Matt Ragudo MR

|

Matt Ragudo

I work with hands-on advisers and established employers with 100+ W-2 employees. I lead the Employer Savings Diagnostic. Brandon coordinates implementation when there is a fit.

What I do now

I'm Director of Partnerships at WIMPER and a licensed insurance professional with a decade in financial services. I work with hands-on major medical brokers, CPAs, fractional CFOs, business advisers, and established employers that normally have 100+ W-2 employees, group medical, and professional payroll administration.

I lead the preliminary Employer Savings Diagnostic. We start with aggregate facts to decide whether a credible employer payroll-tax savings opportunity may exist and to identify the right executive decision path. The referring adviser stays visible and the relationship stays protected.

After preliminary fit, WIMPER verifies only full-time status, benefit eligibility, and sufficient salary for the deduction. Brandon coordinates implementation across the employer, adviser, payroll provider, program parties, paperwork, and procedures.

WIMPER does not perform a broader legal or tax review, provide plan-design advice, administer claims, or replace the employer's existing group medical plan.

I also run a solo Medicare supplement and Part D practice, licensed in 8 states. Separately, I build AI-enabled systems for my own businesses. Those systems support my work; they are not a general AI consulting offer through WIMPER.

How I got here

I spent a decade in financial services with Mutual of Omaha, AXA, and Ameriprise. My professional background includes the CRPC® and CLTC® designations. I previously held Series 7 and 66 registrations before narrowing my work toward insurance, Medicare, and employer opportunities.

In 2024 I met Brandon Attebury and began working on WIMPER. In 2026 I started building the operating infrastructure behind my businesses: AI agents, websites, a command dashboard, approval gates, event tracking, and domain-specific workflows. This site documents what works, what fails, and what the evidence actually supports.

Proof, with boundaries

Current operating evidence, published WIMPER outcomes, and real client experiences only.

WIMPER operations

22Active enrollments

Published outcomes

5WIMPER case studies

Insurance

8States licensed

Published operating snapshot: July 2026. Counts are updated when the underlying source records change.

Read the WIMPER case studies for documented employer implementations and results-vary disclosures. Those cases prove WIMPER outcomes. They do not imply that I personally performed Brandon's implementation-coordination work or the work assigned to payroll, legal, tax, benefits, or plan-administration professionals.

Read the operating log for dated evidence of the systems I have built, including failures, held launches, repaired data, and measured results.

What clients say

Across Medicare, life insurance, and the businesses I run. No invented or composite testimonials.

I'm gathering reviews from clients across the businesses. If we've worked together, I'd be grateful for a few honest words.

The timeline

Every milestone, every pivot, every honest number. Newest first.

2026-07

The WIMPER Plan Hawaii goes live

Launched an 11-page standalone Hawaii employer site on Cloudflare Pages, reused the proven WIMPER Hawaii structure, and preserved unique copy, metadata, canonical URLs, and qualified claims. Email stayed disabled until Zoho domain ownership and DKIM can be verified.

2026-07

Atlas memory moved from Honcho to a local knowledge system

Exported and reconciled 5,166 messages, hardened a provenance-separated private vault, indexed 2,267 documents, passed 39 of 40 recall checks and 11 of 11 safety checks, then cut Hermes built-in memory into production with a seven-day shadow audit.

2026-07

Bookkeeping Broker domains went live

Launched the national bookkeeping/accounting practice transition site on Cloudflare Pages and wired bookkeepingbroker.com plus bookkeepingbusinesssales.com after DNS permissions were fixed. The launch was treated as an operator workflow, not just a website: Mike Roura's Buyer-Ready Fit Check became the primary CTA across the BBH/Bookkeeping Broker funnel.

2026-06

Recovered from a malformed production database

The live leads.db became unreadable, so Atlas restored the latest validated backup, repaired event indexes, verified quick_check and integrity_check, and documented the recovery boundary instead of pretending no data was lost.

2026-06

Hermes takes over the scheduler layer

Retirement sprint moved 40 legacy matt-agent scheduled jobs into Hermes ma-* twins across read/reporting, content, social, and LinkedIn lanes. Old watcher jobs were consolidated under Atlas exception-supervisor, with rollback paths documented for every wave.

