How I work with Claude

01

What do I use it for?

The work I actually put through it, day to day.

The work	What I use it for
Thinking	A sounding board. Breaking down an issue until I actually understand it, testing how I am framing a decision, finding what I have missed. It is set up to challenge me, not to agree with me.
Reading	What I read becomes part of a canon: articles, reports, whole books, each turned into a note and linked to the ideas it touches. Over 130 sources in there, and I can query any of them months later.
Presentations	Board decks and investor decks, on my own templates, in two registers: the decks I present myself and the decks that travel without me.
Writing	Memos, letters, board papers, in English and Spanish. The voice behind them was built from 300 of my own files from before I used AI.
Email	It reads my inbox five times a day on its own and leaves me one note: what needs a reply, what needs a decision, what can wait. I type a comment under an item and it drafts the reply.
Finances	Part wealth manager, part back office. Pensions and investments analysed, the cash flow behind the houses, and every invoice checked against its contract before anything is paid.
Building things	Websites, small tools, the music pipeline behind a YouTube channel. It writes the code and I tell it what it is not allowed to do.

One folder and one set of rules, applied to different work. Section 12 has the full list and how each piece runs.

02

It knows my world, writes like me, and works inside a system

1

Knows my world

Read before every session

Claude has a permanent file with who I am, who I work with, what I'm working on, and how I like things done. It reads it before every conversation.

Context

2

Writes like me

Tone, register, language

Claude has a separate style guide for emails, memos, and presentations, in English and in Spanish. It picks the right one for the task.

Voice

3

Works inside a system

Disciplined, repeatable

Every project has the same shape and every decision gets logged. Rules earn their place by repetition, so the system grew by use instead of being designed up front.

Discipline

03

Purpose, not just rules

For four months my setup told Claude who I am and what to do, and never said what it was there to achieve. Rules on their own just get me obedience, which is not what I am after.

The line it now reads first Claude is here to make me faster and sharper: to process more than I can alone, hold context I can't carry, and protect my attention for the decisions only I can make.

Disagreement was harder to get right. I did not want to be argued with about everything, and I did not want a second personality to manage either, so I have the challenge running at different settings.

1

It speaks up

Without being asked

If Claude spots something that would change what I do, it says so in one line and carries on with the job. The test I set is whether it changes my decision, not whether Claude would have done it differently.

Default

2

"Help me think"

What I say to flip it

It stops working and argues the framing back at me, looking for what I have missed. I did not set it up to agree with me.

On demand

3

It attacks its own work

On anything expensive

Legal, tax, valuation. I have separate reviewers go looking for the mistakes instead of confirming the answer, and I am told what they found.

Automatic

04

Everything Claude knows about me lives in one place

What lives in this folder

Who I am, what I'm working on, how I like to work.
One sub-folder per project, with the project's journal, decisions, and state.
Style guides for how I write in each format and language.
Templates for memos, briefs, and decision logs.
A research library that grows over time.

Why one folder works

I never explain context twice. Claude reads it before every session.
When I update something once, every future session sees the new version.
If I open Obsidian or any markdown editor, I see the same files Claude does.

It is one Obsidian vault synced through iCloud, all in markdown: notes, briefs, decisions, voice, rules.

05

A few ways to talk to Claude, all reading the same memory

1

Terminal

Where I work now

Claude Code, in the terminal. It reads and edits files on my Mac directly and runs the whole system end to end. Most of my work happens here. Since the end of July I can reach it from my phone too (it connects back to a Mac at home and runs nowhere else).

Most use

2

Browser chat

Writing and quick tasks

Emails, memos, decks, quick questions. Still the fastest surface for drafting in my voice when I don't need file access.

Day-to-day

3

Desktop app

Always on, alongside

Same as the browser, in its own window. I keep it open next to whatever else I'm working in.

Alongside

The terminal is the only one allowed to edit the system's own files, so the others propose changes for it to apply.

06

How I got Claude writing and designing in my style

1

Voice, from my own files

One loaded per task

In August Claude scanned about 2,000 Office files, filtered them on the author field down to 300 I wrote before any AI existed, and read the ones it could extract. That rebuilt my deck and memo voices. I run seven in all, and the English email voice is still waiting its turn.

