Changelog
There is a specific kind of bug that erodes trust faster than an outage: the one that fills your screen with alarm when nothing is actually on fire. v2.7.11 kills the worst offender, the "LLM API Error" messages that could flood the chat panel in a
Changelog
Yesterday we told you the built-in vision fallback got sharper. Today it got fast. v2.7.10 swaps the local vision model for Google Gemini, called server-side, and the result is the kind of speed jump you feel immediately: reading an image drops from 13 to 33 seconds down to
Changelog
Long conversations have always had the same quiet tax: finding something you said an hour ago means scrolling, and scrolling, and scrolling. v2.7.9 fixes that with a Prompt Rail, a set of ChatGPT-style markers down the right edge of the chat that let you see the whole shape
Changelog
The little percentage next to the model picker has one job: tell you how full the current conversation is. For a while it was quietly answering a different question, how full the last conversation was. v2.7.8 makes it say what it means, in every situation, and clears out
Changelog
Some releases add features. This one takes three things that looked broken and makes them work the way you always assumed they did. If you have tried to assign a bot to an employee lately, refreshed a busy chat and watched it come back wrong, or raised your context window
Changelog
Every release note about "you can now pick a model" tends to bury the part that actually matters to whoever pays the bill. So let us put it up front: v2.7.5 gives your team the full Claude 5 lineup, adds the brand-new Fable 5 for your
Changelog
There is a particular kind of disappointment that comes from asking an AI to make you a presentation and getting back a wall of plain text pretending to be slides. You wanted something you could actually put in front of a client. You got an outline. This release closes that
Changelog
If you run your AI employee on a public Geta.Team workspace, here is the change you will feel first: a teammate sends an email, and it lands in your chat the moment it arrives. No refresh, no polling delay, no waiting for a sync cycle to catch up. v2.
Changelog
Open your chat after this update and the first thing you notice is quieter. Not fewer features, less noise. The whole conversation now shares one design language, and a single soft glow does the job that a dozen coloured labels used to fight over. v2.7.0 is a release
Changelog
If you have ever been on a phone call with an agent that talked over you, repeated itself, or cut you off mid-sentence, you know exactly how quickly it breaks the illusion that you are talking to a competent colleague. v2.5.0 is largely about closing that gap. It
Changelog
A scheduled task has exactly one job: fire at the right moment, every time. When it does not, you usually find out the hard way, by noticing something that should have happened did not. v2.4.10 is a small, focused release that fixes two scheduling bugs doing precisely that
Changelog
Voice was the theme of this release. If you have your AI employees answering or making phone calls, v2.4.9 makes those calls steadier, gives you real control over how they open, and puts a hard boundary around what a phone agent can remember. There is also a macOS