Taming Token Bloat in Long-Running Agents with Context Editing and the Memory Tool
For long-running agents whose input tokens balloon as tool results pile up, here is how to pair context editing with the memory tool and measure the savings with count_tokens, including a working backend implementation.
When a Long-Running Agent's Context Quietly Decays — Budgeting and Compaction
An agent that runs all night gets sloppier by morning. The cause is dilution from accumulated context. Here is how to treat context as a budget, measure its decay, and keep it healthy with compaction — with working code and field notes.
Test-Driven Development with Claude Code — A TDD Workflow for the Agent Era
Adding the constraint of 'write tests first' to Claude Code stops the agent's drift and dramatically changes the quality of generated code. Here's the TDD workflow I arrived at after six months of trial and error.
Four Places My MCP Agent Broke — Measuring Aggregation Tools, Fake Parallelism, and Input Validation
The implementation holes I hit while running MCP servers and agent workflows as a solo developer, with numbers measured on my own machine: boundary values in aggregation tools, parallelism that quietly runs serially, brittle JSON parsing, and the limits of blocklist-style input validation.
Production-Ready Stateful AI Agents with Claude API + LangGraph: Graph-Based Design, Persistence, and Human-in-the-Loop
Implementation patterns for running stateful LangGraph + Claude API agents in production: why from_conn_string fails at compile(), how the recursion_limit default changed, and the schema-evolution trap that breaks interrupt() resumption.
Claude MCP Hybrid Architecture — Design Patterns for Combining Deterministic Tools with AI Reasoning
Learn how to build reliable AI agents using Claude MCP hybrid architecture. Combine deterministic tools with AI reasoning using patterns inspired by Andrew Ng's Tool Use framework.
Claude API Real-time Multimodal Agent Architecture: Design Patterns & Implementation
Master building real-time multimodal agents combining Vision and Tool Use. Learn streaming pipelines, production error handling, and cost optimization patterns with TypeScript and Python examples.
Implementation Patterns for Custom Claude Code Skills — SKILL.md Design, Testing, and Distribution
A hands-on tutorial for building three production custom Claude Code skills from scratch. Covers SKILL.md structure, agent types, context injection, testing, and team distribution.
Claude API Advanced Tool Use: Tool Search, Programmatic Tool Calling, and Tool Use Examples
A working walkthrough of Claude API's Tool Search Tool, Programmatic Tool Calling, and Tool Use Examples — starting with the beta header that everything depends on, plus how to read Anthropic's published reduction figures and when to skip each feature.