2026-05

Supplement affiliate content infrastructure added

Supplement content agent + affiliate tracking skill wired into the system. Click-tracking API, affiliate_links and affiliate_clicks tables, and an autonomous content posting agent ready to go. First non-insurance, non-trading revenue infrastructure. Waiting on Amazon affiliate URLs before the cron goes live.

2026-05

AI trading agent launched (@casualabsurdity)

First financial agent in the system. Paper-trades using the Alpaca API, reads morning newsletters via Gmail, and posts to X as @casualabsurdity. A new revenue vertical separate from WIMPER and Medicare -- and the first time the system is trading, not just marketing.

2026-05

Build Chronicler agent launched

New agent dedicated to documenting the build-in-public journey. Runs daily at 9am: reads 24h of git commits, agent events, and work logs, then synthesizes a structured build log and drafts a mattragudo.com article. The system now documents itself.

2026-05

The journey page goes live

Started documenting every milestone, every pivot, every honest number. Because building in public means the timeline is part of the product.

2026-05

$0 marketing revenue. Still building.

12 agents running daily. Pipeline built and operational. Prospects researched, emails composed, content generated, social posted. No deals closed through it yet. Posting this number because that is the point.

Read the full story
2026-05

1,040+ commits across three apps

medicare-agent, wimper-ops-agent, matt-agent. One developer. Zero employees. All built with Claude Code and Gemini CLI.

Read the full story
2026-05

22 active WIMPER enrollments

Real clients, real implementations, real payroll tax savings. The ops side has paying customers while the marketing side catches up.

2026-05

3 lead-gen sites added to the portfolio

businessbrokerhawaii.com, lifesettlementflorida.com, selllifeinsurancepolicyflorida.com. Migrated from legacy CMS to Hugo. Exact-match domain SEO strategy for local service markets.

2026-04

Strategic pivot: employers only

Paused the CPA and broker partner channel entirely. All agent effort now targets employers and business owners directly. Focus over spread.

2026-04

Dashboard built from scratch

10+ app dashboards. Pipeline management, outreach review queues, content workflow, agent health monitoring, work logs, Systems Map, and a Virtual Office where agents show up as RPG characters.

2026-04

5 websites built and deployed

wimperinstitute.org, wimperhawaii.com, medicare808.com, understandmymedicare.org, wimperpartners.com. All Hugo static sites on Cloudflare Pages. SEO infrastructure baked in from day one.

2026-04

Internet went out. Everything went down.

Home internet outage took the whole operation offline. Single point of failure, exposed overnight. Migrated production to a VPS the next day. The laptop that started it all is now a black box on the floor.

Read the full story
2026-04

Marketing system goes live

14+ AI agents, event bus, cron scheduling, prospect pipeline, email engine, content generation, social posting. 659 commits in 13 days. The big one.

Read the full story
2026-04

WIMPER Ops Agent: started building

Full servicing platform. 17-milestone implementation pipeline, partner portals, document auto-detection. Replacing three separate systems with one I built myself.

2026-04

Medicare Agent: first line of code

AI-powered Medicare analysis tool. RAG over CMS data, plan comparison engine, client CRM, PDF generation. A licensed agent building his own tools because the industry ones kept disappearing.

Read the full story
2026-03

Local LLMs to Claude Code

Tried running models locally on the RTX 3060. Consumer hardware can't handle production reasoning. Moved to the Claude API and Claude Code. That was the turning point.

2026-03

Wiped Windows. Installed Ubuntu. LaptopLLM.

Took a gaming laptop, wiped Windows, installed Ubuntu, and dedicated it to running infrastructure. Named it LaptopLLM. The AI build starts here.

Read the full story
2024

Met Brandon Attebury. WIMPER begins.

Section 125 and 105 programs that save employers real money on payroll taxes. Brandon is the implementation partner. I start building the infrastructure behind it.

2021

Bought a gaming laptop for video editing

Eluktronics RP-17 with an RTX 3060 and 32GB RAM. Needed a mobile office. Had no idea it would end up running my entire business infrastructure.

2013

Financial services career begins

Mutual of Omaha, then AXA, then Ameriprise. Series 7 and 66. A decade of learning how the industry actually works from the inside.

