Step-by-step tutorial: build a TypeScript code review agent using the Anthropic SDK. Tool use, agent loops, real code — no frameworks needed.
Building an AI Coding Agent from Scratch with Claude Agent SDK
Related
Workfront MCP and Claude: a field report from production
What Adobe's Workfront MCP server does, where it stops, and what a verified Claude toolkit does differently — findings from production, with timings.
I Trust My AI Completely—Except When It Says “Done”
A forged confirmation, falsely green tests, and the acceptance gate I built afterward.
Model + Harness = Agent: The Gap Isn’t Where You Think
Same model, different harness: why agent reliability depends on the system around the model.