The Journey
Most posts here are ad hoc: what I learned building with AI that week, some philosophy, a writing lesson, something I came across.
Subscribe via RSS
Building David, Not a Smaller Goliath
How a trading agent reveals the game retail can actually win — by playing where the funds can't or won't go, and learning to love the play.
BOS-AI had twelve XML files holding nothing
I checked the XML files BOS-AI used to store 'institutional memory' for thirty agents. Every tag was PLACEHOLDER_X. So I deleted all twelve.
I trade three coins, not fifteen
Coinbase lists 15 perp markets. Most alts are leveraged BTC with noise. The case for staying with three, and the one coin I'd seriously paper-test.
Half of agent-11 was scaffolding the platform now provides
I shipped v6 of agent-11 last month. The biggest single change was deletion. The deployed CLAUDE.md went from roughly 250 lines to under 80. The MCP prof...
Now the Real Data Starts
Seven months of building bought me a system that finally tells the truth about itself. The data those seven months produced is mostly unreadable. The clock just started, and not a moment too soon.
What Building a Trading Bot Taught Me About Building Trading Bots
Across 200 trades, the bot was rarely wrong about the market. It was wrong about itself. The dominant failure mode wasn't strategy. It was a system lying to itself about what it was doing.
The House Always Wins. But Retail Can Still Play.
The first move is to see the game. The second is to refuse to play it on the funds' terms — and find the one you can actually win.
The House Always Wins: Why Retail Crypto Trading Is About to Get a Lot Harder
Three forces are converging on retail crypto traders, and none of them favour the small player. The edge isn't intelligence anymore. It's owning the table.
Ten days of letting the check do the work
April 23rd I shipped a blog post about how I'd nearly shipped a fix that referenced three database fields that didn't exist. Author-reviewer collapse. I'd ...
I wrote the rule. Then I skipped it.
Four days ago I published a blog about a bug I'd nearly shipped. The spec referenced two database fields that did not exist — trade.risk_amount and `trad...
Sprint 120 removed a safety rail. 41 trades later, I got the bill.
By the time I ran the SQL, the number was already there: 41 closed trades since Sprint 120, 24.4% win rate, minus $217 net. Before that month, the system h...
The 10 columns I shipped before touching the multiplier
At 00:56 UTC on 17 April, a trailing stop on XRP-PERP widened from 0.69% to 1.56%. Two-point-three times. The trade took the widened stop, held for 15 hour...
The market is smarter than you. That's the feature.
Sprint 130 added a risk-reward floor: no trade below 2.0:1 post-ATR. Three expert reviewers signed off. The logic was clean, the code was tested, the deplo...
The Compute Class Divide
AI providers are chasing enterprise contracts. Compute is finite. The solopreneur gets whatever's left.
The sprint where I removed a gate
Yesterday I shipped a sprint that did something the previous 131 sprints had never done. It removed a gate. For twenty hours the system had opened zero tr...
The Higher Ground Strategy
When 100,000 new apps launch every day, competing on volume is suicide. Here's what I'm doing instead.
The Gates That Never Fired
Building an autonomous trading system, day 145. When safety nets exist but the numbers make them impossible to trigger. --- Three days ago I wrote abou...
6,048 Contributions and Nothing to Show for It
I'm the 18th most active GitHub user in the US. I have 12 followers. Something doesn't add up.
When Your Automation Becomes the Job
When Your Automation Becomes the Job ReadTime: "7 min read" I used to brag about OpenClaw. I had agents running on a Mac Mini. Content. Social. Marketing. O...