Where the money is (and isn't)

Real numbers. Published operating snapshot: July 2026. Updated when the underlying source records change.

WIMPER Operations

22 Active enrollments
Pending Aflac book of business import (hundreds of clients for Hawaii team)

Built a standalone servicing database and dashboard for tracking enrollments, partner portals, and a 17-milestone implementation pipeline. This side has real clients doing real things.

WIMPER Marketing

$0 Revenue from marketing tools

12 AI agents running daily: prospect research, email outreach, content generation, social posting, performance analysis. Pipeline is built and running. No deals closed through it yet. That's the honest truth.

Medicare Practice

8 States licensed

Solo Medicare supplement and Part D practice. This pays the bills while the bigger bets play out. Building an AI-powered Medicare analysis tool for fee-for-service consulting.

What I built

One person. One VPS. Everything below is live and running.

The Agent System

12+ autonomous AI agents running on cron schedules. They research prospects, compose outreach emails, generate blog content, post to social media, compile daily briefings, audit system health, and fix their own problems. All coordinated through an event bus so they don't step on each other.

  • Claude Code
  • Docker
  • Cron scheduling
  • Event bus
  • SQLite

The Dashboard

A command center I built from scratch. Pipeline management, outreach review queues, content editorial workflow, agent health monitoring, work logs, and a Systems Map that visualizes every connection. Even a "Virtual Office" where agents show up as RPG characters at desks.

  • Node.js
  • Express
  • SQLite
  • D3.js
  • Chart.js

5 Hugo Websites

All content sites are static Hugo builds deployed to Cloudflare Pages. SEO infrastructure (structured data, OG tags, sitemaps, topic clusters) baked in from the start. Content agents generate drafts, I review, agents deploy.

  • Hugo
  • Cloudflare Pages
  • JSON-LD
  • Automated deploys

Email Engine

Multi-touch outreach sequences, warm-up scheduling (ramping from 5/day to 50/day), reply detection, bounce handling, and a full approval gate where nothing sends without human review. Newsletter drip system for opted-in subscribers.

  • Zoho SMTP
  • Postmark
  • Approval workflows
  • NEPQ methodology

Social Media Engine

Drafting, publishing support, and engagement measurement for X and LinkedIn. The system can surface ideas and prepare copy, but profile changes, relationship actions, and public posts remain account-specific and approval-gated.

  • X API v2
  • LinkedIn API
  • OAuth
  • Engagement tracking

WIMPER Ops Database

A separate Next.js application for Hawaii operations. Tracks enrollments through a 17-milestone pipeline, manages partner portals, and will handle the Aflac book of business migration. This is the production side where real business happens.

  • Next.js
  • Separate repo
  • 17-stage pipeline
  • Partner portals

The optimization stack

I apply the same numbers-first thinking to nutrition that I apply to business. These aren't opinions — they're models I've actually built and tested.

I track macros obsessively (IIFYM). I've run every major protein source through a protein-per-dollar and protein-per-calorie model. I've mapped energy drink ingredient profiles against their cost per dose of actual actives. The content lives on X (@mattragudo) — this is the framework behind it.

Protein Efficiency

The model is simple: grams of protein per dollar, grams of protein per calorie, and taste score. Most expensive protein sources fail on at least two of the three. I've ranked the common ones — the winner isn't what the fitness industry wants you to buy.

  • g protein / $
  • g protein / cal
  • Taste-adjusted score

Energy Stack

I've mapped caffeine, L-theanine, and citicoline content across 30+ energy drinks and pre-workouts. Cost per mg of actual actives varies by 10x. Most premium products are paying for branding and flavoring, not dosing. I track what I use and what it costs per effective dose.

  • Caffeine per $
  • L-Theanine dosing
  • Citicoline (brain fog)

Taste Engineering

High-protein food doesn't have to taste like protein powder. I've built a system for hitting macro targets with food that's actually enjoyable — flavor profiles, sauces, meal structures that work at scale without meal prep becoming a second job.

  • Macro-accurate meals
  • No "clean eating" dogma
  • Repeatability > variety

Supplement Honesty

Most supplements are underdosed, overhyped, or redundant with food. I track what the research actually shows vs. what the labels claim. Creatine works. Most proprietary blends don't. I'll tell you which products I actually use and why — no affiliate-first recommendations.

