Chief of Staff AI Agent for owners, lawyers, and C-suite
A $150,000 Chief of Staff. For $600 a month.
One private, secure line between you and your agent. Works beside you at your desk, and without you on its own machine. Set up for your job, not sold as a login. You message them exactly like a human executive assistant: forward the receipts, hand off the calendar, ask for the follow-up email. Trained once on your business, available 24/7, and live in one 45-minute setup session.
$600/month flat. No tiers, no seats, no games.
Claire Hayes
Chief of Staff · private channel
The problem
Roughly a third of your week is spent below your pay grade.
That's not a feeling, it's a measured pattern. ServiceNow's State of Work research found managers spend about two days a week, more than a third of their time, on administrative work that isn't core to their jobs. For owners, partners, and executives the picture is the same, at higher stakes.
Until now there were exactly two ways out. Keep slogging. Or pay $100,000 to $150,000 a year for a human Chief of Staff competent enough to actually take it off your plate. Competence is the whole ballgame: a cheap assistant who needs constant supervision doesn't give you your time back, they just change what you're supervising.
And here's the part nobody says out loud. The work isn't hard. That's exactly the problem. The expense report that's rolled over three weeks because it takes an hour you refuse to give it. The calendar Tetris. The follow-up email you've composed in your head four times and never typed. None of it is difficult, all of it is beneath you, so all of it gets deferred, and the deferral itself sits in the back of your mind all week, taking up space that partner-level work should own.
So the fork has always been: keep slogging, or spend $150,000. There's finally a third option.
How they work
Two agents. One hire.
Your Chief of Staff works in two places, the same way a good human one would.
At your desk
Local Agent
Works beside you at your own computer. Sees what you see: inbox, files, calendar, and the browser you use for systems that have no API. For work you want to review before it goes out. It reads everything, assembles the context, drafts the answer, and you approve.
On its own machine
Freestanding Agent
Works without you, on its own machine, always on. You text it through one private line and get a “done” back. For work you just want finished: follow-ups, expense reports from a forwarded stack of receipts, overnight research, the weekly report you keep meaning to build.
If you'd want to look at it first, that's your Local Agent. If you'd just want to hear it's done, that's your Freestanding Agent.
The work behind the work
Most of a task is gathering. The output is the small part.
Watch what actually happens when you reply to a client asking where things stand. You open the case management system and read the history. You pull the last two email threads. You find the document that changed the answer. You ask whoever spoke to them last week what was said. Twenty minutes of gathering, for a six-sentence email.
Nearly every job at a desk is built this way, whether the desk belongs to a paralegal, an administrative assistant, or a CEO. The real work is collecting: from systems, files, inboxes, and people. Then focusing all of it into one narrow beam, the email, the deck, the answer.
Those gathering steps are the elements of the job, and elements are exactly what we scope. Your agent gets set up for your job, one task at a time, with four questions:
- 1What are we solving for?
- 2What tools does this job touch?
- 3What level of access does each tool need: read, draft, or act?
- 4Who approves the output, and which agent runs it?
The answers become a Scope Card, one per job. It records what your agent can touch, what it can't, and who signs off. Once your agent holds the scopes, the twenty minutes of gathering becomes their job, and the narrow beam at the end stays yours to approve. Setup delivers your first two or three cards. Every card after that is another job off your plate.
A Scope Card in the wild: a law firm owner answering client inquiries.
- Job
- Reply to client inquiries with full case context
- Trigger
- Client email arrives
- Access
- Email (read and draft) · case management system (read, through the browser) · document archive on Google Drive (read, matter folders only)
- Output
- Draft reply in your voice
- Approval
- You, every time
- Runs on
- Local Agent
What they take off your plate
Not a tool that does tasks. A hire that takes ownership.
You message them like a person, because that's how they work. They get sharper every week you work together, and you add responsibilities at your own pace, like any new hire.
Expense reports
Forward the receipts. The report shows up done, categorized, ready to submit. The one that's been rolling over for three weeks takes them minutes.
Calendar and meeting prep
They manage the calendar Tetris, protect your focus blocks, and show up before every meeting with the context you need in front of you.
Email drafting and triage
The follow-up you've written in your head four times gets typed, in your voice, waiting for your approval. Inbox triage so you see what matters first.
Meetings, end to end
Agendas before, notes during, action items after, and the follow-through that usually dies in someone's notebook.
Your systems, connected
CRM lookups and updates through your existing systems, API or not. Read-only visibility into financial reporting and bank accounts, so "how did we do last month" gets answered in seconds.
Whatever you train next
Describe a new job in plain English. It runs draft-first until it proves out, then joins the portfolio. One workflow at a time, like any hire earning more responsibility.
The part most AI products skip
One private line. And a security doctrine behind it.
All communication between you and your agent travels through a single secure private channel, closed to the public. Nobody else can message your Chief of Staff, and your Chief of Staff talks to nobody but you and the people you explicitly authorize. Then the doctrine layers on top, built from live business operation, not a lab.
