Scored by asking 15 questions a buyer of a infrastructure product asks, then grading this site’s own pages: answered, hedged (partial or vague), or silent (no page answers it). How scoring works
15 buyer questions · graded against the site’s own pages
3 of 15 come back answered. 4 get a hedge. 8 meet silence.
74 points sit between chatgpt.com and 100: 12 open questions and 9 missing protocol checks, ordered by estimated payoff.
Point estimates are per fix under scoring v2. They are not additive to a promised total.
01integration · importance highGoes silent+7 content pts est.
What is the exact URL and JSON schema for programmatically fetching the current system status?
What the pages say
No page on the site addresses this.
The fix
Add a developer/API section to the status page (or link from it) that documents the exact programmatic endpoint URL and JSON schema for fetching current system status.
confidence high · grounding synthesized · weight 0.00 · Absent
02getting-started · importance highGoes silent+7 content pts est.
How do I sign up for email alerts whenever a new incident is posted?
What the pages say
No page on the site addresses this.
The fix
Add a 'Subscribe to Alerts' section or footer on the status page that explains how to sign up for email, SMS, or webhook notifications when new incidents are posted.
confidence high · grounding synthesized · weight 0.00 · Absent
03operations · importance mediumGoes silent+7 content pts est.
What is the typical delay between an outage beginning and the first public update appearing on the status page?
What the pages say
No page on the site addresses this.
The fix
Publish an incident communications policy on the status page or trust center that specifies the target delay between outage onset and the first public update.
confidence high · grounding synthesized · weight 0.00 · Absent
05limits · importance lowGoes silent+7 content pts est.
Are there rate limits or caching headers I need to respect when polling the public status page JSON endpoint from my monitoring system?
What the pages say
No page on the site addresses this.
The fix
Add developer documentation to the status site (or a linked FAQ) that specifies rate limits, caching headers, and recommended polling intervals for the public status JSON endpoint.
confidence high · grounding synthesized · weight 0.00 · Absent
06operations · importance lowGoes silent+7 content pts est.
Can I filter the incident history to show only events that affected the developer API and exclude ChatGPT consumer issues?
What the pages say
No page on the site addresses this.
The fix
Document incident-history filtering capabilities on the status page or in a help article, explicitly stating whether users can filter historical incidents by affected component (developer APIs vs ChatGPT consumer).
confidence high · grounding world-knowledge · weight 0.00 · Absent
07integration · importance lowGoes silent+7 content pts est.
Does the status page support webhook notifications, and what fields are included in the incident-created JSON payload?
What the pages say
No page on the site addresses this.
The fix
Add a documentation page or section on the status site describing notification options such as webhooks and include the incident-created JSON payload schema.
confidence high · grounding world-knowledge · weight 0.00 · Absent
08operations · importance lowGoes silent+7 content pts est.
What timezone are incident timestamps displayed in, and can I switch the view to UTC or my local time?
What the pages say
No page on the site addresses this.
The fix
Add a note on the status page or in an incident-details FAQ specifying the default timezone for timestamps and whether users can switch to UTC or their local time.
confidence high · grounding synthesized · weight 0.00 · Vague
10What exact latency or error-rate thresholds trigger a "Degraded Performance" status instead of "Operational" for the API?technicalHedges+2 pts est.+−
What exact latency or error-rate thresholds trigger a "Degraded Performance" status instead of "Operational" for the API?
What the pages say
The retrieved status-page chunks list historical API uptime figures (e.g., the APIs component shows 99.93% uptime for Jun–Sep 2026) but do not specify the exact latency or error-rate thresholds that trigger a 'Degraded Performance' status instead of 'Operational'.
The fix
Publish the specific latency and error-rate thresholds that trigger 'Degraded Performance' on the status page or in linked SLA/operations documentation.
confidence high · grounding synthesized · weight 0.70 · Vague
11Where do I find the complete archive of resolved incidents and scheduled maintenance events?operationsHedges+2 pts est.+−
Where do I find the complete archive of resolved incidents and scheduled maintenance events?
What the pages say
The chunks identify https://status.chatgpt.com/ as the system status page and contain links to individual incidents at paths like /incidents/01M34TAFM9WBGEBE3G1GBH4SE8, but they do not explicitly state where the complete archive of resolved incidents or scheduled maintenance events is located.
The fix
Add a visible 'Incident History' or 'Scheduled Maintenance' link or section on the status page with a stable URL that crawlers can index.
confidence medium · grounding synthesized · weight 0.65 · Vague
12If the primary status page is unreachable during a major outage, is there an independent mirror domain or alternate endpoint I can check?operationsHedges+2 pts est.+−
If the primary status page is unreachable during a major outage, is there an independent mirror domain or alternate endpoint I can check?
