Outage tracker
Is the internet down?
When many services fail at the same time it is usually not many outages: it is one incident at a layer they share, a CDN, a cloud region, a transit route. We probe 195 services from ten regions on our own schedule, and this page reads all of those measurements together. A provider is named only when at least 5 services that measurably sit behind it are probe-confirmed down at once while the services on other providers stay up. Nothing here comes from user reports, social posts or a vendor's status page, and nothing here changes any service's own verdict.
No shared incidentevaluated moments ago
The internet is not down
None of the 195 services we watch is probe-confirmed down right now.
Who sits behind whom: the measured dependency map
Of the 195 services we track, 195 have a recorded provider signal on their primary endpoint. A service can carry more than one signal (a CDN in front of a cloud region), so the rows overlap. Measured from our own probe responses, daily since Aug 23, 2026, last observation moments ago.
| Provider signal | Kind | Services | Share of catalog |
|---|---|---|---|
| Cloudflare | edge / CDN | 57 of 195 | 29% |
| Amazon CloudFront | edge / CDN | 31 of 195 | 16% |
| Google front end | cloud | 16 of 195 | 8% |
| Fastly | edge / CDN | 15 of 195 | 8% |
| AWS us-east-1 (N. Virginia) | cloud region | 12 of 195 | 6% |
| AWS us-west-2 (Oregon) | cloud region | 7 of 195 | 4% |
| AWS eu-west-1 (Ireland) | cloud region | 3 of 195 | 2% |
| Vercel | edge / CDN | 3 of 195 | 2% |
| AWS (load balancer or S3 front) | cloud | 2 of 195 | 1% |
| Azure Front Door | edge / CDN | 2 of 195 | 1% |
Shared-infrastructure incidents, last 30 days
ClosedCloudflareOct 3, 2026, 10 min
Confidence: inferred, based on 6 of the 57 services behind Cloudflare failing together, but 10 of the 77 control services were also down, closer to the tolerance limit than a clean read. 6 of the 57 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 67 of the 77 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 3, 2026, 1 min
Confidence: inferred, based on 5 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 24 of the 124 control services were also down, closer to the tolerance limit than a clean read. 5 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 100 of the 124 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 3, 2026, 1 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 3, 2026, 2 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 3, 2026, 2 min
Confidence: inferred, based on 6 of the 11 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 11 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 3, 2026, 11 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 125 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 100 of the 125 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 3, 2026, 1 min
Confidence: inferred, based on 5 of the 11 services behind AWS us-east-1 (N. Virginia) failing together, but 22 of the 126 control services were also down, closer to the tolerance limit than a clean read. 5 of the 11 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 104 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAmazon CloudFrontOct 3, 2026, 8 min
Confidence: inferred, based on 6 of the 31 services behind Amazon CloudFront failing together, but 21 of the 105 control services were also down, closer to the tolerance limit than a clean read. 6 of the 31 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 84 of the 105 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareOct 3, 2026, 51 min
Confidence: inferred, based on 6 of the 57 services behind Cloudflare failing together, but 15 of the 79 control services were also down, closer to the tolerance limit than a clean read. 6 of the 57 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 64 of the 79 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareOct 2, 2026, 5 min
Confidence: inferred, based on 5 of the 57 services behind Cloudflare failing together, but 13 of the 81 control services were also down, closer to the tolerance limit than a clean read. 5 of the 57 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 68 of the 81 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareOct 2, 2026, 0 min
Confidence: inferred, based on 5 of the 57 services behind Cloudflare failing together, but 16 of the 80 control services were also down, closer to the tolerance limit than a clean read. 5 of the 57 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 64 of the 80 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 3 min
Confidence: inferred, based on 5 of the 11 services behind AWS us-east-1 (N. Virginia) failing together, but 16 of the 125 control services were also down, closer to the tolerance limit than a clean read. 5 of the 11 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 109 of the 125 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareOct 2, 2026, 2 min
Confidence: inferred, based on 5 of the 57 services behind Cloudflare failing together, but 15 of the 81 control services were also down, closer to the tolerance limit than a clean read. 5 of the 57 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 66 of the 81 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 6 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 17 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 109 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 0 min
Confidence: inferred, based on 5 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 5 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 0 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 1 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 0 min
Confidence: inferred, based on 6 of the 11 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 11 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 1 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 1 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 1 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 1 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 2, 2026, 1 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 4 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 125 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 100 of the 125 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 5 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 5 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 128 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 103 of the 128 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 0 min
