Writing
Start here
35 posts
I wrote a C++ options pricer to learn low-latency numerics, and the first clean version priced fifteen million options a second. Getting to 215 million meant finding out my bottleneck was not where I thought, catching the compiler claimi…
A 3D render crossed my feed once and stuck with me, so I tried to see an option the same way: as a surface I could grab and turn, not a number. That turned into five market visualizations on one shared trick, a compliance rule the archit…
In one working session I designed a read-only advisor and spent the rest of it being the customer of another. Both ran on the same short discipline: surface the decision and never seize it, verify before you assert, pilot before you fan…
A screensaver joke, every stock a fish, grew into a six-lens market board I leave running on a wall. It lives in one HTML file on purpose, its data is baked because the browser is not allowed to fetch it, and the feature that finally mad…
You cannot out-staff a security team when you are the whole team. But the failures that actually end a solo operation are a short, known list, and each has a cheap defense you set up once. Here is the catastrophic floor I stood up in an…
I stopped staring at market dashboards. A set of alarms now watches a dozen signal dimensions across the market and taps me on the shoulder only when something actually needs a decision.
A team holds its hard-won knowledge across many heads. A solo operator holds it in one, and that one forgets. The fix is to externalize memory into structured records the tools read by default, so the system remembers what the person can…
The most dangerous result is the one you want to be true. Your own review is compromised by the same motivation that produced the finding, so the fix is a standing skeptic whose job is to refute, not confirm, before you act on anything.
The instinct with agentic tooling is to add: more agents, more skills, more clever prompts. The leverage runs the other way. Here is the test I use to decide whether a piece of work should be a script, a hook, a skill, or an agent, and w…
Boris Cherny mapped five execution archetypes on the Claude Code team, and noted they cut across job titles. His framework describes a team dividing labor across people. Run a fleet alone and the same five split a different way: across y…
GitHub Actions' default minute allowance is priced for a team that types at human speed. At agent velocity the bill breaks before the engineering does. Here is how a forced workaround, a local CI mirror plus local deploys, became the bet…
I built a self-healing RAG pipeline, a guardrails gateway, and an eval gate as one system, then threw 44 adversarial questions at it. Zero hallucinations, because the most important thing it does is refuse. Here is how trust got built in…
Prompt caching looks like a flag you flip for a cheaper bill. It is really the reuse of a stored prompt prefix, governed by three rules, and applying it across four parts of my own system showed where it pays, where it quietly does nothi…
Every system that fuses signals into one consequential number has a fault line: the data you trust enough to composite into a grade versus the data you only trust enough to watch. How I drew that boundary in my personal finance engine, a…
The Knicks won their first title since 1973, decades before I was born. A lifelong fan on the grandfather who handed down the wait, the lean years that taught patience, and the roster I half-built in my head a decade before it came true.
Four days after I said goodbye to Opus, an export-control directive pulled Fable 5 offline and the fallback became the workhorse again. What I shipped in the window, what it cost, and the model-tiering plan for when Fable comes back.
In April I published one week of SDD production numbers. The same data trail rerun for June 1 through 10 shows the velocity curve: 309 PRs opened, 293 merged, about 185 production deploys, and one footnote about outrunning GitHub Actions…
I handed a backlog to Claude Fable, told it once it could merge, and let it run. It shipped seventeen items across five repos. The line that mattered was not in the work it finished. It was in the work it refused to touch.
A backtest's job is not to find an edge. It is to stop you from believing in one that is not there. The toolkit I used to test my own trading engine, and the part where it killed my single best signal.
Anthropic shipped Claude Fable 5 and Mythos 5: same model, two names, one safeguard layer apart. What the new frontier model means for running agents in production.
Dumping the whole corpus into an AI agent makes it worse, not better. The fix is architectural: each task loads a curated slice, not everything you have. Here is the method, and the same move at three different layers: specs, sensor data…
A small ARM box that started as a local LLM experiment and ended up a self-governing node: private retrieval, a resident agent under a written constitution, a code-enforced safety fence, and a nightly job where it audits itself and files…
Why good validation reports every problem at once instead of failing on the first one, and how to build the accumulator, phasing, and structured errors that make it work.
Anthropic published a guide on building a session-level orchestration mode. I built it two ways, on the CLI and on the API, and then hit the part the guide does not cover: an orchestrator that fans out is useless without a backlog of rea…
How I replaced manual CSV exports with a live Garmin data feed for my AI marathon coach: a scheduled unofficial-API poller, resilient session handling, and the design calls that keep training and recovery data fresh and trustworthy.
Two posts ago I bet that keeping my portfolio reviewer's engine deterministic and auditable was worth it. This is where that bet paid off: because the engine is replayable, I could run a simulated market crash through the real production…
A high-level tour of the technologies running this site: Next.js on CloudFront, Python Lambdas behind API Gateway, DynamoDB plus S3, Anthropic's API with a Bedrock fallback, and AWS CDK wiring it together.
A personal portfolio reviewer where the scoring is deterministic and the AI only narrates. The architecture that held up after I had to rewrite the model it was built on, and why that boundary is the whole point.
Two weeks after I shipped a post about a scoring engine I'd built, I rewrote the spec it was based on. Here's what I learned, and why I had an AI agent do the literature review.
The previous two posts made claims. Here is what a week of the workflow looks like as a data trail, PRs, deploys, CI runs, specs merged, pulled from GitHub.
Spec-driven development reads like a methodology for controlling AI agents. It isn't. It's a methodology for managing context across stateless sessions. The spec is the persistent memory.
Two production sites, a blog, and two personal AI projects, shipped this week from a phone. The chain is voice dictation into Perplexity Computer, a spec, then Claude Code on the web. The interaction model is the story.
How I built a personal AI coaching system for marathon training, layering deterministic guardrails over an LLM narrative engine, ingesting Garmin FIT files, and designing for my own injury history.
A practitioner's review of Doug Kerwin's Enterprise Vibe Coding Playbook, why AI as a thinking partner, not a replacement, is the framework enterprise engineering teams need.
Where this blog started: owning enterprise monitoring at Prudential and Amazon, an automation mishap that paged a whole support queue for ten minutes, and the throughline that still runs through everything I build, make the safe path the…