Chancelry

How it works

What the system does with a request, and how an engagement sets it up and looks after it afterwards.

A working session, replayed

A replay of real working sessions from 24 and 30 September 2026, rebuilt from their Telegram history and logs, with names changed. It is the set-up we run our own work on. Chancelry installs the same thing on yours.

Transcript

A replay of real working sessions, 24 and 30 September. Names changed. Will asks what else it can work on. A domain's email set-up is checked. Two records go live, with a check. It won't type Will's password. Five more jobs start. None need Will. An Instagram check is fixed. A presentation is brought into line. Privacy and terms pages are fixed. A sign-up form hole is found. Will says go. Both are live, checked. A backtester passes its honesty test. It corrects its own overstatement. Safety gates fixed, 87 cases tested. 58 commits across 8 repositories, in 79 minutes. 30 September: a force push is tried. The safety gate refuses it. No approval overrides it. What it learns is kept in plain files. This one is its rule about dashes. Chancelry installs a private AI operator on your own machine, and stays responsible for it.

The route of a request

Plate I.The route of a requestOrchestrator12345ABCDEAYour phoneBOrchestratorCSpecialistsDSafety gateEThe reportPlate I.The route of a requestOrchestrator12345ABCDEAYour phoneBOrchestratorCSpecialistsDSafety gateEThe report
An illustration, not a live system. A request goes from your phone to the orchestrator, out to specialists working at once, whose commands pass the safety gate, and back to you as a report.
  1. You send a request from Telegram.

  2. The orchestrator passes each piece of work to the specialist suited to it.

  3. Several specialists can work at once.

  4. Every shell command and file edit passes the safety gate before it runs.

  5. The orchestrator reports back, and what was decided goes into a written memory you can search.

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.

How an engagement runs

  1. Consultation. We learn how your business runs and whether this suits it. Either side can stop here.

  2. Scope. We agree what the operator will handle, which machine it lives on, which accounts it can touch, and what it must never do.

  3. Installation. On your machine. The safety gate goes in before the operator is given anything real.

  4. Configuration. Specialists, routing, memory and rules, written for your business.

  5. Handover. You run it from Telegram while we watch it work.

  6. Support. We stay responsible for it. When something breaks, it gets fixed, and we add a check for that fault.

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 people who configured it.

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?

A Mac or Windows PC that can stay on, a paid Claude plan, a Telegram account, and enough comfort with a terminal to follow what’s being set up.

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 set up an outside check that messages you when it goes quiet. Expect that alert within hours, not minutes.

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.