Confidence: inferred, based on 6 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 6 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 2 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 125 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 100 of the 125 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 6 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 2 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 0 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 2 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 6 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 0 min
Confidence: inferred, based on 5 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 5 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 6 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 0 min
Confidence: inferred, based on 5 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 5 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 6 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedGoogle front endOct 1, 2026, 0 min
Confidence: inferred, based on 5 of the 16 services behind Google front end failing together, but 24 of the 122 control services were also down, closer to the tolerance limit than a clean read. 5 of the 16 services whose responses we measured behind Google front end were probe-confirmed down together, while 98 of the 122 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 6 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 0 min
Confidence: inferred, based on 5 of the 11 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 5 of the 11 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedGoogle front endOct 1, 2026, 2 min
Confidence: inferred, based on 5 of the 16 services behind Google front end failing together, but 24 of the 121 control services were also down, closer to the tolerance limit than a clean read. 5 of the 16 services whose responses we measured behind Google front end were probe-confirmed down together, while 97 of the 121 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 5 of the 11 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 5 of the 11 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedGoogle front endOct 1, 2026, 0 min
Confidence: inferred, based on 5 of the 16 services behind Google front end failing together, but 24 of the 123 control services were also down, closer to the tolerance limit than a clean read. 5 of the 16 services whose responses we measured behind Google front end were probe-confirmed down together, while 99 of the 123 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 4 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 125 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 100 of the 125 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 5 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 5 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 2 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 6 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 5 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 128 control services were also down, closer to the tolerance limit than a clean read. 5 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 103 of the 128 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 125 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 100 of the 125 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 15 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 125 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 100 of the 125 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 5 min
Confidence: inferred, based on 6 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 125 control services were also down, closer to the tolerance limit than a clean read. 6 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 100 of the 125 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 125 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 100 of the 125 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 6 of the 13 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 125 control services were also down, closer to the tolerance limit than a clean read. 6 of the 13 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 100 of the 125 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 5 of the 14 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 5 of the 14 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 5 of the 11 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 128 control services were also down, closer to the tolerance limit than a clean read. 5 of the 11 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 103 of the 128 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 1 min
Confidence: inferred, based on 5 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 5 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 2 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 3 min
Confidence: inferred, based on 5 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 126 control services were also down, closer to the tolerance limit than a clean read. 5 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 101 of the 126 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedGoogle front endOct 1, 2026, 1 min
Confidence: inferred, based on 5 of the 16 services behind Google front end failing together, but 24 of the 123 control services were also down, closer to the tolerance limit than a clean read. 5 of the 16 services whose responses we measured behind Google front end were probe-confirmed down together, while 99 of the 123 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAWS us-east-1 (N. Virginia)Oct 1, 2026, 20 min
Confidence: inferred, based on 6 of the 12 services behind AWS us-east-1 (N. Virginia) failing together, but 25 of the 127 control services were also down, closer to the tolerance limit than a clean read. 6 of the 12 services whose responses we measured behind AWS us-east-1 (N. Virginia) were probe-confirmed down together, while 102 of the 127 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAmazon CloudFrontOct 1, 2026, 6 min
Confidence: inferred, based on 6 of the 31 services behind Amazon CloudFront failing together, but 21 of the 109 control services were also down, closer to the tolerance limit than a clean read. 6 of the 31 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 88 of the 109 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAmazon CloudFrontOct 1, 2026, 56 min
Confidence: inferred, based on 5 of the 31 services behind Amazon CloudFront failing together, but 19 of the 109 control services were also down, closer to the tolerance limit than a clean read. 5 of the 31 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 90 of the 109 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareOct 1, 2026, 43 min
Confidence: inferred, based on 6 of the 57 services behind Cloudflare failing together, but 16 of the 83 control services were also down, closer to the tolerance limit than a clean read. 6 of the 57 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 67 of the 83 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareSep 30, 2026, 6 min
