ThrivingHenry - everything I publish

Thriving with AI Membership is open.

OpenAI models can handle extremely long running tasks, but I still have to watch them closely and budget attention and tokens to clean up after them.

The current state of working with AI feels a whole lot like a plate spinning act.

My @Work page is live: one frontier polished, two honest sketches.

Token debt is having old recurring loops or cron jobs that are still running but are effectively useless.

One of the skills of working with AI is parallelizing work between sessions, models, and harnesses efficiently.

A new family fun quest, a real budget my wife and I committed to together, a Thriving Wage calculator, and my first agent in the cloud.

It's easy to forget how deep in the AI echo chamber I am.

Every's answer to why AI rollouts stall: it's easier to raise the ceiling than the floor.

A budget and forecast system where every category correction and every change to future spending feeds back into the learning engine sounds awesome.

A forecast projects past spending into the future.

A September-through-December forecast now runs from the expected-transaction lines and matched my hand-built rollup to the cent.

Weekly, monthly, and quarterly review loops now separate quick picks from long-lead planning, and a cloud successor built on Vercel's Eve framework ran its first safe preview: 308 future events narrowed to 81 candidates without touching the live calendar.

My email quest is floundering because Slack is too high friction for triage.

A few intense weeks, progress on money and cloud agents, and a useful new frame for building with AI.

I am pulling scheduled work into service accounts with an agent framework.

Team mode with AI is uneven.

The ledger reached 99% categorization, July's review corrections landed, and fourteen expected-transaction lines turned known recurring, periodic, and one-off costs into a forecast I can inspect from the total down to the individual payment.

One shared source of visual inspiration raised the polish of every prospect- and customer-facing artifact overnight.

What AI changed about trust in B2B SaaS go-to-market - and what it didn't.

Proactive Family Finances is live, and the email quest reached its first inbox zero.

A standards-based CalDAV calendar put high-signal family outings and date-night options on my phone without turning them into commitments.

On a brand-new inbox.

The first four-email Slack brief got two action classifications right.

Roundcube is live on the self-hosted mailbox, so the daily brief can link back to the copy that actually arrived on the server - from a phone or any browser.

Curiosity, patience, attention to detail, and critical thought mediate every agent skill and best practice I've found.

Cycling agent tabs and tracking concurrent streams creates a granular fragmentation of work.

A serious pup scare, an unexpected staycation, and the agent-native email quest that brought me back to writing.

The July audit found a substantial build: 5,862 synthesized transactions and 160 categorization rules, but no trustworthy operating loop.

First I check whether I set them up for success.

Thriving with AI launched from the new agent-native stack - and OpenAI's Sol sent the launch email before it was fully complete.

My first Thriving quest is to increase my capacity for connection with agent-native email.

I needed a better word for a grouping of agents.

The quest hub went public - this page, the receipts, the real token costs, all of it.

The hosting provider refused to open direct outbound - so the relay path designed on day one took over.

The launch surface went from route inventory to four reviewed page redesigns in one day - drafted as design cards, edited in a shared design pane, shipped as pull requests. 30 routes went dark; 13 pages remain, crawl-audited clean.

My thrivinghenry.com mailbox now receives on hardware I control: MX cutover done, first real message delivered in under a second, and an EA agent triaging at 100% on its golden-set eval.

Design spec approved before any building: a self-hosted OpenBSD mail server, a newsletter relaunch on owned rails, this quest hub, and a five-seat cast of agents - with success criteria declared up front.

Financial freedom, resilience, lifestyle boundaries, and redesign triggers were written down, then translated into goal tiers, income assumptions, budget thresholds, and allocation rules.

Statements, Plaid, and Tiller became independent raw inputs feeding one synthesized ledger.

Goals, watched spending, live metrics, balance snapshots, and commitments came together in one review surface.

Five years ago I started writing about thriving without AI.

The long game: a Unified Theory of Thriving to understand and a Global Institute for Thriving to study and practice.