I Don’t Read My Own Specs Anymore | by David Park | May, 2026 | MediumSitemapOpen in appSign up<br>Sign in

Medium Logo

Get app<br>Write

Search

Sign up<br>Sign in

I Don’t Read My Own Specs Anymore

David Park

9 min read·<br>Just now

Listen

Share

A three-agent workflow for a product manager who can only type with one hand<br>Press enter or click to view image in full size

Apollo 9 Mission Operations Control Room, 1969. One coordinator, many specialists, shared state on the wall. Image: NASA.I’m a former Facebook product manager. A few years ago I had a stroke. I have left-sided paralysis and aphasia. I can only type with one hand.<br>I’m also building an automated ML trading bot that trades 15 different forex pairs — a Double Dueling DQN for entries, XGBoost for stop-loss and take-profit, running live on a Windows Virtual Private Server. It’s not a small project. It has roughly 25 technical indicators per pair, an ML system making buy and sell decisions, 2 different ML models, a walk-forward validation system for the ML models, a currency-concentration gate, and a long list of things still broken.<br>Here’s the part I want to be honest about up front: I don’t know how to build ML systems at all. I’m a product manager by background, not a machine-learning engineer. I can’t sit down and design a reinforcement learning architecture from scratch. I also can’t do serious DevOps — wiring up EC2 instances to brokers over WebSocket with the kind of reliability live trading actually needs is not something I could pull off on my own.<br>But Claude can. And that’s the whole point of this post.<br>Three agents, three roles<br>Press enter or click to view image in full size

The two AI never talk to each other directly. Google Drive is the communication bus.The setup is three agents:<br>Me — the operator. Product manager, decision-maker, screenshot-taker.<br>Claude.ai — the architect. Writes specs, reviews outputs, makes recommendations, holds the long-term context of the project.<br>Claude Code — the coder. Reads specs, executes them, ships code, runs experiments, writes back result reports.<br>The three of us talk through a shared Google Drive folder.<br>The obvious way to use an AI coding assistant is to open one instance, describe what you want, watch it code, and review. That’s how I started — I went straight to Claude Code and typed out specs myself. It worked for small things. For anything complex it fell apart fast, partly because typing long prompts with one hand is brutal, and partly because I didn’t even know how to write good specs for a machine learning system. There was also no second pair of eyes. Bad designs or poor specs would become four hundred lines of committed code before anybody caught them.<br>So I made a change. I moved the spec-writing job to a separate Claude.ai instance — the architect — and let Claude Code stay focused on execution. Two different Claudes, different contexts, different jobs.<br>That single change made everything else possible.<br>Why the architect is the magic<br>The architect is infinitely better at writing specs than I am. Not because it’s smarter than me on any individual point. Because it’s thorough in a way I am not.<br>When I describe a problem in two sentences — “make an automated ML trading bot that’s profitable” — the architect comes back with the right questions. What instruments? What model class? What’s the risk budget? What broker API? What’s the eval methodology? What does “profitable” even mean numerically? Then it writes the spec: architecture diagram, feature engineering choices, training loop, validation strategy, acceptance criteria, edge cases, scope limits, things to not do.<br>Those specs are eight to ten times more detailed than anything I would have written, and they cover things I literally would not have known to ask about. Concrete example: when I told the architect I wanted to expand the bot beyond gold to trade more instruments, it didn’t just pick the next obvious pairs. It proposed a set of 15 forex pairs, and then surfaced a risk I hadn’t even considered — that those 15 pairs concentrated exposure to USD, JPY, and GBP in ways that could blow up the portfolio if one of those three currencies moved hard. The spec it wrote included a currency-concentration gate that caps how much of the portfolio can ride on any single currency at once. I had never even thought about currency-level concentration. And I wouldn’t have. But the architect knew the issue existed and built the guardrail into the spec before a single line of code got written.<br>That’s one example. There are dozens more. The architect knows that a reinforcement learning system with DDQN can’t output continuous SL/TP values, so the spec calls for a hybrid with XGBoost. It knows that without walk-forward validation a 94% win rate on training data means almost nothing, so the spec carves out a test set. It knows that a futures-based CFD has rollover artifacts that will confuse an RL feature, so the spec specifies a back-adjusted source. I would...