Confidence: inferred, based on 8 of the 56 services behind Cloudflare failing together, but 13 of the 89 control services were also down, closer to the tolerance limit than a clean read. 8 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 76 of the 89 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAmazon CloudFrontSep 30, 2026, 9 min
Confidence: inferred, based on 8 of the 38 services behind Amazon CloudFront failing together, but 16 of the 107 control services were also down, closer to the tolerance limit than a clean read. 8 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 91 of the 107 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmafronteggshopifytrello
ClosedAmazon CloudFrontSep 30, 2026, 1 min
Confidence: inferred, based on 8 of the 38 services behind Amazon CloudFront failing together, but 20 of the 109 control services were also down, closer to the tolerance limit than a clean read. 8 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 89 of the 109 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmafronteggshopifytrello
ClosedAmazon CloudFrontSep 30, 2026, 0 min
Confidence: inferred, based on 9 of the 38 services behind Amazon CloudFront failing together, but 21 of the 109 control services were also down, closer to the tolerance limit than a clean read. 9 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 88 of the 109 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmafronteggshopifysnowflaketrello
ClosedAmazon CloudFrontSep 30, 2026, 1h 14m
Confidence: inferred, based on 9 of the 39 services behind Amazon CloudFront failing together, but 21 of the 107 control services were also down, closer to the tolerance limit than a clean read. 9 of the 39 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 86 of the 107 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitecrates-iofigmafronteggshopifytrello
ClosedCloudflareSep 30, 2026, 1h 16m
Confidence: inferred, based on 9 of the 56 services behind Cloudflare failing together, but 18 of the 90 control services were also down, closer to the tolerance limit than a clean read. 9 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 72 of the 90 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAmazon CloudFrontSep 27, 2026, 2 min
Confidence: likely, based on 5 of the 38 services behind Amazon CloudFront failing together while only 9 of the 105 control services were also down. 5 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 96 of the 105 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareSep 27, 2026, 10 min
Confidence: inferred, based on 7 of the 56 services behind Cloudflare failing together, but 14 of the 87 control services were also down, closer to the tolerance limit than a clean read. 7 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 73 of the 87 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAmazon CloudFrontSep 27, 2026, 11 min
Confidence: inferred, based on 8 of the 38 services behind Amazon CloudFront failing together, but 14 of the 105 control services were also down, closer to the tolerance limit than a clean read. 8 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 91 of the 105 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmafronteggsnowflaketrello
ClosedCloudflareSep 27, 2026, 2 min
Confidence: inferred, based on 8 of the 56 services behind Cloudflare failing together, but 17 of the 89 control services were also down, closer to the tolerance limit than a clean read. 8 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 72 of the 89 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareSep 27, 2026, 2 min
Confidence: inferred, based on 9 of the 56 services behind Cloudflare failing together, but 17 of the 89 control services were also down, closer to the tolerance limit than a clean read. 9 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 72 of the 89 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareSep 27, 2026, 6 min
Confidence: inferred, based on 9 of the 56 services behind Cloudflare failing together, but 18 of the 90 control services were also down, closer to the tolerance limit than a clean read. 9 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 72 of the 90 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareSep 27, 2026, 48 min
Confidence: inferred, based on 9 of the 56 services behind Cloudflare failing together, but 17 of the 89 control services were also down, closer to the tolerance limit than a clean read. 9 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 72 of the 89 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAmazon CloudFrontSep 27, 2026, 1h 42m
Confidence: inferred, based on 9 of the 38 services behind Amazon CloudFront failing together, but 19 of the 107 control services were also down, closer to the tolerance limit than a clean read. 9 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 88 of the 107 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmafronteggshopifysnowflaketrello
ClosedAmazon CloudFrontSep 26, 2026, 4 min
Confidence: inferred, based on 5 of the 38 services behind Amazon CloudFront failing together, but 16 of the 104 control services were also down, closer to the tolerance limit than a clean read. 5 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 88 of the 104 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareSep 26, 2026, 11 min
Confidence: inferred, based on 10 of the 56 services behind Cloudflare failing together, but 9 of the 86 control services were also down, closer to the tolerance limit than a clean read. 10 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 77 of the 86 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
anthropicdiscorddwollakrakenmonzonew-relicpostmanrenderworkoszoom
ClosedCloudflareSep 26, 2026, 1h 29m
Confidence: inferred, based on 9 of the 56 services behind Cloudflare failing together, but 18 of the 90 control services were also down, closer to the tolerance limit than a clean read. 9 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 72 of the 90 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAmazon CloudFrontSep 26, 2026, 1h 35m
Confidence: inferred, based on 8 of the 38 services behind Amazon CloudFront failing together, but 21 of the 108 control services were also down, closer to the tolerance limit than a clean read. 8 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 87 of the 108 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmashopifysnowflaketrello
ClosedCloudflareSep 25, 2026, 40 min
Confidence: inferred, based on 8 of the 56 services behind Cloudflare failing together, but 10 of the 86 control services were also down, closer to the tolerance limit than a clean read. 8 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 76 of the 86 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAmazon CloudFrontSep 25, 2026, 48 min
