Personal Operating System
Jersey · GMTEst. 2026Get in touch →
Practitioner notes · AI applied to finance & operations

Jewel Nguyen

An operator who builds — turning back-office problems into systems that run themselves.

One person, running on a personal operating system — capture, digest, retrieve. Below: who I am, how the system works, and what it has built. Hand-made, not hand-held.

The Big One · How I Work

I run my life on a system I built myself.

Telegram in, daily brief out. Every note, article and decision flows through one pipeline — so nothing is lost and everything is findable.

13 → 1
manual steps collapsed into a single review
3
systems running live, every day
Daily
brief, written & delivered automatically

Most people drown in their own inputs — bookmarks they never reread, notes they never find, ideas that evaporate by lunchtime. I treat that as an operations problem, because it is one.

The personal OS has three moving parts. Capture is frictionless: a message to a Telegram bot, a saved bookmark, a voice note. Process turns raw input into clean, linked markdown in a single vault. Digest reads it all back and hands me a styled morning brief.

None of it is magic. It is small, boring automations wired together with judgement about what actually deserves attention. The same instinct I bring to a finance back office: remove the manual step, keep the human one.

About

From the back office to building.

Finance and operations professional, recently moved into Investor Relations in fund services. I spent years automating back-office work, then started building the tools instead of just specifying them.

Read the full story →
The Method

Research first, build it right.

Every build starts with research, then a clear scope, then the smallest system that removes the manual step. I would rather do something once and well than thirteen times by hand.

See how I work →

From the Journal

Selected public entries

All entries →

Reading Desk

This week
1
The personalised morning magazine
Curation beats feeds
2
Agent architectures for everyday tasks
When orchestration earns its keep
3
Document AI in financial operations
Extraction that survives real PDFs
4
The case for local-first knowledge
Why my vault stays plain markdown
5
Investor relations in fund services
The day job informs the build

Full reading desk →

The Showcase

Selected builds & portfolio
Knowledge · Live

Second-Brain / Life-OS

Telegram capture → markdown vault → styled daily brief. Scattered inputs into one searchable system.

View →
Finance Ops · Portfolio

Contract-to-Order Pipeline

Reads signed PDFs, verifies the counterparty, drafts the sales order — thirteen manual steps into one review.

View →
Reliability · Live

The Self-Auditing Dashboard

A morning chief-of-staff that reads yesterday's work, checks every automation, surfaces only decisions.

View →
Get in touch

Have a back-office problem worth automating?

I'm open to conversations about building systems in finance & operations — and about the work above.