Delegate the work.Keep the seal.
Chancelry installs an AI operator on your own machine, fits it to how your business runs, and supports it afterwards.
The Pilot
The way in. One job, built on your own accounts, so you can see it earn its keep before you hand over anything more.
- One job you name. Agreed in a one-page scope before we start: the job, the accounts it touches, and what “working” means.
- Aiming for 7 days. We aim to have it live within 7 days of agreeing the scope, set up on your own accounts over a screen share you start.
- Three paid months minimum, after a first month included. Long enough to see whether the job is worth keeping.
- It can grow. If you want more of the firm covered, the Pilot grows into a bigger set-up, up to the full operator. Go ahead within 90 days of handover and the Pilot build is credited in full against it.
- Everything in writing. You get the scope and the full terms by email before anything is agreed.
The price isn’t on this site. Ask and we’ll email you the figure and the full terms. You don’t need a call first.
Start with one job
Name one job you’d take off your desk. We agree in writing what “working” means, and we aim to have it running within a week of agreeing it, in your own email and systems.
You name the job. Reply to our email or use the consultation form. We’ll reply by email to say whether it fits.
We agree it in writing. A one-page scope: the job, the accounts it touches, and what “working” looks like.
Aiming for a week. We aim to have it running within a week of agreeing the scope, set up on your own accounts over a screen share you start.
Handover. A 45-minute screen share, then one round of changes within 14 days.
If it earns its keep, it grows. The same set-up can take on more of the firm, up to the full operator described below.
Examples of a single job. Not client results.
- Candidates who’ve gone quiet. A list each morning of candidates who haven’t replied in the time you set, with a chaser drafted for each. You decide in the scope whether it sends or waits for you.
- Business development research. A weekly list of firms that match what you look for, with why each one made the list and where the details came from.
- Replies you’d otherwise miss. When a candidate or client replies, you get a message on your phone saying who it was, and any follow-up to them stops.
What you’ll need
- The accounts the job runs on, in your own name and paid for by you.
- A paid Claude plan whose terms allow your business use, if the job uses Claude.
- If a computer is involved: administrator access, and a backup you’ve checked can be restored.
- One person who can approve the scope and sign off at handover.
- Nothing technical to learn. You start a screen share and we do the set-up.
An operator you run from your phone
The system is built on Claude Code. A lead orchestrator reads your messages on Telegram, passes each piece of work to the specialist agent suited to it, and reports back. Several specialists can work at once.
It can run commands, edit files, push commits and send messages. It keeps a written memory of decisions and context, searchable across sessions, so a new session picks up what the last one settled.
It isn’t hosted anywhere. It runs on your machine, under your own Claude plan.
We run the same design on our own work.
The name comes from the chancellery, the office that held a ruler’s seal and acted with their authority.
What you have at the end
When the engagement ends, each of these is in place.
- An orchestrator installed on your machine and running on your own Claude plan.
- Specialist agents set up for the work your business does, with the routing written down where you can read it.
- A Telegram channel that only the accounts you approve can reach.
- A memory in plain files, started with how you work.
- A safety gate in place before the operator is given real work.
- A technical reference and a handoff note for each project it works on.
- Support afterwards, from the person who configured it.
How an engagement runs
Consultation. We learn how your business runs and whether this suits it. Either side can stop here.
Scope. We agree what the operator will handle, which machine it lives on, which accounts it can touch, and what it must never do.
Installation. On your machine. The safety gate goes in before the operator is given anything real.
Configuration. Specialists, routing, memory and rules, written for your business.
Handover. You run it from Telegram while we watch it work.
Support. While the monthly support runs, when something we set up breaks we restore it or give you a workaround, and we add a check for that fault.
What’s on your machine at handover
At handover, the way the operator works is written down in files on your machine.
- The rules it follows, in a plain-text file you can change.
- Its memory, as plain files you can read and correct.
- A technical reference for each project it works on, and a handoff note recording where the work stopped and what comes next.
- An audit log of what it did.
None of it needs us to open it. It can also be backed up to a private GitHub repository if you choose. The Claude plan it runs on is yours, paid to Anthropic directly.
It checks before it acts
Every shell command and every file edit passes through a safety gate before it runs.
Some commands are refused outright. A force push to your main branch is one of them, and no approval overrides it.
