Claude Code je već instaliran

AI agenti u oblaku koji rade 24/7

Iznajmite računar na kome je Claude Code već instaliran: vaši agenti obrađuju poštu, odgovaraju u Telegramu i upravljaju pregledačem dok vi spavate.

Izaberite plan Pogledajte studije slučaja

Vaš laptop ostaje po strani.

Prosledite fakturu sa telefona i tabela vam stiže u Telegram. Agent ima sopstveno poštansko sanduče i bota, na računaru koji niko nikad ne zatvara.

Radi sam, čak i dok spavate.

Zakažite posao za šest, a rezultat pročitajte u devet. Agent je na računaru na kome nema ničeg osim posla, pa može da radi bez pitanja na svakom koraku, a ograničenje broja pokretanja sprečava da petlja preko noći potroši vaš budžet.

Pomažemo u prvim koracima i sa najboljim praksama.

Pokrećite agente sami na Mini računaru ili to prepustite nama: Start, Basic i PRO uključuju jednog, dva ili tri upravljana agenta. U oba slučaja root je vaš.

Poručite udaljeni računar

Tipičan udaljeni računar

Linux (Ubuntu LTS), obično u evropskom data centru. Basic i PRO: sopstveni server, najmanje 4 GB, 40 GB SSD, sopstvena IPv4 adresa. Start: Mini, 1 GB, 10 GB, deljeni host, bez pregledača.

Vi ste jedini korisnik tog računara i root je vaš, pa ga možete podesiti kako god vaš posao zahteva. Postoje dva načina pristupa: terminal u pregledaču, unutar kontrolne table, bez ikakve instalacije kod vas, ili običan SSH kada dodate svoj ključ.

Izaberite plan

Najnovije studije slučaja

Video 26:28

Claude apologised and promised never to do it again? Do not trust promises, set up hooks

Claude apologised and promised never to do it again, and a couple of days later it all happened again. A promise lives in one conversation, and Anthropic's guide calls the rules in CLAUDE.md advice. A hook is a check Claude cannot skip: Claude Code runs it itself, before an action, after it or at the end of an answer. Where a hook is needed (deleting data, emails, putting code online, spending money), where it only slows the agents down, and the author's five working hooks: dangerous commands, emails in his name, the task log, the skeptic and a sound. The recording of the masterclass and the working kit of files that goes with it.

Slava Sazhin 30. septembar 2026
Video 28:22

Giving your child the right access to top AI. Building a custom web app

A child needs their own helper, not a shared chat under your login. A web app on your server goes on the phone's home screen, and Claude answers on a separate subscription. The character says what the helper is like, not what it must not do: it does not shut down a topic beyond the child's age but answers briefly and calmly, sends the child to adults about health, medicines and money, and on anything dangerous puts a mark the child cannot see, and you get a message. You read the chats, and the child knows it. The recording opens with the new Opus 5.5: which effort level for which role. The recording of the masterclass and the working kit of files that goes with it.

Slava Sazhin 23. septembar 2026
Video 26:40

Which model for which task, so the bill does not ruin you? Do not ask Fable 5 for a casserole recipe

There are two knobs, and usually only one gets turned: the model is the ceiling of ability, and the effort level is how thoroughly it works. Slava's own blind test and the independent FrontierCode measurement say the same thing: the line of the model matters more than the effort inside it, and max costs four times what medium does without adding accuracy. Where the model and effort pair is set, and why it belongs in one file. And a fallback for helper agents when an expensive model runs out of limit: a hook catches the refusal and moves the role to a fallback model. The recording of the masterclass and the working kit of files that goes with it.

Slava Sazhin 17. septembar 2026
Sve studije slučaja

Sa bloga

Svi članci

Kontaktirajte tim Combobulating