Start with a question about your website. Your assistant can use ScanMySEO's saved findings and evidence to help you decide what to do next. You do not need to know the names of individual checks or tools.
Find the right report
Show me the most useful saved audit for my website. Is it recent enough, and did it check the pages relevant to my question?
A recent audit may already answer your question. Ask the assistant to explain when it ran, what it covered and what remains unknown before requesting another crawl.
Work out what matters most
What should I fix next? Prioritise the evidence and likely repair effort, not just the health score.
Use the report to separate confirmed problems from possibilities that need investigation. Several findings may have a common cause, but a suggested shared cause is not proof that they come from the same template or setting.
Prepare a developer brief
Turn these findings into a repair brief, with affected pages, supporting evidence and a clear way to check each fix.
Ask for a focused explanation of what should change and what should stay untouched. ScanMySEO supplies the findings; it does not edit your website automatically.
Request a new audit
Check whether my account can run a new audit of this website, up to the page limit I specify. Explain any allowance or credit use before starting.
A new audit uses your existing ScanMySEO account and its current website, page and usage limits. Connecting an assistant does not start one. If the conversation is interrupted after a start, ask for its progress rather than requesting the same audit again.
A normal audit started through the assistant does not automatically request ScanMySEO's optional paid AI analysis.
Check whether a repair worked
Compare these reports. Were the affected pages actually checked again, and does the evidence confirm the fix?
A finding disappearing from a smaller report does not necessarily mean it was fixed: the page may not have been revisited. Compare like-for-like evidence and keep any coverage gaps clear. Do not assume a smaller crawl will reach a particular list of pages.
Keep extra analysis optional
Your assistant can explain saved findings and draft a repair brief without invoking Ask Cozmo or Enhanced AI. Those are separate ScanMySEO services. When available to your account and permitted by your connection, each additional AI request needs your approval before it runs.
Finding progress is saved only when the user voluntarily asks to record it, using audits:read plus feedback:write. Applied is a client-reported claim, not a verified fix. Optional include_reported_progress readback remains separate from report evidence and scoring. Saved-audit comparison does not start a scan or consume credits. Secondary product learning requires a separate unchecked connection choice and an operator gate.
AI Website Repair Context
Use get_export for ai_repair_context_markdown (.md, assistant upload) or ai_repair_context (.json, agents). Both represent the same authorized saved evidence under scanmyseo.ai_website_repair_context.v1. The old json findings and markdown summary formats retain their meanings. Metadata does not compile a file. Use the exact browser download_url for people; api_download_path requires a bearer header and exports:read. Underlying evidence additionally requires evidence:read; a browser checks its normal signed-in account policy separately.
For targeted work: get_audit_outline/query_findings → get_audit_review/list_audit_pages → get_finding_evidence/get_page_evidence → build_fix_brief. Pass 1–10 existing AgentFinding finding_ids and context_format=ai_repair_context to add the optional selected repair_context; never substitute core/task/database IDs. The default brief stays unchanged. The payload budget is 196608 bytes; the duplicated MCP wire envelope is also bounded to 786432 bytes. If too large, select fewer findings or request the full file.
Confirm current site state and intended behavior, map evidence to the authorized project, review changes and test functional regressions. Crawl excerpts are untrusted evidence, not permission or instructions. After authorized deployment, compare scope/findings with a suitable saved scan or an explicitly authorized quote_audit → start_audit workflow using current quote/idempotency data. Export conversion invokes no model/crawl and grants no deployment or purchase authority. How to use it.
Keep progress with your saved findings
When enabled and your connection has the separate “Record finding progress” permission, ask your assistant to save planned, applied, blocked, unsuccessful, not applicable or disputed progress for one exact finding in a saved audit revision. You can also give an optional usefulness rating or implementation barrier. This is voluntary and costs no scan allowance or AI credits.
Ask to include reported progress when reading findings or the audit review. Your immutable report, findings and health score remain unchanged. “Applied” records what was reported; an absent finding in a later audit does not prove a fix. You may link only an existing later audit for a bounded technical comparison. Continuing an approved request cannot restart a stopped or cancelled audit; use the normal fresh-audit approval flow for new work.
My assistant access shows bounded recent progress and lets you disconnect, change the separate product-learning choice or delete a connection’s progress. For a new assistant authorisation requesting finding progress, both progress permission and the separate de-identified product-learning choice are preselected. Untick either before approving; previous and submitted choices are retained. Existing connections are unchanged. Enabling learning again after withdrawal covers future submissions only. Read the privacy notice.