Episode 0 of our build-in-the-open series: what actually happens when you put AI agents to work running your business.
Last week I went looking for why we had picked a particular vendor back in March. I knew we had debated it. I knew there was a good reason. I scrolled Slack for twenty minutes and found three-quarters of the thread, none of the conclusion, and a link that had gone dead. Eventually I gave up and asked the person I thought made the call. He didn't remember either.
That is the tax nobody puts on the invoice. The studio's real work is visible: code ships, designs go out, clients watch progress arrive. The operations underneath stay invisible until they break. Decisions get made in a thread and evaporate by Friday. The weekly status update quietly eats an afternoon. A client call sneaks up with nobody prepped. None of it is hard. It is just death by a thousand small things nobody owns.
At Crescentic we had two choices: hire someone to own all of that, or build something that could. We built something. Actually, we built a small team of them.
Meet the squad
Three AI teammates live in our Slack now, each with one job.
Pulse watches the projects. Every code change, every build, every quiet week, summarized each morning before anyone logs on. Friday afternoons it posts the week in review. I never ask it to. It just shows up.
Scout does the client prep I always meant to do and never did. It watches our calendars, and shortly before a call a briefing lands in my DMs: who I'm meeting, what changed since last time, what to know walking in.
Memo remembers, so I don't have to. Every decision and every action item, captured with who decided it, when, and where, and searchable in plain English. That vendor question I lost twenty minutes to? Memo would have answered it in one.
They're not chatbots
A chatbot waits for you to ask. These do the work on a schedule, without being asked. The morning summary isn't a reply to a question. It arrives because it's morning. The meeting briefing arrives because the calendar says a meeting is coming, not because someone remembered to prep for it.
That gap, between answering when asked and acting on its own, is the whole thing. You already know what it's like to ask an AI a question. It's a different feeling to have one show up with the answer first.
And because the three of them share one memory, they compound. The decision Memo filed in March becomes the context Scout uses to brief me in June. Pulse's summaries feed the same knowledge base the team searches with /ask. Three teammates, one brain.
What it costs, to the cent
Here's the number most write-ups skip, so I'll put it first. Every time one of these agents does anything, it records what that cost, down to the millionth of a dollar. Not an estimate. A line in a ledger. Every morning the team gets yesterday's AI bill in the ops channel, broken down by agent.
Concretely: a morning project summary runs about half a cent. A full client research briefing, a couple of cents. The whole day in the report above came to seven cents of model time, so call it a few dollars a month in inference. That isn't the total cost of running this. My own time building and steering it is the bigger line item. But it does mean that when someone asks what the AI costs, I can point at a number instead of shrugging.
Where it gets thin
Let me be straight about the seams, because a build log that only shows the wins is just an ad with better production values. These agents are good at the repetitive, well-shaped jobs: summarize this, research that, file that decision. They aren't running the studio while I sleep. When a task is ambiguous, Pulse will cheerfully summarize the wrong thing with total confidence, and I have to catch it. I steer more than the tidy version of this story suggests. The reliability we do have came from deliberate, boring engineering, not from the model being magic, and a whole later post goes straight at that, because it's the part that decides whether this is useful or a toy.
Why we built instead of bought
The most-Googled version of this is "which AI is best for running a business?" I think that's the wrong question. The better one is whose business the tool was built for.
We didn't buy this off a shelf, and we didn't assemble it from an agent-framework kit. It's one small custom system, deliberately small, small enough that we understand every moving part. Off-the-shelf tools automate the average business. The whole value of operations is that yours isn't average: your clients, your naming conventions, your definition of "urgent," your Friday rituals. A system shaped around your specifics is the difference between a tool your team tolerates and a teammate your team leans on.
This isn't a software-studio thing
Strip the labels off what we built and it's a pattern almost any operations-heavy business can run:
- A clinic could have a Pulse that posts the morning's schedule, the gaps, and the prior-auths to chase before the front desk sits down.
- A logistics team could have a Scout that briefs a driver on the route, the customer, and the dock quirks before dispatch.
- A law firm could have a Memo that never loses a client decision or a filing deadline, with the source attached.
Same three moves, watch, prepare, remember. A different industry.
What's next
Over the next few posts we'll open the hood on each teammate: what it does, what it actually costs to run, and how we kept it reliable and safe, which is the part everyone worries about, rightly. Not a sales pitch. A build log, with the receipts attached.
If you saw your own business somewhere in the last few paragraphs, that wasn't an accident. That was the whole reason I wrote this down.
We're building this in the open. Follow along for the next teammate, and if you're already picturing it in your own shop, say hi. Get in touch
Technical readers: the engineering deep-dive, the custom runtime, the routing, the shared memory layer, the cost accounting, lives in the appendix.