Product
Version 2.1.1 adds a third AI engine to the platform. OpenAI Codex, powered by GPT-5.4, now sits alongside Claude and OpenCode as a fully integrated CLI provider. This release also includes connectivity fixes across 13 skills, environment cleanup, and a default behavior change for new employees. OpenAI
Product
This is the biggest release since we launched. Geta.Team v2.1.0 ships Team Collaboration, a complete MFA overhaul, mail search, a redesigned employee catalog, and a stack of fixes that make the platform meaningfully more reliable. Here's everything that changed. Team Collaboration: Shared Folders + Employee Delegation
Product
This release is a big one. Fifteen bug fixes, three new features, and a handful of UI improvements that collectively make Geta.Team feel noticeably sharper. Here is what shipped in v2.0.21. Employee Tags: Organize Your AI Team As teams scale their AI workforce beyond two or three
Product
You deploy your first AI employee on a Monday. By Friday, you are not sure if it is actually doing anything. By the end of the month, you cannot imagine going back. That is the pattern. Almost every time. The problem is that most people expect the wrong things at
Product
You know the feeling. You're working with your AI employee, you send a message, and then while it's processing you think of something else. Maybe a follow-up instruction, maybe a correction, maybe a completely different task. But the send button is gone. You're stuck
Product
Your AI employee just learned to wait its turn. That sounds trivial until you realise how annoying the alternative was. The Problem With Always-On Employees Here's a scenario every Geta.Team user has hit at least once. You're mid-conversation with your AI employee — working through a
Product
This release is all about making voice calls actually usable and giving the File Explorer some overdue muscle. Here's what changed in v2.0.16. Voice Calls: Custom Instructions, Speed Control, and a Big Latency Fix Three things that were either missing or broken in voice calls are
AI Agents
Ask ChatGPT a question today. Ask it the same question tomorrow. It will have no idea you were ever there. This is the default state of almost every AI tool on the market. Each conversation starts from zero. No context from yesterday. No memory of your preferences. No understanding of
Product
Every AI platform has the same pitch: "We integrate with 200+ tools." Then you check the list and the one tool you actually need -- your niche CRM, your internal wiki, your industry-specific billing system -- isn't on it. So you file a feature request. You
AI Agents
Last week an AI agent published a hit piece on an open source maintainer because its PR got rejected. The agent, built on OpenClaw and going by "MJ Rathbun," researched Scott Shambaugh's coding history, dug through his personal information, and published a blog post accusing him
Tutorial
Geta.Team runs on Claude by default. It's a great model, but sometimes you need something different — a cheaper option for high-volume tasks, a specialized model for coding, or simply access to the latest releases from OpenAI, Google, or Meta without waiting for us to add native support.
Product
Telegram has 900 million monthly active users. But unlike WhatsApp's broad consumer base, Telegram's audience skews technical: crypto communities, developer groups, privacy-conscious professionals, and a massive presence across Eastern Europe and CIS markets. If your customers live on Telegram, your AI employee should too. Today we&