Professional coaching · solo founder · A business coach · Live May 2026

An AI operating system for a one-person coaching practice: 4 agents that read one document.

Inbox triage, scheduling replies, voice-note task capture, and a calendar-to-invoice workflow, all reading one document she edits in plain English.

13 to 15emails/day triaged with zero noise, each decision citing its source message

115 of 115 stale tasks archived in one sweep, fully reversible, because every agent stamps its work

Diagram: one brain document read by four agents, with a maintainer agent as its only editor — One document, four agents, one maintainer.

What I built

The build

The brain document: one doc holding her voice, brand rules, client roster, and policies, read by every agent as live knowledge. She changes it by messaging a maintainer agent in plain English.
4 agents inside her project tool: inbox triage that defaults to skip and cites the source message, scheduling that drafts the reply inside the task, voice-note capture that splits and routes, and meeting notes on a scheduled routine she owns.
Calendar to invoice: on the first of the month it reads both calendars, parses client and service codes from the events, and writes hours to a color-coded sheet. Receipts, automatically.
Every agent stamps its work, so output is always attributable and sweepable. That made a 115-task cleanup safe, reversible, and rehearsed in a sandbox first.

What changed

Before and after

Before

By hand

InboxRead everything herself

Scheduling repliesWritten by hand

Invoicing proofNone

Changing a ruleRe-prompt every tool

After

The system

Inbox13 to 15 a day triaged, sources cited

Scheduling repliesDrafted inside the task

Invoicing proofCalendar to sheet, monthly

Changing a ruleEdit one document

Where the numbers come from. The email count is her daily inbox volume during the build; the 115 tasks were the stale backlog archived on 2026-07-20 with an undo manifest kept.

For engineers

How it's built

Architecture: No-code agents configured in plain English inside ClickUp, all pointed at one Brain Doc as shared knowledge. A maintainer agent is the only writer to that doc. One integration workflow for calendar to sheet, because that step crosses tools.
Where it runs: Inside her own ClickUp and Google accounts. She owns every piece; the exit shipped a portable 7-file operating system and a 15-page printed system tour.
Tests and evals: A regression test per agent after a scope-creep incident, where the maintainer rewrote unrelated sections; instructions hardened with a self-check step. The 115-task sweep was rehearsed in a sandbox before it ran.
Cost and latency: About $20 a month in tooling.
Guardrails: Every agent defaults to skip, forces the assignee and a source stamp on every task it creates, and must cite the inbox message it acted on. No agent sends email.
The tradeoff we chose: Why this way and not the other
Native ClickUp agents instead of a custom stack. Less power, but she can read and change every instruction herself, and there is nothing of ours to maintain. A one-person practice needs a system she owns, not a vendor.