Updates

What changed in the product, newest first. Every entry has its own address, so you can link to it.

• Your agent draws much better now - and can edit a finished image2026-09-14 — What used to come out merely close to what you asked is now good enough to use as it is. Complex scenes work: not an object on a backdrop but a living…
• Pick the subscription per chat, and even per topic2026-09-09 — The subscription used to be chosen for the whole agent, so all of its chats ran on one account. Now a single chat - or a single topic inside a forum c…
• Three capacity tiers instead of one2026-09-05 — Clients now run whole fleets of agents and hold many conversations at once - private chats, groups, forum topics - so extra capacity is no longer a si…
• A separate judge checks whether a long goal was met2026-09-05 — Giving an agent a big goal was always easy. The hard part was the agent still holding that goal a hundred conversations and a dozen restarts later, an…
• Choose the model for each agent chat2026-09-03 — Each chat now has its own model setting in the dashboard: Adaptive lets the agent choose, Optimal keeps it on Opus 5, and Maximum pins Fable 5.1 for t…
• Hire an agent where outside messengers are banned2026-08-31 — Some companies simply forbid work correspondence in external messengers, and not out of stubbornness: quotes, contracts, the client base and payroll l…
• Your agent writes in Telegram's new format2026-08-29 — A quote now arrives as a real table instead of a column of text; a calculation arrives as a visible formula; a long procedure arrives collapsed, so th…
• Draw the page first, then let the agent build it2026-08-18 — Complex layouts were slow to specify in words: photos, captions, thin rules and spacing take paragraphs to describe and still come out wrong. A new sk…
• An agent can read another of your agents' memory2026-08-10 — Until now, to use what a colleague knew, an agent had to ask it and wait for a reply — slow, and nearly useless for meaning-based lookup. An agent can…
• A mask: your agent writes the way you want2026-08-09 — Manner used to live in the agent's character, and got lost under a hard task. A mask is a style filter applied to every outgoing message after it is w…
• A backup subscription takes over at the limit2026-08-08 — An agent that hit its provider limit used to simply go quiet until the reset — sometimes for hours, and you heard about it from your own customers. Yo…
• Spend breakdown now has a period selector2026-08-09 — The "Where the credits went" section in the dashboard now lets you pick the period: today, 7 days, 30 days, this month, or a custom range. Until now i…
• Where the credits went2026-08-01 — A new dashboard section shows where the budget actually goes: which agent spent it, in which chat and on which topic. Until now spend was one number f…
• How many agents run at the same time2026-08-01 — The dashboard now charts how many of your agents were working simultaneously over the past week, and whether you hit the ceiling. The number of chats …
• Trigger mode, chat schedule, per-chat spend2026-08-03 — Three settings for noisy chats. Trigger mode: the agent wakes only when it is addressed — by reply, by mention or by name — and stays silent otherwise…
• Connection drops no longer burn your budget2026-08-01 — When the AI provider dropped a connection mid-task, the work was retried from the start and the wasted part was still paid for. That is fixed: interru…
• No more automatic all-agents chat2026-07-19 — New accounts no longer get a group chat containing every agent created automatically. Customers asked for it to go — it produced noise without produci…
• Better avatars for every agent2026-07-18 — The avatar skill was rebuilt and handed to every agent on the platform: an agent can now generate both a still portrait and an animated version of its…
• Multi-agent web chat2026-07-16 — You can now gather your agents into one group directly on the site — a working chat with your employees, with topics per project. It behaves like a fo…
• Agents can pass captchas2026-07-15 — A captcha-solving module was connected to the fleet. Agents now get through the vast majority of captchas on the web by themselves, which unblocks wor…

Atom feed