v0.0.19: Answer Archive, GSC Prompt Import & AI Mode Finalized

Answers

Answer archive and diff

From the rankings drill-down, any past scan’s answer to a question can be reopened, with the wording changes against the previous scan shown as additions and removals and the claims the answer made or dropped. That is answer text diffing, which makes a hallucinated-claims problem visible: what an engine changed its answer to, and when.

Search Console queries to tracked prompts

The Search Console top-queries table imports the queries already earning you clicks as tracked prompts in one click: demand from your own property instead of a guessed list. Imports land inactive, since activation counts against your plan’s active-prompt cap. They dedupe case-insensitively against your existing prompts and carry estimated monthly volume wherever a keyword provider is configured. The tracking Google search performance tutorial covers the Search Console side; choosing tracked prompts covers what happens once they are in the library.

Google AI Mode

AI Mode moved out of the engine picker

Google AI Mode joined the weekly SEO-data pass in v0.0.18. It no longer appears in the AI engine picker in Settings. Like Google AI Overviews, it is not a model you select: on paid plans it runs automatically every week alongside AI Overviews, answered by a search lookup rather than a chat model and billed on the SEO-data meter instead of your credit allowance.

Search Console’s generative AI report

Search Console’s generative AI performance report (announced June 2026) is impressions-only, reports AI Overviews and AI Mode together, is rolling out to properties gradually, and is not yet in Google’s API. The knowledge base says exactly that, so the report is not read as more than it is. AI Mode visibility in LLM Metrix comes from the weekly SEO-data pass instead.

Search surfaces

Microsoft Copilot on the weekly pass

Microsoft Copilot is tracked on the weekly SEO-data pass as its own search surface: the answer panel from Bing’s copilotsearch page. It is billed on the SEO-data meter, not your credit allowance, and skipped when no search provider serves it.

Deep Research

Research runs

A Deep Research run asks a research model to answer your tracked prompts with a full report, then grades each report for brand mention, rank, stance and claims. On paid plans it bills from your credit allowance on its own meter.

Recommendations

Generated artifacts

A recommendation on the board can be turned into a deliverable (an llms.txt file, schema JSON-LD, or a content brief) and copied or downloaded from the item.

Public API

Read and write endpoints, plus MCP

The developer API grew from two read-only endpoints to a read-and-write REST surface: trigger scans, retry jobs, manage prompts and the webhook URL, plus an MCP server for AI agents, all on the same personal access tokens.