v0.0.7: Tracked Prompts, Site Audit & Grounded Answers

Scans

Track your own prompts

Rather than relying only on automatically discovered questions, you can maintain a list of prompts per project, and scans draw from that list. The setting up tracked prompts tutorial walks through it. Each scan runs up to your plan’s per-scan prompt limit, so order the list by what matters most. Suggested prompts come with topic clustering and, when a keyword-data provider is configured, estimated search volume.

Site-wide content audit

Point the audit at your domain and it discovers and crawls your pages, scores each one for how well it answers the questions AI engines are asked, and aggregates the result into the Content Gaps view.

Search-grounded answers

Engines can be queried with their provider’s live web search enabled, so an answer comes back with the URLs it actually cited rather than domains inferred from the prose. There is no switch for this in the dashboard: it is off by default, and where it is enabled a grounded prompt carries a credit multiplier, because a grounded query costs more to run. Perplexity and Google AI Overviews are the exceptions in both directions: they search on every call, so their result is grounded already and carries no surcharge.

When grounding is off, a citation is a domain rather than a page. Where URL-level data is unavailable, the page says so rather than treating every ranking page as uncited.

Google AI Overviews

Scans can include Google AI Overviews, the answer block above Google’s results. It works differently from the other six: rather than querying a chat model it reads a search-data provider, so it is included when one is configured and skipped from a mixed scan when none is. That makes seven surfaces in total.

Free tools

Two more free tools

The free tool set gains an llms.txt audit and a schema markup generator.