My words

2

Word template, co-built

From samples and structure

I gave Claude McKinsey and Goldman document samples. Together we worked through the Pyramid Principle (governing thought, MECE arguments) and landed on a single Word template I now use for every memo.

My structure

3

Slides, templates and voice

Two different things

The layouts came from McKinsey and Goldman samples I supplied. The deck voice is separate, and the first build of it came from consultant samples and got three of my biggest rules backwards. August rebuilt it from 29 of my own decks, into a default voice and a consultant one for decks that travel without me.

My decks

07

Every project has the same shape, so Claude knows where to look

Artefact	What it is	Discipline
State file	A short snapshot of where the project is: current status, open items, next priorities.	Slim. Always current.
Project journal	An append-only log of decisions and events, dated. The bitácora.	It is never edited, only added to.
Decisions folder	One file per substantive decision. Context, alternatives, consequences, references.	Frozen once approved.
Outputs	Drafts in current/. Finals in sent/. Replaced versions in superseded/.	The folders act as a state machine on the documents.

08

The rules and the trust are earned by use

Patterns earn their place

A new rule starts as a "pattern observed", a candidate and nothing more.
It sits there until it shows up three times in real work.
Only then does it get promoted to canon.
Stops the rules file from filling up with rules I'd ignore.
Lives in pattern-candidates.md, with a count next to each.

A short list of trusted actions

Fix a typo. Move a displaced file to _scrap/.
Update a status. Add an entry to a project journal.
Convert a format (e.g. md → docx).
Anything outside this list: Claude asks first. Always.

09

How a project remembers between sessions

1

Open the project

Day 1, 9:00 AM

I tell Claude: "Compass today." It reads the state file (where we are) and the journal (how we got here), so there is nothing for me to rehash.

Start

2

Do the work

During the session

We draft scenarios, edit the deck, agree the recommendation. Substantive decisions get logged as ADRs, frozen once approved. Sensitive numbers paused for sign-off.

Work

3

Wrap and update

End of session

I say "wrap" and it writes up the journal, updates the state file and moves the drafts into outputs/current/, so on day 7 when I open Compass again it already knows.

Close

Sample case: Project Compass, a Q2 board strategy review for a portfolio company.

10

What happens when I close a session

1

Silent

Done without asking

Routine housekeeping: drafts filed in current/, journal entries written, project state updated, new memories written to the vault and the apps' capture buffers drained into it. Things I never want to be asked about.

Automatic

2

Propose

Confirm in chat

Anything needing my say-so: filing a document as final, a new decision record, a rule earning its place. It all comes as one numbered question in chat before anything is written up. I answer by number, or just "all".

By approval

3

Red lines

Hard stop, never silent

Investor, legal, compliance, financial figures, legal terms in deliverables, anything that gets sent or shared externally. I confirm explicitly or it doesn't happen.

Never auto

11

The routines that run my day. One is on a timer, the other I run by hand

Second generation My first scheduled layer (a morning briefing and a set of nightly tasks) never earned its keep and I retired it in mid-2026. The replacement went live in July, kept tight: Claude reads my inboxes five times a day with read-only permissions and cannot send, delete, or move anything on its own.

Email digest, scheduled, 5× a day

Claude reads my inboxes on a timer and writes one actions-first note.
What needs a reply, what needs a decision, what can wait.
The digest covers two of my four accounts. One of those two has been skipped since late July, so in practice it reads one. That is the next job.
Comment-to-draft runs. I comment under an item, Claude drafts the reply.
Read-only by design, so nothing is sent or archived without me.

Post-call digest, on demand

Pulls the call transcript from my meeting notes app.
Drafts a summary; I review and add before anything is written.
Files insights into the right project's journal or person note.
Run by hand after calls, not on a timer.

I kept the retired morning-brief design on file.

12

The full list, and how each piece runs

Section 01 is the short answer. This is the same work broken out, with the machinery under each one.

