All Articles
Claude API × Convex: Reactive AI Apps — Data Flow, Streaming, and Agent Patterns
How to combine Convex's reactive database with the Claude API to build chat and agent applications that hold up in production. Covers schema design, the Action/Mutation/Query boundary, streaming, tool-call state, and the cold-start pitfalls nobody warns you about.
Why Claude Vision Misses Things — The Preprocessing Settings That Actually Matter
When Claude Vision struggles to read your images, the fix usually isn't a better prompt — it's better preprocessing. Here's a practical look at how resolution, cropping, and model choice change what Claude can actually see, drawn from shipping Vision-powered features in production.
Editing Multiple Repositories at Once With Claude Code --add-dir
How to use Claude Code's --add-dir flag to edit multiple repositories in a single session. Practical patterns for cross-repo API changes, shared utility refactoring, and keeping docs in sync with code.
Running Claude Code Without Breakage — A Failure-First Production Workflow with Plan Mode, Hooks, Rewind, and Subagents
If Claude Code has ever landed a broken commit on your main branch, this guide shows how to combine Plan Mode, Hooks, Rewind, and Subagents into a single failure-first workflow that keeps your repository safe without slowing you down.
Why Your Custom MCP Server's Logs Disappear — Writing to stderr in Claude Code
If you're building your own MCP server and your console.log lines never appear — while Claude Code silently reports the tool as unresponsive — you're probably polluting stdio. Here's how to spot it and rewrite your logs to keep the protocol intact.
Diagnosing Claude Code Subagents That Stall or Never Return
Diagnostic flow for Claude Code subagents that freeze, return silently, or produce the wrong output shape — classified by symptom with runnable examples.
Claude Code's TodoList Quality Comes Down to Task Granularity — Patterns That Actually Worked
The TodoList tool in Claude Code can backfire when used carelessly. Three field-tested patterns — task granularity, verification steps, and update timing — that shift the output from 'looks organized' to 'actually delivered'.
Anthropic, Claude, and Claude Labs — Untangling the Names Behind the Product Lineup
If you've ever felt confused about the difference between Claude, Anthropic, and Claude Labs, this article lays it out clearly — the company behind Claude, how the models are organized, and what each product in the lineup is actually for.
Running the Claude API in Python Production — Rate Limits, Retries, and Timeouts
If you put Claude API into a real backend service, how you handle 429, 503, and read timeouts decides your reliability ceiling. This is the design I settled on after operating it in production.
Claude API × MCP: Building a Paid Consulting SaaS That Runs Without You
Build a sustainable consulting SaaS solo. Learn the complete architecture, implementation, and operations behind a ¥30,000/month revenue system using Claude API, MCP, Stripe, and CloudFlare KV. Includes real code, cost breakdowns, and hard-won lessons from scaling to enterprise.
Claude API Micro-SaaS Pricing Blueprint — Blending Usage, Subscription, and Freemium for Durable Margins
A practical blueprint for pricing a Claude API powered micro-SaaS: how to reverse-engineer healthy margins from token economics, blend usage-based, subscription, and Freemium models, and launch prices you can adjust without breaking trust.
Giving Claude Agents Long-Term Memory in Production — Seven Pitfalls and the Patterns That Fix Them
A production playbook for Claude agents with long-term memory — seven pitfalls that break memory agents live, and the design patterns that fix each one.