Two intense weeks, and a jig
A few intense weeks, progress on money and cloud agents, and a useful new frame for building with AI.
ThrivingHenry - everything I publish
Essays, newsletters, quest updates, and thoughts on Thriving with AI - at work and at home.
Latest posts
Service accounts for scheduled agents
I am pulling scheduled work into service accounts with an agent framework. OpenClaw was a hard no; Vercel's Eve is next.
AI needs an org chart
Team mode with AI is uneven. I am learning the boundaries between skills, workflows, spawned agents, and named agents.
A brand assets repo is a force multiplier
One shared source of visual inspiration raised the polish of every prospect- and customer-facing artifact overnight.
GTM in Flux - AI Changed Everything, and Nothing
What AI changed about trust in B2B SaaS go-to-market - and what it didn't.
Thriving Quest #002: Proactive family finances + #001 progress
Proactive Family Finances is live, and the email quest reached its first inbox zero.
Made it to inbox zero!
On a brand-new inbox. With almost no email. I classified and actioned 49 messages! It only took 14 hours and 8 minutes of active work, spread across 4 days, 21 hours, and 33 minutes, with 67 merged PRs. Oy.
The first email brief sets a 50% actioning baseline
The first four-email Slack brief got two action classifications right. Both the attention and FYI items should have been archived with no action, so the original brief remains unchanged and the 50% result becomes the baseline for calibration.
The server mailbox gets a mobile door
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.
Four characteristics for excellent agent work
Curiosity, patience, attention to detail, and critical thought mediate every agent skill and best practice I've found.
Managing agents is a context-switching skill
Cycling agent tabs and tracking concurrent streams creates a granular fragmentation of work. That skill is trainable, but it isn't intuitive.
Hello (again), World!
A serious pup scare, an unexpected staycation, and the agent-native email quest that brought me back to writing.
The prototype became a systems audit
The July audit found a substantial build: 5,862 synthesized transactions and 160 categorization rules, but no trustworthy operating loop. A failed derived-layer repair proved that fixes must live in durable rules.
When my agents fail
First I check whether I set them up for success. Then I turn the failure into guardrails and evals.
Agent-native email launch fumbled by agent
Thriving with AI launched from the new agent-native stack - and OpenAI's Sol sent the launch email before it was fully complete. The most ironic agent workflow possible is now becoming a stricter dual-inbox test, explicit post-test approval gate, and permanent incident trail.
Thriving Quest #001: No-stress email (with agents)
My first Thriving quest is to increase my capacity for connection with agent-native email.
A cast of agents
I needed a better word for a grouping of agents. Swarm, team, and village never quite fit. Cast does.
The site you're reading is the launch
The quest hub went public - this page, the receipts, the real token costs, all of it. Two days after the mail server was born, the story of building it became the launch surface itself.
Outbound went live the day the host said no
The hosting provider refused to open direct outbound - so the relay path designed on day one took over. Messages queued for 23 hours flushed in seconds, and the whole stack scored 10/10 on mail-tester. The foundation workstream is complete.
Four pages designed and built in a day
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.
The server is alive
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.
The trailhead is mapped
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.
The philosophy became operating rules
Financial freedom, resilience, lifestyle boundaries, and redesign triggers were written down, then translated into goal tiers, income assumptions, budget thresholds, and allocation rules.
The ledger became vendor-independent
Statements, Plaid, and Tiller became independent raw inputs feeding one synthesized ledger. Vendors could now be replaced without surrendering the family record or its provenance.
Goals became a shared review loop
Goals, watched spending, live metrics, balance snapshots, and commitments came together in one review surface. The breakthrough was treating family finance as a recurring decision ritual, not another dashboard.
Thriving, This Time with AI
Five years ago I started writing about thriving without AI. The tools changed. The question didn't. My inaugural essay relaunching my website and newsletter to focus on Thriving with AI.
50 Year Master Plan - Unified Theory of Thriving (UTT) and Global Institute of Thriving (GIFT)
The long game: a Unified Theory of Thriving to understand and a Global Institute for Thriving to study and practice.