Relevance AI outage history
We hold 7 Relevance AI incidents from Relevance AI's status page, the newest from Sep 9, 2026. 2 of the 7 listed carry Relevance AI's own update timeline. Each one links to a page with the vendor's updates and what our five-minute checks recorded while it was open.
Uptime & history
Tracking since Jun 22, 2026% of our checks that found Relevance AI fully operational — a degraded check counts against it, because a slow or partly-broken service is not a working one. Down and degraded time are counted at our 5-minute check resolution, so both are approximate. Longer windows fill in as data accrues — we never show uptime we haven't measured.
- Customers are unable to save triggers when creating workforcesSep 9, 2026 → Sep 9, 2026 · resolved
- Degraded Claude Sonnet 5 serviceAug 4, 2026 → Aug 4, 2026 · resolved
- [Region US] Modal Python Steps Experiencing Service OutageMay 7, 2026 · ongoing · resolved
- Agent tasks are not being processed for some customers.Apr 15, 2026 · ongoing · resolved
- Some Workforces and Agents using tool based triggers cannot be published or clonedApr 13, 2026 · ongoing · resolved
- Chat and Builder are experiencing extreme slownessApr 8, 2026 · ongoing · resolved
- Degraded performance for some chat interactionsApr 1, 2026 · ongoing · resolved
How Relevance AI fails
Since Jun 27, 2026, Relevance AI's status page has marked 9 Relevance AI components as impaired, across 10,027 of our five-minute readings. Anthropic accounts for the most: 8,303 readings (about 692 hours) on 76 days, 8,303 of them marked as an outage rather than degraded, most recently on Nov 18, 2026. Next is WorkOS, with 1,099 readings on 27 days. We hold 7 Relevance AI incidents from Relevance AI's status page, the earliest from Apr 1, 2026.
| Component | Outage | Degraded | Maint. | Days | Last |
|---|---|---|---|---|---|
| Anthropic | 8303 | — | — | 76 | Nov 18, 2026 |
| WorkOS | 1090 | 9 | — | 27 | Nov 18, 2026 |
| Orb Billing | 441 | — | — | 17 | Nov 14, 2026 |
| Agent Builder | — | 70 | — | 4 | Sep 9, 2026 |
| Modal | 66 | — | — | 14 | Nov 18, 2026 |
| Pipedream | 28 | — | — | 3 | Oct 5, 2026 |
| Chat | — | 11 | — | 1 | Aug 4, 2026 |
| OpenAI | 5 | — | — | 2 | Oct 20, 2026 |
Incidents by month: Apr 2026: 4 · May 2026: 1 · Aug 2026: 1 · Sep 2026: 1
Counts are five-minute readings of Relevance AI's own component statuses, recorded only when a component is not operational. Hours are readings times five minutes, so a gap in our recording would undercount, never overcount.
Every recorded incident
September 2026 · 1
- Sep 9, 2026Customers are unable to save triggers when creating workforcesresolved54 min3 updates
August 2026 · 1
- Aug 4, 2026Degraded Claude Sonnet 5 serviceresolved54 min2 updates
May 2026 · 1
- May 7, 2026[Region US] Modal Python Steps Experiencing Service Outageresolvedend not published
April 2026 · 4
- Apr 15, 2026Agent tasks are not being processed for some customers.resolvedend not published
- Apr 13, 2026Some Workforces and Agents using tool based triggers cannot be published or clonedresolvedend not published
- Apr 8, 2026Chat and Builder are experiencing extreme slownessresolvedend not published
- Apr 1, 2026Degraded performance for some chat interactionsresolvedend not published
Incidents and their updates are Relevance AI's own words from its status page, recorded every five minutes; we never add an inferred cause. AIDownCheck is independent and not affiliated with Relevance AI.