Provider redundancy added; auto-cleanup rollback in testing

An Update on Wispr Flow Reliability

Flow has been less reliable than it should be over the past few weeks. Here's a transparent look at what went wrong and what's being done about it.

Outages: The issues stemmed from infrastructure changes made while scaling up capacity. The rollout moved faster than planned, and failover didn't hold up the way it should have. Redundancy is now in place so a single provider outage doesn't take Flow down, along with health monitoring and an on-call rotation to catch issues faster. This is the top priority across engineering and infrastructure right now.

Accuracy: The introduction of the auto-cleanup setting may have affected other settings as well. A rollback is actively being tested. An upgraded speech recognition model is also in progress, targeting both accuracy and latency. All users run on the same model, so any improvements reach everyone at once.

Longer term, better internal tooling is being built so issues like these get caught before they reach you.