
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.
Field manual · AI engineering
Practical, code-first tutorials on agents, RAG, prompt engineering and shipping LLM apps to production. No hype — just what works.
[ 01 · Featured ]

A from-scratch walkthrough of the agent loop — tools, reasoning, and termination — using the Claude API and plain TypeScript. No frameworks.
[ 02 · Latest ]
How to use AI to turn raw git diffs and commit messages into clear, user-facing changelogs and release notes — without losing important context.
A practical guide to using AI coding assistants to extract hardcoded strings, generate translation files, detect coverage gaps, and keep i18n in sync as your app evolves.
How to use AI coding tools to catch WCAG violations, understand accessibility requirements, and ship inclusive web code from the first commit.
How to get AI coding assistants to produce reliable regex: giving the right context, supplying test cases, and validating patterns before they reach production.
How to use AI coding assistants to diagnose intermittent test failures — the context-sharing strategies and prompting patterns that surface root causes fast.

A practical workflow for using AI coding assistants to learn, integrate, and debug unfamiliar external libraries — without reading every page of the docs.
[ 03 · Topics ]
Core concepts every AI engineer should internalise first.
Designing, building and orchestrating autonomous LLM agents.
Retrieval-augmented generation, embeddings and vector search.
Reliable prompting patterns for real production systems.
The frameworks, SDKs and dev tools that ship AI faster.
Evals, observability, cost and reliability at scale.