Daily digest · 2026-11-13 (UTC)

What broke for AI agents on 13 Nov 2026

6 incidents on 3 status pages.

In progress. As of 12:11 UTC, rebuilt every hour; it freezes at 07:00 UTC on 14 Nov 2026.

What broke

Anthropic: “Elevated errors affecting the Microsoft 365 connector”major impact · opened Nov 12 17:52 UTC · identified as of 12:11 UTC · Claude Cowork | claude.aistatus page ↗provider-incidents v118
Cloudflare: “Changes to Cloudflare Workers are not producing Event Subscription events”minor impact · opened Nov 10 01:53 UTC · identified as of 12:11 UTC · Queues | Workersstatus page ↗provider-incidents v111
Cloudflare: “Durable Objects increased error rates in North America”minor impact · opened Nov 12 22:39 UTC · resolved 03:44 UTC (5 h 5 min) · Durable Objectsstatus page ↗provider-incidents v119
Cloudflare: “Replicate Model Registry Unavailable”minor impact · opened Nov 11 04:33 UTC · resolved 01:44 UTC (45 h 11 min) · Replicatestatus page ↗provider-incidents v119
OpenAI: “Elevated errors affecting the Microsoft 365 connector”the feed gives no impact level · first seen by our reader 00:20 UTC (the feed gives no start time) · investigating as of 12:11 UTC · Connectors/Appsstatus page ↗provider-incidents v118
OpenAI: “Sites: Publishing failing”the feed gives no impact level · the feed gives no start time · resolved 05:55 UTC · Sitesstatus page ↗provider-incidents v119

No new major version of the SDKs and tools we follow.

6 other releases on the day

92 round-trips to 23 endpoints agents depend on, 0 failedmodel APIs, registries, chains, the x402 facilitator, status pages and two baselines · measured from macbook-kragent-api-observatory v178
480 of 800 remote MCP endpoints probed answered a handshake (60.0%), on 536 hostsa different slice of the official registry each day, so the share is not compared across days · one attempt per endpoint, an auth challenge counts as an answer · measured from macbook-krmcp-server-liveness v43

Every line comes from one of WITAN's public datasets and links the version its records landed in: provider-incidents, agent-api-observatory, mcp-server-liveness, agent-sdk-releases, agent-tool-releases. They are free to read.
Incidents are what the providers' own status pages published (Anthropic, OpenAI, GitHub, Cloudflare, npm, Vercel), read every 6 hours; scheduled maintenance is left out. Follow a line's status page link for the provider's text.
Round-trips and MCP handshakes are WITAN's own measurements from one vantage point, named on each line. A failure there can be the network between us and the service; it is not a verdict on the service. A latency line needs the day's median at least 2× the previous 7 days' and 250 ms more.
Releases are those of the SDKs and agent tools the datasets follow; pre-releases are left out.
Days are UTC. A day is rebuilt every hour while it runs and frozen 7 hours after it ends. Model prices are not here: that dataset's collector is off. WITAN is a testnet preview run by one developer.