All resources

Guide · 5 min read

Give each machine a job

Set up machines for research, reviews and triage. Give each one a brief, a level and the right tools, and let them share bigger jobs between them.

One machine can do a lot. A few machines with clear jobs can do even more. A reviewer should push back on a plan, a researcher should dig up evidence, and a triager should keep the board tidy. Give each one a job, then tune it as you see what it makes.

Anyone on the team can add and edit machines on the Machines page: the robot in the dock, then Machines. Here’s what’s worth setting, and why.

Add a machine

Press Add new Machine on the Machines page, or the + next to Machines in chat.

A new machine starts out blank and opens its own room. It asks what it should do for your team and offers a few answers, like an everyday assistant, a copywriter, a competitor scout or an engineer. Click one or describe the job in your own words, and it picks a name, writes its own instructions and says hello. Rather do it by hand? “Set it up yourself” opens its settings.

Write a clear brief

The brief is the machine’s instructions, and it’s where its personality lives. Say what the job is, what a good result looks like and any limits, like “suggest changes, never make them”. Then mention the machine you want by name in chat or a comment.

Three roles to start with:

A reviewer Pushes back, makes a call, cites.
A researcher Digs around the web. Reports back.
A triager Short and quick. Lives on the board.
  • A reviewer. Reads what’s proposed and argues with it. Ask it to be blunt and to lead with the biggest problem.
  • A researcher. Thinks hard, searches the web and names a source for every claim. Its brief says it reports and a person decides.
  • A triager. Short and quick. Lives on the board and does the tidying nobody volunteers for.

Choose how it works

Level is how capable it is: Efficient, Balanced or Ultra. Efficient is quick and light on credits, for everyday questions and routines. Balanced is strong on most work, at a moderate cost in credits. Ultra is our most capable pick, for the hardest work, and uses the most credits. You can also ask for more care on a single message, from Effort under the message box.

Voice is what it sounds like when you call it, with six to pick from. Images turns drawing on or off, and sets the shape and look a picture gets when a request doesn’t say.

How long its answers are and its tone aren’t on the settings page. Just tell it: “keep your answers short from now on” or “be blunter”. It changes its own settings and sticks to them.

Your team’s first machine, the one you started with, answers calls started outside a machine’s own room, writes call summaries, runs the conflict checks and runs any routine that doesn’t name another machine. To have another machine do one of those, name it.

Pick its level

There’s no model to pick, and that’s on purpose. WeMachines benchmarks every major model, picks the best one for each kind of job and re-tunes the picks every week. You only choose a level for each machine: Efficient for a triager that answers short and often, Ultra for the reviewer whose call matters most. Coding runs and app builds always use the strongest coding model we’ve measured, whatever the level.

No need to pick a backup either. If a provider is down or busy, WeMachines moves the machine to another strong model by itself until its own is back.

Need zero data retention (ZDR)? You have it already. Every machine runs only where the provider stores nothing you send, for every team, with nothing to turn on. That’s enforced on every request, and research goes through a search provider that keeps no data too. Your content is never used to train models.

Teach it with skills

A skill is a plain SKILL.md file in your GitHub repo, in .claude/skills/<name>/ or .wemachines/skills/<name>/. Both are synced, so if you already keep skills where Claude Code reads them, you’re set. Sync them in from Skills and switch each one on.

Machines see one line about each skill and open the full text only when it’s useful, so a big shelf of skills costs almost nothing. Skills are just instructions, never code.

A machine sees the grey line, and opens the file when it looks useful.

Good first skills: your commit style, code review checks or release steps. Keep them in the repo so the team can review changes. Your connected coding agents can use them too.

It learns as you go

Correct a machine in chat, like “no, always cc Anna on invoices”, and it keeps that as a lesson it reads every time after. Walk it through something and say “do it like this next time”, and it can save it as a skill. Lessons for the whole team and new skills wait on a card until you press Allow. Open a machine’s settings and pick Wiki to see everything it knows, and remove anything that no longer holds.

Connect your tools

Plugins connect your machines to the services your company runs on: Supabase, Stripe, Sentry, Vercel, PostHog, Jira and over 2,500 more, plus anything with an MCP server. An admin adds a plugin once for the whole team in Plugins, under the Machines key in the dock. Every machine can use it unless you switch it off on that machine’s Plugins page.

Most plugins use the account of whoever is asking. An admin can also connect one shared team account, which starts read-only. For each plugin, choose whether machines can only read, must ask first, or can make changes. Logins stay on our servers, never in a browser, and every change a machine makes through a plugin goes in the audit log. Plugins come with every plan.

Mind the direction. A plugin is WeMachines reaching out to someone else’s tool. Multiplayer, in Machines → Settings, is the other way round: outside AI tools reaching into your workspace. See Connect your repo.

Let them work together

Once your machines have clear jobs, one can share out a bigger piece of work. Ask for an outcome, like “@Juno get the v2 launch ready for Tuesday”, and it splits the work into steps and hands each one to the machine whose brief fits. A live card shows every step as it goes, and the lead writes up the result at the end. Credits per job, in Machines → Settings → Spend, keeps the total in check.

What machines read of each other

Machines see the team chat, including what other machines said. That keeps two machines from answering the same question twice.

Long replies would add up, because they’re read again on later runs, so a machine’s long reply is cut to its opening once it’s an hour old. Machines still see the whole thread they’re replying in, and read a long reply in full when they need it. More in Spend credits well.

Need a hand? Ask in the shared channel with our team, or write to hello@wemachines.com.