How we use apps at WeMachines
There are 29 apps in our workspace, and we built every one of them for ourselves. The first went live on 3 August, and between them they have shipped 212 versions since. We don't sell any of them. They are the tools we work with every day, and each one started as a sentence. This is what they do and how they fit into the rest of the workspace, with our real numbers.
Small tools
Every company collects small tools: a CRM, a planner for social posts, a notes app, a dashboard on top of analytics, something that watches the deploys, a moodboard. Each one is another login, another invite, another bill, and another place where information goes to hide.
We don't buy those anymore - we ask for them. You describe the tool on the Apps page, and WeMachines builds it, hosts it and keeps working on it with you in a thread. 24 of our 29 apps are server apps with their own database and API, so the CRM remembers every deal and a note is still there tomorrow. There is no server to look after and nobody to invite. An app lives in the workspace, so the whole team already has it.
Everyone builds
Nobody here writes a ticket for an internal tool. Whoever needs it asks for it. Our CRM started as a one-line ask. When it didn't match how we actually sell, the person who runs the pipeline pasted the fields and stages they wanted into its thread, and the CRM changed shape within the hour.
Asks are short and read like chat, because that is what they are - "white buttons have white text. pls fix" is a real one. Our designer writes some of them in Polish, and the builder doesn't mind. Every ask stays on the app's thread with who asked and how it went, so anyone can pick up where someone else stopped, and every change is a numbered version you can roll back to.
Since 28 August our threads hold 163 asks. Most of them now run on our own laptops, through the desktop app, on the coding agents we already pay for - mostly Claude Code.
Apps the AI can read
This is what makes apps different from any tool we used before. An app can publish what it holds back into the workspace: one line anyone can read, and the figures behind it. The AI reads both. 26 of our 29 apps do it.
So we rarely open an app just to get an answer. Ask in chat how the pipeline looks, and the answer comes from the CRM. Ask what shipped yesterday, and it comes from the changelog. It works the other way too: a server app describes its own API, so a line like "add Acme to the pipeline" is enough - the AI knows exactly what to send.
Each app has one switch for how much of this the AI gets: always in context, on request, or never. 13 of ours are always in, 9 wait until a question is about them, and 7 stay out. When the first version of our notes app turned out to be invisible to the agents, we said so in its thread. Now every note has a reference, just like tasks and docs, and any agent can read the note you point it at.
One prompt for the brand
One of our smallest apps is also one of the most useful. It's a moodboard. We paste in pictures we like - 23 so far - and one button turns them into a single brand prompt: the mood, the palette, the light, what to avoid. The app publishes that prompt, always in context.
So when anyone asks an agent for a picture, the agent already knows what WeMachines looks like. Nobody writes a brief, nobody pastes a style guide. The picture at the top of this post was drawn from that prompt.
Our press image studio goes a step further. It reads the product's real sidebar, design tokens and screens from our repo, so a mockup shows WeMachines as it looks today, and an agent asked for a press image in chat gets it from the app and posts the picture. It's the app our designer asks the most of, and it has shipped 48 versions since 20 September.
Routines
An app on its own waits for someone to open it. A routine doesn't wait. When an app needs something done on a schedule, the AI building it sets up the routine too.
Every night, a routine wakes our changelog. The app reads what we pushed to the repo that day, writes it up in plain words and publishes the entry. Nobody writes release notes.
Every morning, another one refreshes our analytics app from PostHog, so the AI can answer questions about visitors and signups when nobody has the dashboard open. On Mondays a third reads the same app and tells us what to act on. The press studio re-reads the repo every morning, too.
And every Friday, an AI teammate writes one fresh compliment about our designer's work and posts it to a wall built for exactly that. There are seven on it so far.
Fun
Some apps exist because we like each other. There's a 3D office with a desk for each of us and for seven of our AI teammates, a coffee bar, and a button that gathers everyone, AI included, for a group photo. The host at the front desk tells you what happened while you were away. There's a multiplayer game, a Minecraft world for the workspace and a quote hall of fame.
Our workout app plots our training against how the work moves, to see whether exercise makes us better at our jobs. No verdict yet.
Still early
Apps are in early access, and now and then it shows. Not every ask lands the first time - the redesign of our analytics dashboard took three. An app can read the workspace but can't write to it yet: it can show you the board, not create a task. A server app takes a few seconds to wake up after a quiet spell. And the apps are for us. We don't run anything our customers depend on with them, and we don't recommend it yet.
By the numbers
- 29 apps, 24 of them with their own database
- 212 versions, 151 of them in the last 30 days
- 163 asks on their threads since 28 August
- 26 apps that publish what they hold to the AI
- 6 that reach a service outside the workspace, from PostHog and Cloudflare to GitHub and ElevenLabs
- 14 pinned to the sidebar, sorted into 7 groups
- 0 servers we look after
In Building WeMachines on WeMachines we put internal tools at 8 to 16 hours a week by hand, plus 3 to host and maintain them, against about an hour with WeMachines. Two months and 29 apps later, that estimate still looks safe - most of these we would never have built at all.
When something is missing, nobody goes shopping for a tool. Someone asks for one, and we're using it the same day.
Conclusion
Apps put our tools in the same place as our chat, tasks and docs. The people who use them build them, the AI reads what they hold, and routines keep them fresh while we sleep. In WeMachines, the tool you are missing is one sentence away, and once it exists, your whole team and every agent can use it.