• prioritized cleanup actions before embedding

Pricing Events

• website_rag_snapshot_report - $9
• website_rag_readiness_report - $29 Use the listed report tiers for public runs; recurring watch workflows should be created as Apify tasks from a successful paid input.

demoMode, dryRun, invalid URLs, blocked/private pages, no-content pages, source failures, and cap-limited groups are no-charge.

Source Rules

Allowed: public website URLs, public docs, help pages, blogs, product pages, pricing pages, sitemaps in a future version.

Blocked: login-only pages, private dashboards, paywalls, checkout/account portals, CAPTCHA/rate-limit bypass, personal data extraction, and unsupported business outcome claims.

Output

Each dataset row includes status, chargedEvent, chargedUsd, reason, decisionSummary, score, prioritizedActions, sourceUrls, warnings, and errors.