Changelog

Choose dates in a clearer calendar

• Search Console dates, publication dates and work deadlines now share a calendar with keyboard controls and clear date limits.
• Dropdowns across onboarding, imports, recommendations and settings now use consistent Aureo controls.
• The calendar adapts to mobile screens and your light or dark theme. You can still type a date directly.

Connect Search Console to your brand

• Connect Google in Settings, Integrations, and choose a Search Console property for each brand.
• Fetch Google queries for your chosen dates and filters, then review which questions to add to AI tracking.
• Owners manage accounts and property mappings. Disconnecting keeps previously adopted questions and their source history.

Turn Google queries into questions to track

• Import an extracted Search Console CSV in Prompts. Review cleaned rows locally before sending selected queries for AI review.
• Edit and review suggested wording, then choose which questions join your existing allowance. Google counts stay separate from AI measurements.

Review the pages behind AI answers

• Sources now has a page queue with exact URLs, questions, engines and retained answer evidence.
• On Plus and above, keep private review notes and record which pages are relevant, contacted or unsuitable.
• Check whether a source page loads, without confusing availability with an editorial opportunity.

Follow the work through Aureo

• On Agency, invite clients to view selected brands. They can read results, recommendations and reports, while you control their access.
• Invite teammates from Workspace settings, switch between your workspaces, and keep team and billing controls with the owner.
• The product guide highlights real sections across results, questions, gaps, recommendations and reports.
• Empty states explain what comes next, and the guide is available from the mobile More menu.
• Skip without marking the guide complete. Replay it whenever you need it.
• Recommendation results explain when query, model, search or sample changes prevent a before-and-after comparison.

Keep setting up your brand when AI analysis is unavailable

• Gap actions distinguish a rejected proposal from an unavailable analysis and explain when no task was created.
• Query drafts consider distinct buying needs and alternatives beyond identical materials. Recommendations require a concrete information gap before entering the task queue.
• Business profiles stay in English. Site reading suggests the page language for queries and keeps your manual language choices.
• Brand setup supports a separate AI provider for profiles, competitor suggestions and reviewed query drafts.
• Site reading can use the page title and description when AI analysis cannot finish. Missing details stay empty for you to review.
• Site reading follows linked About pages, removes repeated text and preserves details you already entered.

Prepare a client summary from recorded work

• Add agency commentary and choose the next recorded action for a reporting period
• Save summary versions and export a separate PDF with work, sources and available measurements
• Read client PDFs with clearer evidence rows, dated observations and a distinct next action
• Keep missing baselines, pending measurements and incompatible comparisons explicit

Record the work, then measure the answers

• Search queries, keep filters when returning from a detail and open client work on mobile
• Resume setup from saved brand details and see when scan progress updates lose connection
• Reveal passwords while typing and recover an email confirmation without starting again
• Jump to sections and copy setup examples in the public documentation
• Find your next recommendation in a compact list and open only the details you need
• Prepare a page brief with sources, save versions and copy it for your team
• Assign recommendations to existing workspace members, set a due date and track work separately from publication
• Filter work assigned to you and keep unsaved work details when reviewing evidence or briefs
• Read an empty gap list without an unsupported claim about your coverage
• Rate recommendations without changing their publication status
• Skip new recommendations when the review finds the requested work already covered
• Review engine-specific evidence and recurring gaps before acting
• Group recommendations by page and check the text you published
• Import customer questions through a sanitised preview and choose reviewed drafts
• Dashboard metrics name their sample and measured dates, with commercial priorities first
• Compare periods only when the recorded questions, engines and measurement method match
• Separate brand recognition from questions where AI must discover you
• Record a published URL, its date and what changed on each recommendation
• Compare later answers with the last weekly measurement before publication
• Find ready, published and dismissed work with recommendation filters
• See your next recommendation before the dashboard metrics
• Mark commercially important queries to prioritise the work
• See scan freshness and work awaiting measurement across client brands
• Read completed work and available outcomes in the PDF report
• Keep your domain, selected plan and billing interval through signup

The dashboard learns what matters most, and agents can read the site

A day of sharpening: the dashboard now leads with the week’s finding, and the whole site became readable to AI agents, which is only fair for a product that measures exactly that.

• The week’s insight (new gaps, with its buttons) moved above the metric cards
• Metric cards come in two sizes now, weighed the way the visibility score weighs them
• Reports, Traffic and Portfolio are reachable on a phone through the More sheet
• Markdown mirrors of the main pages at /index.md, /pricing.md and friends, plus llms.txt, so assistants can quote us accurately
• A Developers footer column, and docs playbooks: Aureo in Claude in one command, and scan results in Slack through a signed webhook relay
• A lapsed subscription keeps every recommendation it paid for, read only
• Report a bug or an idea from inside the app, with steps, a screenshot, and the technical context collected for you
• Checkout now handles EU VAT properly: 25% for Croatia, reverse charge with VAT ID validation for EU businesses, prices stay net

Export, the heatmap, and a plan for people between Starter and Growth

• CSV export of queries, gaps and cited sources
• A per engine heatmap of who each engine names, with the sample size in every column head
• Suggested queries: the generator proposes, nothing enters your set without a click
• The buyer’s journey: discovery, active search and comparison, each with its own reading
• The Plus plan at 119 EUR: 50 queries with recommendations and alerts included
• Starter repriced to 49 EUR with 15 queries; Agency pools 300 queries across 10 brands

Being recommended is not the same as being named

The week the metrics grew up, and the product got a developer surface.

• Soft mentions: an answer that names you without recommending you is counted as what it is
• The visibility score now weighs being recommended above being named
• Citation share: how much of the sourcing behind the answers is yours, per answer and in the report
• Re-ask a single query without moving the week it belongs to
• A REST API with scoped keys, an MCP server for Claude and Cursor, and signed outbound webhooks
• The /sources screen: every domain the engines cite in your niche, by format

Aureo reads the site it advises on

• Every scan now checks your own site first: robots.txt, the AI crawlers it admits, llms.txt, and whether GPTBot actually gets a page
• Recommendations argue from what your site already publishes, so "write this page" becomes "fix this URL" where that is the truth
• Confidence intervals on the headline metrics: a move inside the sample noise is shown grey, not claimed
• Agency logo upload for white label reports
• Settings is one screen again, and every screen shows its shape while it loads

Queries get their own screen

• Add and retire queries on the queries screen, with the pooled plan limit enforced where you type
• Competitor suggestions from the names the engines keep bringing up
• Scheduled mail arrives at eight in your own morning, wherever you are
• One company counted once per answer, with its domain worked out from its own citations

The first version

• Weekly scanning across ChatGPT, Perplexity and Gemini
• Share of voice, mention rate, average position and citation presence
• Citation gap analysis with the sources each engine quotes
• Recommendations with the evidence they were derived from
• PDF report and weekly email