All Articles
Building Fault-Tolerant Long-Running AI Workflows with Claude Agent SDK × Temporal.io — A Production Design Guide to Durable Execution and Saga Patterns
A complete production guide to combining Claude Agent SDK with Temporal.io to build AI workflows that survive crashes, restarts, and multi-day human approval gates. Durable Execution, retry policies, saga compensation, and signal integration patterns.
How to Read Claude Code Logs to Diagnose Issues Quickly
When Claude Code misbehaves, the logs almost always contain the answer. Here's how I structure log reading so that the time to diagnosis drops by half or more in real projects.
What Claude Design Is (And What It Isn't) — A Practical Look at Anthropic's Figma Challenger
Anthropic launched Claude Design on April 17, 2026. Here's an honest, developer-eye look at what's genuinely new and where it fits alongside Figma and Canva.
Tripling Your Consulting Rate with Claude Code: Proposals, Estimates, and Delivery Playbook
A practical guide for freelance engineers using Claude Code who want to rework their proposals, estimates, and delivery processes to justify meaningfully higher rates.
Handling Frequent 529 Overloaded Errors from the Claude API — A Practical Playbook
A 529 Overloaded response from the Claude API is a very different animal from a 429 rate limit. Here is the retry, fallback, and circuit breaker playbook I actually use in production to keep services responsive when Anthropic's platform is temporarily saturated.
Taking Over an Unfamiliar Codebase in One Week with Claude Code — A Maintenance Handover Playbook
When you inherit a codebase from someone who has already left, how do you use Claude Code to reach a state where you can confidently make changes in just seven days? This is the exact protocol I've repeated many times across solo projects and client work, complete with the prompts I use.
Designing Idempotency in the Claude Agent SDK: Production Patterns for Safe Retries
How to prevent double-charged customers, duplicate emails, and inventory drift when your Claude Agent SDK retries or resumes. Covers idempotency keys, outbox patterns, and wrapper decorators with working code.
How to Set budget_tokens for Claude Extended Thinking: A Practical Guide Based on Cost, Quality, and Latency
Are you setting budget_tokens to 'something generous and hoping for the best'? Here is a practical framework for choosing the right value per task type, grounded in real measurements.
Inserting Approval Gates Into Your Agents — A Production Design for Human-in-the-Loop With the Claude API
Once you put an agent in production, the requirement 'please get a human to approve just this specific decision' appears within days. This guide walks through the design patterns for retrofitting approval gates and handling suspend/resume correctly, with working code.
When Claude Code Skills Won't Fire — 7 Checkpoints to Narrow It Down
You wrote the SKILL.md, but Claude Code never calls your skill. Here's an ordered checklist of seven things to verify, organized by symptom.
Keeping Claude Code Accurate Through Long Sessions: Signals of Context Decay and What to Do About Them
After a few hours in the same Claude Code session, output quality can quietly slip. This is a practical field guide to spotting the early signals, choosing where to end a session, and keeping a long workflow reliable.
Claude Code × Python Hybrid Development Patterns: A Production Guide to 50% Token Reduction
Seven production-tested patterns for hybrid Claude Code × Python workflows, each with working code and real-world token reduction data.