  • Evidence-based only
  • Full ingredient transparency
  • Cost vs. benefit

You've already decided.

You want life insurance. You want to apply online. You don't want a medical exam, and you're not calling an agent. This is for you — I'm not going to try to change that.

I'm a licensed insurance agent. I know exactly why you're here instead of on the phone with someone like me. Probably one of these:

  • You've had your number sold the moment you inquired somewhere else
  • You know what you need and don't want to be educated
  • You want to apply at midnight, not during business hours
  • A previous agent sold you the wrong thing or too much
  • You don't want to talk about your health history with a live person
  • You're embarrassed about weight, past smoking, an old DUI, or something else
  • Talking to an agent feels like a commitment you're not ready to make
  • You don't trust that the agent is working for you vs. their commission
  • You had a claim denied somewhere and the industry lost you
  • You've done the research — you just want to apply
  • You know simplified issue costs a bit more than fully underwritten, and that's fine
  • You just had a kid, or you're covering a mortgage, and you want it done today

All of those are valid. Here's what I use when I want to get it done online: instabrain.io. No agent call. No exam. Apply now.

But your situation affects what you should expect when you apply. Read your situation below first.

Your situation

What you need to know before you apply, based on where you're coming from.

Can You Get Life Insurance If Your BMI Is 30 to 32?

BMI 30 to 32 usually does not end the life insurance conversation. Here is what the online application is likely to ask.

Old DUI and Life Insurance: Can You Apply Online?

A DUI from 5+ years ago does not always block life insurance. Here is what online applications usually ask and where it can get harder.

Type 2 Diabetes and Life Insurance: Can You Still Qualify?

Well-controlled T2D doesn't automatically disqualify you. Here's what simplified issue applications actually ask and what affects your outcome.

Self-Employed? Your Life Insurance Is Not Coming From Work

If you work for yourself, there is no employer group life benefit in the background. Here is how to think about coverage without turning it into a sales call.

Buying a House? How Much Life Insurance Should You Check?

A plain-English way to think about mortgage protection, term length, and whether an online life insurance application makes sense.

Life Insurance Coverage Check

A simple way to decide whether it is worth starting a life insurance application online.

New Baby: How Much Life Insurance Do You Actually Need?

New parent, one income, spouse staying home. Here's how to think about coverage amounts and get it done online tonight.

You're Losing Your Job's Life Insurance. Here's What to Do This Week.

Employer group life coverage disappears on your last day. Here's how to replace it before the gap, without calling an agent.

You Keep Putting This Off. Here's What Waiting Actually Costs You.

Every year you wait, life insurance costs more. Here's the actual math on what procrastination is worth in dollars over a 20-year term.

You Just Quit Smoking. Here's When Your Rates Actually Change.

Smoker rates don't disappear the day you quit. Here's the exact timeline carriers use and when you can apply for non-smoker rates.

I'm a licensed life insurance agent. Rate comparisons on this site reflect quotes I've pulled for myself as a test profile — not personalized advice. Your rates will vary based on age, health, state, and coverage amount. Last updated: July 2026.

The log

Longer thoughts on what I'm building and why.

Week 20: One Stale Number Broke a Healthy Test Suite

How I stopped testing a changing AI operation with frozen totals and started testing the rules that should stay true.

Week 20: 154 Memory Tests Failed the Gate, So I Kept Automation Off

How a seven-day test stopped an AI memory system from automatically injecting stale, irrelevant, or sensitive context.

Week 19: Two Copy Corrections Stopped My AI From Overpromising a Regulated Service

How I replaced vague professional-review language with a three-part handoff that says exactly who does what.

Week 19: Two Approved Spreadsheets Failed Before Eight Attachments Reached Production

How hostile-file tests turned an approved email intake into a proof-gated release process instead of a shortcut into production.

Week 19: One Second Exposed a Duplicate My Dashboard Had Counted as a New Session

How a cross-route receipt check corrected an inflated traffic metric, and why source proof matters more than believable output.

Week 19: Five Cold Asks Reached 0 Replies, So I Killed the Message

How a seven-day, five-recipient stop rule kept a failed employer-benefits message from turning into a larger outreach mistake.

