Agents 4 min read
Build Your First AI Agent in TypeScript
A from-scratch walkthrough of the agent loop — tools, reasoning, and termination — using the Claude API and plain TypeScript. No frameworks.
Josh
Cutting-edge AI engineering, explained
Learn to build AI software, from zero degrees.
Practical, code-first tutorials on agents, RAG, prompt engineering and shipping LLM apps to production. No hype — just what works.
Featured article
Latest articles
View all → Tooling 7 min read
Documenting Code with AI: Keeping Docs Honest
How to get AI coding assistants to write documentation that accurately reflects your code — not plausible-sounding summaries that drift from reality.
0degrees Team
Production 7 min read
Profiling First, Prompting Second: Using AI to Optimize Slow Code
How to structure AI-assisted performance work — what profiling data to share, how to frame bottlenecks, and how to validate that a suggested fix actually helps.
0degrees Team
Tooling 7 min read
AI-Assisted Git: Writing Better Commits and PR Descriptions
How to use AI to write commit messages, pull request descriptions, and changelogs that actually communicate intent — and where the workflow breaks down.
Josh
Tooling 7 min read
Using AI to Review Your Own Code Before It Ships
How to use AI coding assistants as a first-pass code reviewer — prompting for real feedback on code you wrote, interpreting what it finds, and fitting it into your workflow.
0degrees Team
Tooling 7 min read
Briefing AI on Your Codebase: The Architecture Context That Actually Matters
How to give an AI coding assistant exactly the architectural context it needs to write code that fits your project — without overwhelming it with noise.
0degrees Team
Agents 6 min read
Task Decomposition for AI Coding Agents: How to Break Down Complex Features
How to split a complex feature into agent-sized sub-tasks that execute reliably — with concrete patterns and scope rules that prevent drift and rework.
Josh
Explore by topic
Fundamentals
Core concepts every AI engineer should internalise first.
Agents
Designing, building and orchestrating autonomous LLM agents.
RAG
Retrieval-augmented generation, embeddings and vector search.
Prompt Engineering
Reliable prompting patterns for real production systems.
Tooling
The frameworks, SDKs and dev tools that ship AI faster.
Production
Evals, observability, cost and reliability at scale.