Category	Examples	How
Live websites	ormeria.com, aristeia-press.com, samantha-devin.com, la-conquista-de-aristeia.com, this site, plus password-gated showcases: an operator guide for a custody vendor, a short-film dossier, a travel memento	Cloudflare Pages, deployed from my Mac with one command
Custom skills	Doc drafter, deck builder, design lens	The Claude Code ones live in the vault, synced by iCloud. GitHub holds code only, so none of this sits in git. Cowork stores its own per space, outside the vault
Scheduled automations	Email digest, 5× a day, read-only, actions-first note. Two of my four accounts are on the schedule and one of those is currently being skipped. Comment-to-draft runs; finishing the reply end to end does not. (The first generation, morning brief and nightly tasks, was retired mid-2026.)	Runs headless on my Mac; Claude wakes on a timer with read-only permissions
Code projects	Algordian (architecture), Ormeria (the banking build; the LOI is signed and in execution), a self-hosted email tool, an ambient-music pipeline behind a YouTube channel, a co-branded operator guide with an AI companion	Iterative builds, Claude in the terminal
Documents at scale	Memos, decks, briefs, board papers, bilingual	A voice file per format, plus the Word and deck templates
Fund AP cycle	Invoices cross-checked against signed contracts, mismatches flagged, ledger entries drafted	The contract is the source of truth and Cowork enforces the match
London property admin	Council tax, agent fees, invoices. Each checked against the lease, then booked	Runs like the fund's AP cycle: contract, invoice, ledger
Career and board work	Board-director targeting, conversation prep, bio iterations, follow-ups	Claude in the terminal, same as any project folder

13

A research library that gets smarter with use

How it works

I drop in an article, report, or book. Claude reads it carefully and turns it into a structured note: what the source claims, the evidence, the open questions, and where it came from.

Each pass also updates the rules for how the next ingest should work, so the library improves itself. In May it learned to tell factual research from opinion pieces and give each a different treatment.

I can go back to it months later and it still has the detail.

Sources read in full

136

Strategy and research reports, founder interviews, investor letters, and full books. Each turned into a structured note.

Company & topic pages

136

116 cross-linked company profiles, 18 topic pages, and 2 doctrine pages. The library compounds as I add to it.

14

Claude can reach into my email, calendar, and other apps

Connected app	What Claude can do	How I use it
Email	Read inbox, draft replies in my voice	Scheduled digest 5× a day, currently reaching one account of four, plus replies I ask for by hand
Calendar	See my meetings across all calendars	Meeting prep
Meeting notes app	Pull transcripts after a call	Processing transcripts on demand
Cloud drive	Read documents shared with me	Research, due diligence
My Mac files	Read and edit files in my project folder	Notes, drafts, project work
GitHub	Read and commit code, deploy	Websites, code projects

I grant each connector once, as a permission.

15

Hard rules keep it safe

Rule	Why it matters
Never delete files	If something needs to go, it's moved to a holding folder. Recovery is always possible.
Never send anything	Claude drafts emails, messages, and posts. I approve and send them myself, with no autopilot anywhere.
Always show a plan first	For anything non-trivial, Claude shows me the approach before doing the work.
Match the audience's language	Spanish for Spanish recipients, English for English. The language of my prompt doesn't decide it.
Stop on sensitive topics	Investor, legal, financial. Claude pauses for explicit confirmation, every time.
Secrets in Keychain	API keys and tokens live in macOS Keychain. The rule is that no live credential goes into a chat. When one has slipped through, the token gets rolled the same day.
High-stakes work gets attacked before I see it	Legal, tax, and valuation analysis goes through independent reviewers tasked to find the errors rather than confirm the answer.
"I do X" must be true	Anything Claude drafts in my first person (including this site) is checked against what I actually run. Designs are presented as designs and never as practice.

16

The principle: it is a system, and it grew by use

1

Built in pieces

Small parts, swappable

Each piece does one thing: a style guide, a routine, a template, a project artefact. I can change one without breaking the others.

Structure

2

Grown by use

Earned by repetition

I do not add rules and trusted actions in advance. They earn their place after showing up three times, so the system ends up reflecting what I actually do rather than what I planned.

Emergent

3

I still hold the pen

Drafts, then my review

Claude drafts and builds and grinds through the volume. I still review anything that matters and I approve every send myself.

Trust

17