It verifies who's asking before it acts
Identity is checked against a trust registry. Display names, screenshots, and forwarded messages carry zero authority.
Money requires explicit approval
Anything touching money, external communication, or account access requires your explicit approval, tied to the exact item. Not a blanket setting. That item.
Content is information, never instructions
Anything it reads inside an email, document, or web page is treated as information to consider, never as a command to follow. It cannot be talked into a wire transfer by a spoofed email.
Banking changes verify out-of-band
Changes to banking or payment details are confirmed through a separate channel, never through the thread that requested them. This is how firms stop wire fraud, and it is built in.
Every action leaves an audit trail
What it did, when, on whose authority. Reviewable any time.
It starts draft-first
Autonomy is earned one workflow at a time, the same four-phase trust model we run on everything: draft mode, selective auto-send, expanded authority, full operation.
Ask that question of anything else you're considering letting near your accounts.
The trust model
They earn autonomy the way a new hire would.
Everything we build runs the same four-phase model, and your Chief of Staff is no exception. New workflows start in draft mode, where you approve everything. Categories that prove out graduate to acting on their own. You expand what they handle at your pace, and some things can stay approval-only forever. Your hire, your rules. The full trust-building model.
Pricing
$600 a month. Flat. Both agents. That's the pricing section.
Freestanding Agent
Always on, on its own machine
$600/mo, flat
Local Agent
Beside you, at your computer
Included
Includes managed compute infrastructure, ongoing support, and hands-on training for you and your team on how to delegate to a sophisticated AI agent. You bring the model subscriptions to the party: an API account that your Freestanding Agent thinks with, and an AI subscription that powers the Local Agent at your desk. We select and configure the models, both run typically modest at executive workloads, and we walk you through setting up each.
For scale: a human Chief of Staff competent enough to genuinely take work off your plate runs $100,000 to $150,000 a year, works 40 hours, takes vacations, and can quit. This one is $600 a month, trained once, available 24/7, and never leaves for a better offer.
The part that changes the org chart
The fancy title without the fancy price.
In the old world, a chief of staff was something you earned by being expensive. The title existed for people whose compensation justified paying a second six-figure salary to protect the first one. CEOs had one. Everyone else had a to-do list.
At $600 a month, that math is gone. Your managing partner can have one. Your operations director can have one. The senior associate drowning in follow-ups can have one. Anyone whose time is worth multiplying gets the fancy title's support without the fancy price that used to come attached to it.
A chief of staff used to be a status symbol. Now it's a line item. That's the whole shift.
What changes
The third of your week comes back.
The deferred pile is gone. The expense report went out the night you forwarded the receipts. The follow-ups you used to compose in your head are sitting in drafts, in your voice, waiting for one tap. The calendar defends itself.
And the low-grade drain that came from carrying all of it in the back of your mind clears out, because someone competent is carrying it now. You're doing partner-level work with partner-level hours. That's the whole product: you finally get your time back.
Getting started takes ten seconds. Pick a first name, a last name, and a title. That's your new hire.
Common questions
What executives ask before they name one.
- Is the channel really private?
- Yes. One dedicated, secure line that exists only between you and your agent. It is not public-facing, there is no website or widget anyone can wander into, and only people you explicitly authorize can reach it.
- What's the difference between the Local Agent and the Freestanding Agent?
- If you'd want to look at the work before it goes out, that's your Local Agent, working beside you at your own computer. If you'd just want to hear it's done, that's your Freestanding Agent, working without you on its own machine.
- What do I actually message them through?
- A private, secure messaging line that works everywhere: phone, desktop, tablet. It's fast, it feels like texting a person, and you message your Chief of Staff the same way you message anyone else in your life, which is the point.
- What does setup involve?
- One session. We map your first two or three jobs into Scope Cards, connect the access each one needs, and you're live. You bring two model subscriptions (an API account for the Freestanding Agent, an AI subscription for the Local Agent), we tell you exactly which and walk you through opening both. No technical work beyond that.
- Can it work with a system that has no API?
- Yes. The Local Agent works through your browser the same way you do, with read-only access wherever the system allows it.
- Can it really touch my bank accounts safely?
- Visibility into financial reporting and bank accounts is read-only by default. Anything that would touch money requires your explicit approval, tied to the exact item, and changes to banking or payment details are verified out-of-band, never through the requesting thread.
- What happens when they don't know something?
- They say so plainly and ask. Faking confidence is a firing offense for a human Chief of Staff and it's a design rule for this one.
- Can my team message them too?
- Yes. Access and authority are configured per person. Your operations lead might get scheduling authority while an associate gets read-only questions. You decide who's in the room and what each person can ask for.
- What if I want them to do something new?
- Describe the job in plain English, the way you would to a human hire. The new workflow runs draft-first, you review the output, and it earns autonomy once it proves out. Same trust model we use across everything we build.