Changelog
v2.3.2 is a patch release with one feature users have been asking for since the day we shipped multi-model support, one bug that was silently embarrassing the agent on inbound phone calls, and two quieter UX cleanups. Switch models in the middle of a conversation, without slash commands
Changelog
v2.3.0 ships with two features that have been at the top of the user wishlist since the very first wave of onboardings, plus the smaller bullet that quietly fixes the most annoying recurring support pattern. The two headlines: a proper Trello-style task board, one per employee, that the
Product Updates
Five releases in three weeks. Here's everything that shipped in Geta.Team from mid-February to today, starting with the most recent. v2.0.11 — March 4, 2026 Claude Auth Infinite Loop Fix (Critical) On instances with active employees, connecting Claude via OAuth was stuck on "Waiting for
AI Employees
Here's a test I run on every AI tool before I trust it with real work: can it do something useful at 3 AM on a Tuesday while I'm asleep? Not "generate a response when prompted." Not "auto-reply with a template." Actually
AI Employees
Everyone asks the same question before hiring an AI employee: "But what can it actually do?" The honest answer is: not much on day one. And that's fine. Because the interesting part isn't what it does on day one. It's what happens
Engineering
You open your laptop, type "handle my inbox," and walk away to make coffee. By the time you're back, 47 emails have been triaged, three meeting invites accepted, a client follow-up drafted, and a summary sitting in your chat. Magic, right? Not really. What happened in
AI Employees
There is a freelancer in London who publishes a blog post every morning, sends 200 personalized cold emails a week, posts to LinkedIn and X daily, responds to customer inquiries within minutes, and delivers weekly analytics reports to her clients. She has no employees. No VA. No agency. Just herself
AI Employees
Chatbots answer questions. AI employees do work. There is a massive difference, and most people have not crossed that line yet. If you have a weekend free and want to see what agentic AI actually looks like in practice, here are 10 things you can set up with an AI
AI Employees
Your AI Employee Just Got 70,000 New Skills. No Training Required. There's always been a gap between what AI can theoretically do and what it actually does when you need it to. Most AI tools ship with a fixed set of capabilities. Need it to handle something
AI Employees
There's a dirty secret in the AI industry that nobody wants to talk about: autonomous AI agents fail most of the time. Not sometimes. Not occasionally. Most of the time. A November 2025 study put AI agents from OpenAI, Google DeepMind, and Anthropic through straightforward workplace tasks. The
AI Employees
Here's a confession: the first AI employee we built tried to do everything. Customer support? Sure. Social media? Why not. Data analysis, email triage, appointment scheduling, content writing—we crammed it all into one agent and called it a day. It was impressive in demos. It was a
AI Employees
It's 3 AM. You're asleep. Your business isn't. That sentence would have sounded like science fiction five years ago. Now it's just Tuesday. The gap between businesses that figured this out and those still "thinking about AI" is widening faster