Context-First Thinking
A blog about context engineering, structuring information for LLMs and AI development. Practice, not theory.
How I built a 4-stage news pipeline that clusters articles into stories using title similarity, all in stdlib Python with SQLite.
Why running AI-generated code through more AI reviewers doesn't solve the reliability problem — and what a contract-first pipeline changes about it.
How I built a plugin ecosystem for Claude Code — from scattered scripts to a full lifecycle with scaffolding, quality gates, multi-AI review, and one-command install.
Analyzing SkillsBench — the first systematic benchmark for Agent Skills. 7,308 trajectories, critical review, and why skills are context engineering for agents.
Why git breaks AI agents and how jj solves every single one of these problems
How content format determines whether an AI agent can see your site. Research data, real standards, and what to do right now.
Research on Claude model selection for multi-agent teams. Why Opus can be cheaper than Sonnet, and Haiku is dangerous for agentic tasks.
Reference guide for Gas Town — a system for parallel management of 20-30 Claude Code agents. Commands, concepts, workflows.
Applying evolutionary algorithms to startup idea generation with AI agents
How to solve skill drift in AI agents. Manifest + lock + symlinks — a pattern from package managers applied to context management.
Breaking down Claude Code architecture based on PromptLayer founder's talk. Why while-loop, Bash, and context management matter more than complex workflows.
Why Text-to-SQL and direct REST API mapping fail, and how a semantic graph of business entities solves the context delivery problem in enterprise.
Introduction to context engineering — an engineering approach to working with LLMs. Why prompts stop working and what to do about it.
Follow for updates
@ctxtdev