Others wait for you. A recursive delete or a dropped database table stops until you approve that exact command. An approval covers one use and lapses after 30 days.
Everything else runs, and each action is recorded in an audit log. We switch this on for every operator install.
Its rules sit in a plain-text file you can read and change. So does its memory. Only the Telegram accounts you approve can reach it.
What the gate is not
The gate is a check inside Claude Code rather than operating-system enforcement. It hasn’t had an independent security audit.
Put a command to the gate
An illustration of the gate’s rules. It isn’t connected to a live system.
git push --force origin main
Refused. No approval overrides it.
Who it’s for
- Firms that want one job done first, without learning anything technical.
- Owners and operators who already delegate, and want more of the work handled from their phone, inside limits they set.
- People comfortable in a terminal, who want to see how the thing they rely on works.
- Anyone with a Mac or Windows PC that can stay on, a paid Claude plan whose terms allow your business use and a Telegram account.
Who it isn’t for
- For the full operator: beginners, or anyone looking for an app to download. There’s no one-click install and no graphical setup.
- Anyone who needs it answering while their own machine is switched off.
- Regulated environments that require an independently audited stack.
A CRM that remembers every conversation
An upgrade to the engagement. Next to the operator, we set up a private CRM for your business: every firm, every email and call, and what happens next, in one place.
- Every firm you deal with, in one list. Search, filter, open.
- Two businesses, one CRM. Each keeps its own firms and sender.
- Open a firm and see where it stands, and who to speak to.
- Log the call and book the follow-up in one step.
- Set the follow-up for a time. A reminder comes up when it’s due.
- See where leads come from, where they drop off, and why.
An illustration. Every firm and person here is invented, as is Example & Co. The bars show no real data.
- Every firm on one page: the emails you sent and received, with the text of each, and your calls, notes and tasks.
- Email a contact from their page, from your own Google Workspace or Gmail address.
- Reports on where leads come from, how many reply, and why the rest were lost.
- Sign-in only for the people you name.
Questions
Open a question to read its answer.
Is this software I subscribe to?
No. It’s a service. We install the system, configure it for your business and support it afterwards. The software runs on your machine, under a Claude plan you pay Anthropic for directly.
What do I need before we start?
For one job: the accounts it runs on, in your name, a paid Claude plan whose terms allow your business use if the job uses Claude, and one person to sign it off. For the full operator: a Mac or Windows PC that can stay on, a paid Claude plan whose terms allow your business use, a Telegram account, and enough comfort with a terminal to follow what’s being set up.
Where does my information go?
The operator runs on your machine. Our copy of the conversation history stays there. The work itself is done by Claude, so it travels to Anthropic under your own plan. Your Telegram messages pass through Telegram’s servers, as with any Telegram bot. Memory and project files can also be backed up to a private GitHub repository if you choose.
Could it do something I didn’t intend?
It acts on what you tell it, and it can make mistakes. That’s why the gate exists. Commands on its list that can’t be undone are either refused or held for your approval, and every action is logged. Not everything that can’t be undone is on that list: an email it’s allowed to send has gone. The gate has limits. A process started outside Claude Code isn’t checked, and someone who has already gained the ability to run code on your machine has known ways round it.
Has the safety gate been independently audited?
No. It hasn’t been through a third-party security audit. If your sector requires one, this isn’t the right fit yet.
What happens if my machine is off?
It stops. It runs on your machine, so a computer that’s shut down or asleep can’t answer, and it won’t bring itself back unattended. We can build you an outside check that messages you when it goes quiet. Expect that alert within hours, not minutes.
Why isn’t there a price here?
Every engagement is scoped to one business, and you can start with one job. We tell you the fee once we know the job.
Can I change what it does after handover?
Yes. Its rules are a plain-text file you can edit, and its memory is plain files you can read and correct.
Will it act without asking me?
For ordinary work, yes. Commands on its list that can’t be undone are held until you approve that exact command, or refused outright. Not everything that can’t be undone is on that list: an email it’s allowed to send has gone. Everything it does is logged.
What’s left if I stop using it?
The files. Its rules, memory, handoff notes and project references stay on your machine, and in your private GitHub repository if you back them up there. The Claude plan is between you and Anthropic.
Start with a conversation
Tell us how your business runs and what you’d hand over first. If Chancelry suits it, we’ll say so. If it doesn’t, we’ll say that too.
Or write toinfo@chancelry.com