What the pages say
The site references a status page at status.openai.com and hosts status information on status.chatgpt.com, but the chunks do not state whether either is an independent mirror domain or alternate endpoint to use if the primary status page is unreachable during a major outage.
The fix
Document whether an independent mirror domain or alternate endpoint exists for checking service status when the primary status page is unreachable.
confidence high · grounding synthesized · weight 0.70 · Vague
What the pages already answer cleanly
3 of 15. Answered with enough specificity for a buyer to act on. This is the bar the queue above is chasing.
technicalAnswered
Which specific services or components are actively monitored on this status page?
What the pages say
The status page actively monitors the following API components: Responses, Chat Completions, Login, Batch, Search, Images, Agent, Fine-tuning, Embeddings, ChatGPT, Deep Research, and ChatGPT Work. The retrieved chunks also reference totals of 12 and 15 components, indicating the page tracks a dozen or more distinct services.
confidence high · grounding world-knowledge · weight 0.60 · Answered
operationsAnswered
How do I check the real-time operational status of the ChatGPT web interface right now?
What the pages say
Visit https://status.chatgpt.com/ and view the ChatGPT section under System status. The page displays operational metrics such as uptime percentages (e.g., 100%, 99.96%) and component counts for ChatGPT.
confidence high · grounding stated · weight 1.00 · Answered
technicalAnswered
Does the status page report API issues separately by geographic region, or are all regions aggregated into a single status?
What the pages say
The status page does not report API issues separately by geographic region. Instead, it breaks status down by API product or function—such as Batch, Images, Codex, Connectors/Apps, Sites, Agent, Deep Research, CLI, Image Generation, Compliance API, Fine-tuning, and Conversations—with individual uptime percentages for each. Geographic regions appear to be aggregated within each API-specific component rather than shown separately.
confidence medium · grounding synthesized · weight 0.90 · Answered
Protocol plumbing · 18/1002 of 11 checks pass · each fix +9 protocol pts est.
The other half of the score: 11 checks for the files and headers agents look for. The 9 below are installs, not judgment calls, and most are an afternoon. Expand any for the snippet and the standard it follows. They sit after the queue because none of them changes what your pages say.
Sitedex already serves chatgpt.com as an MCP endpoint. Ask chatgpt.com anything an AI agent might ask, and see what its index returns. (To score your own site, use the form below.)
Snippets & configs
For developers and the engineer-on-call: copy these into your tools or your site.
Files from this audit
Built from this crawl. Download or copy each, then install it at the path noted.
llms.txt
Built from this crawl. Install at /llms.txt so agents start here.
organization.json
Organization JSON-LD, pre-filled from this crawl. Wrap in a ld+json script.
server-card.json
MCP server card built from this crawl. Host at /.well-known/mcp/server-card.json.
webmcp.json
WebMCP discovery manifest built from this crawl. Host at /.well-known/webmcp.json.
MCP endpoint
https://mcp.sitedex.dev/s/chatgpt-com/mcp
The URL anyone's agent points at. Read-only; safe to share.
Claude Code
claude mcp add chatgpt --transport http https://mcp.sitedex.dev/s/chatgpt-com/mcp
Drop in <head>. In browsers with WebMCP, this script registers your site's tools with navigator.modelContext.registerTool().
2 · Discovery manifest
{
"schema_version": "2026-04",
"name": "openai",
"description": "It is a site that provides status information on outages. WebMCP tools served by Sitedex.",
"homepage": "https://chatgpt.com",
"documentation": "https://app.sitedex.dev/sites/chatgpt.com",
"source": "navigator.modelContext",
"tools": [
{
"name": "search_site_content",
"description": "Ask about this site in plain language and get the most relevant passages from its pages, each with the source URL and a relevance score. Searches the site's published text, not live inventory or accounts."
},
{
"name": "get_site_info",
"description": "This site's profile: name, description, category, who it is for, page count, and AI Visibility Score. Use it to learn what the site is before you search it."
},
{
"name": "list_site_pages",
"description": "The pages indexed on this site, with title, URL, and path. Use it to see what the site covers, or to find the path to pass to get_site_page."
},
{
"name": "get_site_page",
"description": "The full markdown of one page on this site, by path. Use it after search_site_content points you at a page and you want all of it."
}
]
}
Host alongside the script at /.well-known/webmcp.json. Crawlers that don't render JS rely on this.
Your turn
See which of these questions your site goes silent on.
Free, about 5 minutes. We crawl your site, test it against the buyer questions your category asks, and name what’s vague, contradictory, or missing, plus the files AI agents look for.
ComingEmbeddable grade badgeScore history and deltasOpt-in public board