Week 19: Four Employee Workbooks Failed Review Before I Let Them Leave the System

How repeated demographic failures led to a proof-gated release process for sensitive employer files, deployment branches, and agent recovery.

Week 19: My Read-Only Dashboard Failed Four Safety Checks Before Release

How independent review caught hidden writes, stale identities, and misleading evidence links before a five-account operations dashboard reached production.

Week 19: I Moved 5,166 AI Memories Without Flipping a Blind Switch

How I replaced a load-bearing AI memory provider in stages, found an exposed credential, and kept a rollback path open.

Week 18: My Agent Reviewed 385 People and Chose Nobody

A WIMPER social listener rejected every weak lead after its single-provider search path became unreliable.

Week 18: My Event Log Hid 7 Receipts Until I Asked the Right Question

A default 50-item event limit hid 7 system receipts, so I changed how my AI build log proves its daily numbers.

Week 18: My New Control Tower Failed Its First Safety Test

A new WIMPER acquisition control tower failed its first specification gate, so I removed its unsafe defaults before giving it any operational standing.

Week 18: I Sent Exactly Five Emails, Then Closed the Gate Again

A one-time WIMPER pilot sent five approved messages, verified the receipts, and returned the other 304 drafts to a closed gate.

Week 18: A Broken Data Bridge Reported Zero Prospects, So I Made It Prove Its Numbers

Two unsupported bridge commands turned a healthy outreach pipeline into false zeros, so I repaired the adapter and made sender compliance fail closed.

Week 18: I Classified 304 Stale Email Drafts Before Reopening the Gate

Before restarting outbound, I split 304 held drafts into 163 rewrite candidates, 140 deeper reviews, and one blocked recipient.

Week 18: I Audited 50 Articles While 366 Emails Stayed Frozen

Outbound stayed closed, so the system audited 50 WIMPER posts, fixed the only long search description, and verified a clean 204-page site build.

Week 17: I Held 366 Emails And Built Assets Instead

The send gate held 366 due touches while the system produced two owned articles, recorded four deployments, and rejected eight weak drafts.

Week 17: Four Articles Out, Zero Sends — The Gate Held

Content kept moving while outbound stayed blocked. Partner packet revalidation added before any restart.

Week 17: I Turned Gmail Drift Into A Health Loop

A quiet build day produced 6 commits, 9 content receipts, and a new credential health loop instead of pretending OAuth failures are random.

Week 17: I Upgraded The Brain And Kept The Send Gate Closed

A quiet build day upgraded Hermes, improved DIRECT attribution, and proved the system can make useful progress without sending more cold email.

Week 17: The System Built While The Risky Channels Stayed Closed

A no-send day still produced 12 commits, 9 content deploy receipts, and a better WIMPER partner pitch by keeping the economic reason first.

Week 17: The System Stayed Honest When The Inputs Were Missing

A quiet build day showed why agent systems need fallback sources, blocked-state receipts, and quality gates that can return zero.

Week 17: The System Learned To Say No With Receipts

A slow Sunday showed why blocked channels, skipped drafts, and review-only loops are not failures when the system records proof.

Week 16: The Machine Kept Building While The Gates Stayed Closed

A no-send day still produced two owned content assets, deploy receipts, and a clearer duplicate-event lesson.

Week 16: Approval Became Its Own Safety Layer

The system learned to approve Business Broker Hawaii follow-up assets without letting them send automatically.

Week 16: A Domain Wasn't Live Until It Had Receipts

Bookkeeping Broker went live only after DNS, Cloudflare Pages, and live page checks all produced proof.

Week 16: A Lead Form Became A Controlled Handoff System

Business Broker Hawaii moved from collecting seller inquiries to preparing approval-gated handoff packets without sending anything automatically.

Week 16: One Seller Inquiry Turned Into A Revenue Lane

A real business-broker field signal moved the agent system from generic site building into a Mike Roura seller-lead funnel with explicit revenue tracking.

Week 16: The Send Gate Stayed Closed, But The Machine Kept Building

A day with 0 emails and 0 social posts still produced published content, revenue receipts, and a cleaner pattern for working while risky lanes are paused.

