All Articles
Two Personalities for Claude Code — A Morning and Afternoon Workflow That Separates Exploration from Implementation
Treating Claude Code as a different persona in the morning and afternoon stabilises design decisions. A solo developer's six-month run with two CLAUDE.md files, a switching script, and the failure modes I hit along the way.
Stopping Claude Code from Quitting Mid-Task — Prompt Patterns and Verification Loops
Claude Code says "Done!" — but the build is broken and only half the files were touched. Here are the prompt patterns and automated verification loops I now use in production to keep agents running until the job is actually finished.
Infrastructure Requirements for Claude API Deployment: Sizing, SLA, and Compliance Decisions Before Production
Your prototype works. But what does 'production-ready' actually mean? This guide walks through how to derive infrastructure requirements from traffic, SLA, and data-residency decisions — with concrete numbers and a sizing formula.
Make Claude Your Production Debugging Companion: A Practical Design for Log Triage, Hypothesis Generation, and Repro Scripts
A field-tested blueprint for solo developers who carry their own pager. We split production debugging into three jobs Claude can actually own — log summarization, hypothesis generation, and minimal repro — with full prompts, sanitization code, and traps that cost me real downtime.
Fixing 'String to replace not found in file' errors in Claude Code's Edit tool
Most Edit tool failures in Claude Code come down to invisible differences. Tabs vs spaces, line endings, hidden characters, format-on-save — here's how to diagnose each one.
Designing the One Page You Open Every Morning — Building Living Dashboards with Cowork Artifacts and MCP
Cowork Artifacts promote a chat answer into a re-openable page that fetches live MCP data. Here is how I design pages that replace recurring questions.
Production Semantic Cache for Claude API — Similarity Thresholds, Pollution Defense, and What to Track
A production playbook for adding a semantic cache in front of Claude API — threshold tuning, multi-tenant isolation, pollution prevention, fallbacks, and the metrics that actually prove it works.
Don't Send PII to Claude — A Production-Ready Masking Pipeline You Can Actually Defend in Review
Design and implementation of a PII masking pipeline you can ship in front of Claude API. Covers reversible vs irreversible masking, multi-turn token consistency, and continuous leak-rate measurement with golden datasets — all with working TypeScript code.
Why "The requested model does not exist" Won't Go Away — Claude API Naming and Access Pitfalls
The model_not_found error in the Claude API is almost always a typo or a stale model alias — not a permissions issue. Here are the current model IDs as of April 2026 and a clear order for narrowing down the cause.
From /init Output to a CLAUDE.md That Actually Steers Claude — A 4-Step Refinement
The CLAUDE.md that /init generates is a draft, not a finished file. Here's the 4-step process I run on every new project to turn that draft into a CLAUDE.md that meaningfully changes how Claude behaves.
Four Infrastructure Levers That Cut Claude API Latency Before You Touch the Model
Before you downgrade Sonnet to Haiku to chase faster responses, the network and request shape around your Claude API calls usually has more headroom. Here are four infrastructure levers — region selection, connection pooling, prompt caching, and streaming — with code and measurement notes.
Pasting Screenshots into Claude Code: A Practical Workflow for Fixing UI Bugs Fast
A field-tested workflow for handing screenshots and design comps to Claude Code from the terminal—covering the three input methods, prompt templates that actually work, and the gotchas that bit me in production.