Check the work, and protected chat pages
- A new xMap AI block, Check the work, checks what an xMap LLM or AI agent wrote before it goes out: your rules in plain words (every lead has a phone, a formal tone, under 120 words, no numbers that are not in the data) and ready-made checks. What fails can go back to be redone with what was wrong (up to 3 times), be removed, or stay marked.
- Chat pages and AI agents have Protection: they stay on the topics you set, refuse attempts to change their rules, never share personal data except the contact details you list, keep blocked words out of answers and keep answers short. A new chat page starts with the second and third on. The Conversations window counts the answers protected each week.
How to use it
Check the work before it goes outA second check of what xMap AI wrote: your rules, ready-made checks, and redoing what fails.Share tested AI instructions across flowsKeep how you score a lead or your tone of voice in one place, use it in every AI block, and improve it once for every flow.Run the AI blocks on your own AI providerUse your own OpenAI, Anthropic, Google Gemini, Azure OpenAI or OpenAI-compatible account for xMap LLM, the Place classifier and the AI agent.Build your first flow in ten minutesFrom a blank page to a flow that emails you a ranked list every morning.