AgentRXI Docs Q&A

Use this endpoint when you need to answer a natural language question grounded in a specific website or documentation source that you don't control or can't embed yourself. It is ideal when the target site changes infrequently (7-day index reuse amortizes cost), when you need cited, verifiable answers rather than hallucinated responses, and when you want to avoid building your own RAG pipeline. Prefer this over a general web search when the answer must come specifically from one known domain.

• Site unreachable or blocked by robots.txt — crawl fails and no answer is returned
• Question cannot be answered from crawled content — answer may indicate insufficient information
• max_pages limit reached before relevant content found — answer may be incomplete
• Index expired after 7 days — re-crawl required, increasing latency
• Non-English or heavily JS-rendered sites may yield poor text extraction