8 posts
The twelfth and closing article in Programmer Craft in the AI Era returns to computer fundamentals, systems thinking, product judgment, communication, and collaboration, and discusses which abilities AI will amplify.
Starting from Andrew Ng's comments on small teams and high-context engineers, this article explains why AI pushes senior developers toward a broader product full-stack: problem framing, prototype, code, copy, compliance, launch, operations, and iteration.
A/B testing is not only for frontend pages. API services also need experiment discipline for ranking, throttling, provider selection, fallback logic, and cost control: stable bucketing, real exposure, cross-request attribution, guardrail metrics, and cleanup after the test ends.
Agent systems are no longer just about writing a prompt. What determines production quality is how we select, trim, order, validate, and replay context so the model gets just enough information at each step.
MCP makes tool integration more uniform, but once tools can read files, query databases, and send messages, security becomes a problem of permissions, identity, audit trails, data flow, and supply chain.
A practical look at the protocol boundary of Codex App Server, the product and engineering scenarios it fits, and how it compares with Claude Code and Cursor in automation, cloud agents, and custom integrations.
Article 2 builds ZiQuant's Python engineering skeleton: directories, pyproject.toml, .env, configuration loading, health checks, and test commands. Make the project installable, runnable, and verifiable before the data layer.
Quant trading is not mysticism, and it is not passive income from one magic indicator. Article 1 reframes trading as data, rules, validation, risk control, and review, then starts ZiQuant as a runnable project.