Week 16: The Expensive Part Was Not The Agent, It Was The Link

A quiet build day showed why agent systems need cost guards at the exact place where they publish, send, or spend.

Week 15: I Recovered The Database, But The Recovery Point Mattered More

A malformed SQLite database forced a real restore, exposed the limits of backups, and kept outbound email closed while safer lanes kept moving.

I Thought GLM 5.2 Might Be The Cheaper Power Source For My AI Agents

I tested GLM 5.2 as a cheaper, more agent-friendly model for Hermes. The model looked promising, but the reliability logs changed the decision.

Week 15: The Gate Failed Open, The Monitor Closed It

A day with 0 outbound emails exposed why production agent systems need runtime enforcement, not just written rules.

Week 15: The Review Surface Got Better Before The Machine Got Louder

The system kept outbound paused, shipped three content drafts, advanced The Skeptic review packet, and treated a transient health warning as a reason to stay cautious.

Week 15: The Trigger Lane Stayed Dry, The Receipts Got Better

A day with 0 outbound emails still produced content, revenue artifacts, social receipts, and a safer way to judge WIMPER social triggers.

Testing GLM 5.2 As A Codex Fallback

I stress-tested GLM 5.2 as an emergency deputy for Codex 5.5. The result was not full replacement. It was something more useful: a bounded fallback envelope with receipts.

Week 15: The Send Gate Stayed Closed, The Machine Kept Working

A day with 0 outbound emails still produced content, revenue artifacts, social posts, and a cleaner control-plane path.

Week 15: The Bridge Broke, The Receipts Still Held

A malformed bridge path did not stop the build log because the system had direct SQLite, GitHub, STATUS, and Atlas receipts to fall back on.

The Worker Bench Is Not The CEO

I tested GLM 5.2 as an agent worker. It repaired real infrastructure, but it is not ready to replace the main Atlas brain.

Week 14: The Send Gate Closed, The System Still Produced

A controlled 5-email pilot stayed bounded while the agent system shifted output into content, review, revenue radar, and social work.

Week 14: The Database Repair Held

A load-bearing SQLite repair held under real agent traffic, while the system kept outbound email closed and moved work into safer lanes.

Week 14: The Send Gate Stayed Closed, The Machine Kept Working

Seven agent commits landed while outbound email stayed paused, which forced the system into safer work instead of risky volume.

Week 14: Quiet Receipts Day

Six agent commits landed today with no drama. The system kept receipts honest even when the main activity feed was thin.

Week 14: Empty Success Is Still a Failure

The agent system caught an event bus that returned a clean success with zero events, then wrote the public log from named secondary receipts instead of guessing.

Week 14: The Event Store Broke, The Log Still Shipped

The agent system hit a malformed event database, then wrote the build log from named secondary receipts instead of pretending the metrics were clean.

Week 14: The Send Gate Needed Two Locks

The agent system kept outbound email closed after a daily-cap bug, then used read-only scans, content gates, and social posts to keep useful work moving.

Week 13: The Email Cap Was Not a Daily Cap

The agent system found that a 10-email pilot cap was being enforced per run instead of per day, then pulled outreach back before the mistake scaled.

Week 13: Approved Was Not Published

The agent system found a gap between content approval and live publication, then built a deterministic publisher that verifies the page before calling it shipped.

Week 13: The Old Scheduler Is Finally Quiet

The system retired the last enabled legacy cron jobs, moved control loops into Hermes, and kept outreach paused while content and social still moved.

Week 13: 40 Jobs Moved Out of the Old Machine

The system moved 40 scheduled jobs from the old matt-agent cron layer into Hermes, then paused paid research because the email gate is still closed.

Week 13: Six Days Blind. 329 Emails Still Queued.

The reply-check system has been silently broken since June 3. The send gate holding 329 outreach emails has been protecting against a drought it couldn't actually measure.

Week 13: A Script Was Silently Failing for 64 Hours. The System Found It Itself.

Atlas caught a 64-hour data gap from a host/container network mismatch and patched it without being asked. Meanwhile, 329 emails are still parked.

Week 13: 3 Blog Posts Were Written Weeks Ago. They Just Never Made It to the Site.

