Open-source agentic AI Search Execution Platform. Track AI visibility, find opportunities, and let agents turn signals into prioritized actions and drafted fixes across ChatGPT, Claude, Gemini, Google AI Overviews, Google AI Mode, Perplexity, Grok, and Microsoft Copilot.
TypeScript aeoai-agentai-searchanswer-engine-optimizationbrand-monitoringchatgptclaudecopilotdockergeminigeogoogle-ai-overviewsgrokmcpnextjsopen-sourceperplexityseosupabasetypescript
docs: document SCRAPEDO_API_KEY + AUDIT_LLM_MODEL for Site Audit (#294)
Gökhan Geyik6d80d08017f2
diff --git a/docs/faq.mdx b/docs/faq.mdxindex 96f368f02..cd25b328d 100644--- a/docs/faq.mdx+++ b/docs/faq.mdx@@ -16,6 +16,8 @@ description: "Common questions about Ansvisor."<Accordion title="Why don't you scrape ChatGPT/Gemini directly?">For programmable AI engines (OpenAI, Anthropic, Google Gemini API), Ansvisor uses official APIs — most reliable, well-priced, and TOS-compliant. For *web* AI engines that don't have public APIs (like ChatGPT.com search results), Ansvisor uses Cloro as a managed scraping backend. Cloro handles browser fingerprinting, captcha bypass, and rate-limiting at scale.++ These are two distinct fetchers: **Cloro** scrapes the AI answer engines, while **Scrape.do** (via `SCRAPEDO_API_KEY`) fetches your *own* pages for the **Site Audit** feature (proxy + JS render). Self-hosters who want Site Audit need a Scrape.do key.</Accordion><Accordion title="How often does tracking run?">diff --git a/docs/self-host/env-variables.mdx b/docs/self-host/env-variables.mdxindex 4fb33ebc7..7952c41f8 100644--- a/docs/self-host/env-variables.mdx+++ b/docs/self-host/env-variables.mdx@@ -44,12 +44,14 @@ Fed to the Express API + workers.| `TOPIC_SUGGESTION_MODEL` | optional | LLM for topic suggestions || `PROMPT_SUGGESTION_MODEL` | optional | LLM for prompt suggestions || `COMPETITOR_SUGGESTION_MODEL` | optional | LLM for competitor suggestions |+| `AUDIT_LLM_MODEL` | optional | LLM for the Site Audit's LLM-judged signals + AI recommendations (default: `google/gemini-3-flash-preview`) || `ALLOWED_ORIGINS` | ✅ | Comma-separated list of web origins allowed to call the API (for CORS) || `IS_CLOUD` | optional | `"true"` only for the official cloud build || `DATAFORSEO_LOGIN` | optional | DataForSEO login (for prompt volume analysis) || `DATAFORSEO_PASSWORD` | optional | DataForSEO password || `CLORO_API_KEY` | optional | Cloro web scraper API key (for ChatGPT/Gemini/Perplexity web scraping) || `PLATFORM_PROVIDER` | optional | Default `cloro`. Used to pick scraper backend |+| `SCRAPEDO_API_KEY` | Site Audit | Scrape.do API key — required to run **Site Audit** (it fetches target pages via Scrape.do's proxy + JS render). Distinct from `CLORO_API_KEY`, which scrapes the AI answer engines. || `AI_VOLUME_MULTIPLIER` | optional | Estimated AI search adoption rate (default `0.15` = 15% of Google volume) || `CRON_SECRET` | cloud only | Shared secret with web's CRON_SECRET; protects internal cron endpoints |