Confidence: likely, based on 7 of the 38 services behind Amazon CloudFront failing together while only 8 of the 105 control services were also down. 7 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 97 of the 105 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedAmazon CloudFrontSep 22, 2026, 4 min
Confidence: likely, based on 5 of the 38 services behind Amazon CloudFront failing together while only 5 of the 104 control services were also down. 5 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 99 of the 104 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
ClosedCloudflareSep 22, 2026, 6 min
Confidence: inferred, based on 10 of the 56 services behind Cloudflare failing together, but 11 of the 84 control services were also down, closer to the tolerance limit than a clean read. 10 of the 56 services whose responses we measured behind Cloudflare were probe-confirmed down together, while 73 of the 84 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
discorddwollakrakenmonzonew-relicplivopostmanrenderworkoszoom
ClosedAmazon CloudFrontSep 22, 2026, 16 min
Confidence: likely, based on 9 of the 38 services behind Amazon CloudFront failing together while only 7 of the 103 control services were also down. 9 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 96 of the 103 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
atlassian-jirabitbucketbuildkitefigmafronteggplivoshopifysnowflaketrello
ClosedAmazon CloudFrontSep 22, 2026, 14 min
Confidence: inferred, based on 10 of the 38 services behind Amazon CloudFront failing together, but 21 of the 107 control services were also down, closer to the tolerance limit than a clean read. 10 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 86 of the 107 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmafronteggplivoshopifysnowflaketrello
ClosedAmazon CloudFrontSep 22, 2026, 0 min
Confidence: inferred, based on 9 of the 38 services behind Amazon CloudFront failing together, but 21 of the 107 control services were also down, closer to the tolerance limit than a clean read. 9 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 86 of the 107 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmaplivoshopifysnowflaketrello
ClosedAmazon CloudFrontSep 22, 2026, 0 min
Confidence: inferred, based on 9 of the 38 services behind Amazon CloudFront failing together, but 21 of the 105 control services were also down, closer to the tolerance limit than a clean read. 9 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 84 of the 105 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmafronteggplivoshopifytrello
ClosedAmazon CloudFrontSep 22, 2026, 14 min
Confidence: inferred, based on 10 of the 38 services behind Amazon CloudFront failing together, but 21 of the 106 control services were also down, closer to the tolerance limit than a clean read. 10 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 85 of the 106 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmafronteggjfrogshopifysnowflaketrello
ClosedAmazon CloudFrontSep 22, 2026, 0 min
Confidence: inferred, based on 9 of the 38 services behind Amazon CloudFront failing together, but 21 of the 106 control services were also down, closer to the tolerance limit than a clean read. 9 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 85 of the 106 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmajfrogshopifysnowflaketrello
ClosedAmazon CloudFrontSep 22, 2026, 0 min
Confidence: inferred, based on 9 of the 38 services behind Amazon CloudFront failing together, but 21 of the 106 control services were also down, closer to the tolerance limit than a clean read. 9 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 85 of the 106 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmafronteggjfrogshopifytrello
ClosedAmazon CloudFrontSep 22, 2026, 0 min
Confidence: inferred, based on 9 of the 38 services behind Amazon CloudFront failing together, but 21 of the 105 control services were also down, closer to the tolerance limit than a clean read. 9 of the 38 services whose responses we measured behind Amazon CloudFront were probe-confirmed down together, while 84 of the 105 services on other providers stayed up. Measured correlation from our probes; not a statement from the provider, and no service's own verdict is changed by it.
akamaiatlassian-jirabitbucketbuildkitefigmafronteggshopifysnowflaketrello
How this is measured, and what it cannot tell you
A provider signal is where a service's primary endpoint answered from. Every probe response carries two things we keep: the address our pinned socket actually dialed, and a short fixed set of edge-identifying response headers (cf-ray, x-amz-cf-pop, x-served-by, x-vercel-id, x-azure-ref, server, via). The address is matched against a small table of well-known provider ranges committed in our code (71 prefixes for Cloudflare, Fastly, a few AWS regions and Google, checked against the providers' published lists); the headers are matched only where a header is one that provider alone sets. A match says "this response came from behind X". No match says nothing. We never guess from a vendor name.
A provider incident is declared only when, inside a 15-minute window, at least 5 distinct services sharing one signal are probe-confirmed down (an outage our probes opened, which the database admits from probes alone) AND the control group, the services that carry some other signal, is mostly up: at most 20% of them down, over at least 10 of them. If the control group is failing too, the failure is broader than the provider and nothing is declared. It closes when the rule stops holding.
What it cannot tell you. It is a correlation we measured, not a root cause the provider has confirmed, and it can be wrong in both directions. It misses incidents at providers our prefix excerpt does not cover, incidents that affect fewer than 5 of the services we happen to track, and incidents behind a second layer we cannot see (a service on its own network whose database lives in a failing region). It can over-read a coincidence of unrelated outages behind one very popular provider, which is why the control group and the threshold exist. The dependency map counts only services whose primary endpoint answers from behind a provider; a service that uses a provider for something we do not probe is not on it. A service's own verdict on its own page is never changed by anything here.
Machine-readable: /api/v1/outages/internet (no key), and the is_the_internet_down tool on the keyless MCP server. Each service's JSON answer also carries its own provider signals under infra. Read the tracker methodology for what a single reading means.