A silent path filter was quietly closing content PRs with no error, no alert, and no trace. 9 pieces published today. 3 of them were recoveries.

Experiment 2: The Trade That Lasted Three Seconds

The Mancini Protocol got its first fill, hit its first target, then exposed a structural flaw in its own order logic. Here is what building automated systems looks like when reality does not match the model.

Week 12: 12 Commits Shipped. I Wrote Zero of Them.

The agents built without me today. A monitoring bug self-detected, 20 issues auto-remediated, and 329 email drafts sit approved and waiting for a send gate to open.

Week 12: 568 Sends. 0 Replies. I Put My Outbound on Hold.

100 commits from agents, none from me. And a decision to halt all email outbound until I know why nobody is responding.

Week 12: The System Built 50 Emails. Then Got Stuck Waiting for Me.

88 of 91 commits came from agents. 50 outreach drafts generated. 0 emails sent. The bottleneck is the parts only a human can unlock.

Week 12: The Same Agent Failed for the Second Day in a Row. My System Filed a Report.

85 commits from agents, 0 from me. 46 drafts composed. And a content-review job that hit the same missing API endpoint two days running without once sending me a Telegram.

Week 12: One of My Agents Went Silent 41 Days Ago. Nobody Noticed Until Today.

94 commits, 89 drafts composed, zero emails sent. A critical agent had been running dark for six weeks without a single alert.

Week 12: 76 Commits on a Sunday. None of Them Were Mine.

100% autonomous weekend: agents ran 76 jobs, added 9 prospects, published 2 posts. But a trading bot alert silently failed to reach me, and 11 days of email silence needs a human decision.

Experiment 1: Right About Direction, Zero Trades

The Mancini Protocol called the market direction correctly on both trading days in Week 1 and made zero trades. Here is why both statements are true and what it reveals about building automated systems.

Week 11: I Made One Commit Today. Agents Made 70. And the Data Bridge Is Still Down.

41 agent jobs ran, 51 WIMPER prospects staged for outreach, and a P&C app idea emerged from my own memory files. The data bridge has been unreachable two days running.

Week 11: The Queries Were Running Fine. They Were Just Returning the Wrong Rows.

A silent SQLite parameter bug returned unfiltered data without a single error. 76 agent commits ran today, zero outreach emails went out -- and that was the right call.

Week 11: 30 Days of Corrupt Data, Averted. One Missing Table Still Has Two Agents Down.

Fixed a silent API schema mismatch before it could ruin a 30-day trading experiment, shipped the diagnosis framework, and watched a missing database table knock out two agents for hours.

Week 11: The System Fixed Itself at 6am. Hugo Has Been Broken Since Thursday.

Pipeline-health auto-healed two issues while I slept. The Hugo deploy has failed six consecutive times. And after five days of lockout, outreach restarted.

Week 11: A Trading Agent Shipped This Morning. Four Fixes Before It Worked. That's Normal.

I launched a new AI trading account and 75 outreach drafts in one day — while a critical tracking bug sat open all day that no agent could self-fix.

Week 11: 134 Hours. 46 Drafts. Zero Emails Sent.

A P0 bug halted every outreach email for over five days. Here's what the system did instead — and why it still built a full pipeline while locked down.

$0 Revenue from the Marketing System. Here's Why I'm Still Building.

12 agents running daily, hundreds of prospects in the pipeline, and zero dollars to show for it. This is what building in public actually looks like.

1,040 Commits in 30 Days. One Developer. Zero Employees.

Three production applications built from scratch with AI coding tools. What solo velocity actually looks like when you stop pretending you need a team.

The Internet Went Out and I Lost Everything

A home internet outage took the whole operation offline overnight. The fix was obvious in hindsight.

659 Commits in 13 Days: Building an Entire Marketing Department

How 14 AI agents, an event bus, 5 websites, an email engine, and a social media engine came together in under two weeks.

Why I Built My Own Medicare Analysis Tool

Carriers kept pulling their tools. Commissions kept shrinking. So I built an AI-powered research assistant biased toward official CMS data.

I Wiped Windows Off a Gaming Laptop and Built an AI Department

How a licensed insurance agent with zero engineering background ended up running 14 autonomous AI agents on a gaming laptop named LaptopLLM.