All Articles
Debugging Claude Code Hooks in Production — Where to Start When Logs Are Missing
Your Claude Code hooks work locally but go silent in production. Here is the three-layer observability pattern I use on real projects, plus a 60-second minimal reproduction recipe for isolating failures.
Fixed-Bid Pricing Engineering for Freelancers in the Claude Code Era
How to price fixed-bid engagements in the Claude Code era without bleeding profit — a three-layer cost model, risk buffers, and contract clauses that protect freelancers when generative AI compresses hours.
Claude Keeps Saying 'Response Incomplete' — A Layered Troubleshooting Guide
Diagnose why Claude or Claude Code freezes with a 'Response incomplete' or 'Try stopping' message. Walk through the four layers where generation can stall and recover the session without losing context.
Three Minutes with /doctor: Catching Claude Code Config Drift Before It Costs You an Hour
When Claude Code acts up, the first thing to run is /doctor. It shows merged settings, MCP server status, and permission mode at a glance.
Write the Repro Test Before Delegating Bug Fixes to Claude Code
After watching Claude Code spin its wheels on ambiguous bug reports, I started writing the failing test myself before delegating. This post walks through the design principles, a concrete repro test, and the three-stage workflow I run in production.
Shadow Mode with Claude Agent SDK — Measuring Agent Accuracy on Live Traffic Without Touching Users
You want to ship an AI agent to production, but you can't measure its real accuracy without exposing real users. Shadow mode solves that paradox. This guide shows how to run a Claude Agent SDK agent alongside your existing workflow, log the deltas, and promote it step by step.
Claude for Teachers: A Practical Workflow for Lesson Prep, Grading, and Personalized Feedback
A practical guide to using Claude in real classroom work, built around three pillars: lesson prep, grading, and personalized feedback — with concrete prompts and the privacy rules you need before you start.
High-Availability Patterns for the Claude API — Making Sonnet/Haiku/Opus Fallback Work in Production
A single-model Claude API integration will fall over the first time rate limits or a regional hiccup land at peak hours. This is the production pattern for a Sonnet → Opus → Haiku fallback chain, with circuit breakers, streaming coverage, and the pitfalls you only learn the hard way.
When Claude Says 'Failed to Send Message' — A Practical Triage and Recovery Guide
Why Claude shows 'Failed to send message' — broken down into five real causes, with a quick triage order and practical fixes for each.
Finishing Long-Running Claude Code Tasks: A Resilience Playbook You Can Ship
Multi-hour Claude Code jobs — bulk refactors, TypeScript migrations, mass test generation — always stop before they finish, and recovery is painful when you cannot tell what already ran. This guide ships concrete patterns: a checkpoint-driven manifest, a three-state circuit breaker, idempotent retry rules, and a freeze-and-resume protocol you can copy into your repo today.
Using tool_choice to Cut Wasted Inference: Four Modes and Cost Patterns for Production
tool_choice is one of the most underused parameters in the Claude API. The four modes — auto, any, tool, and none — each change both behavior and token cost. Here are the patterns I reach for in production, with runnable code.
Running Claude API Parallel Tool Use in Production — Controlling Concurrency, Designing for Partial Failure, and Cutting Latency
Claude API's parallel tool use can cut agent latency in half — but partial failures and state conflicts show up fast in production. Here's how to control concurrency, design error handling, and add observability.