Originally published on the BuildWithHermes blog. Vapi logged 18 incidents in 90 days, then raised $50M to fix reliability for Amazon Ring. Here is what that means for the agency running 8 clients on it.
On May 28, 2026, Vapi's status page logged another incident: "Increased Call Failure Rates." That was incident number 18 in the last 90 days, including 5 major outages with a median duration of roughly 101 hours, according to IsDown's status monitoring data. That is the reliability record of a platform that just closed a $50M Series B at a $500M valuation.
This is not an attack on Vapi. Their infrastructure genuinely powers a billion calls and a million developers, the round was led by serious investors, and Amazon Ring evaluated 40-plus vendors before choosing them. That is a real technical achievement. The problem is not whether Vapi's infrastructure is good. The problem is whose SLA the $50M is going to improve, and whether your agency is in that conversation.
Why this matters for AI voice agencies
When your agent fleet goes down, your clients' phones stop getting answered. If you run inbound reception for a dental practice, a law firm, or a home services company, a missed call at 9am costs that client a real appointment. A client paying $1,500 per month is paying about $50 per day, and an inbound agent that goes dark for four hours on a Tuesday morning costs them booked revenue, whether or not you noticed the outage.
The Retell parallel
Retell had its own database outage on May 25, four days before Vapi's incident. Call history, analytics, and the QA dashboard went completely offline, documented in Retell's own community forum. Both dominant infrastructure providers had significant outages in the same week.
This is the structural problem with building your agency on API infrastructure that was not designed for agency operations. Vapi and Retell are excellent voice AI engines. They are not agency operating platforms. When they go down, your whole client fleet goes down with them, because the infrastructure is shared and the fallback layer, if it exists at all, is something you had to build yourself.
Action steps for agencies on Vapi this week
- Check your uptime exposure. Pull the last 90 days of incident history and count how many fell during your clients' business hours. If a major outage hit at 9am in a client's timezone, that client felt it whether or not you did.
- Price one outage in client trust. Add up what a single four-hour business-hours outage costs in missed appointments across your active client base. That is the actual risk number you are carrying.
- Ask whether you have a fallback. If your architecture has no provider-level fallback, a single upstream incident is a single point of failure for your entire book.
The bottom line
Vapi raised $50M to solve enterprise-grade reliability for Fortune 500 clients. Amazon Ring needs that. The agency with 8 clients running 1,200 minutes a month needs something different: a platform designed around their P&L from the start, with infrastructure decisions made for their volume, their clients, and their margins. Not a platform that will get around to their problems after it finishes solving Amazon Ring's.
That is what BuildWithHermes is. One platform, your brand, your margins, from $149/month. No VC round changing whose SLA gets prioritized. Full incident data and sources here: buildwithhermes.com
Sources: IsDown status monitoring, Vapi and Retell status pages and community forums.
Top comments (0)