An update on recent Claude Code quality reports

kept by eddie apr 24

Three separate changes to Claude Code's reasoning effort, session caching, and system prompt caused degraded performance for users between March and April 2025, all now resolved.

Harness design for long-running application development
Anthropic engineer Prithvi Rajasekaran builds a multi-agent harness with planner, generator, and evaluator agents that produces full-stack applications over multi-hour autonomous coding sessions.
also on Claude Agent SDK, Claude Code, Anthropic, #user-experience, #ai-coding, #software-engineering, #developer-tools
The Software Factory: Why Your Team Will Never Work the Same Again
AI coding agents like Claude Code already enable software factories where developers design specs and agents implement, shrinking teams and shipping features in hours instead of weeks.
also on Claude Agent SDK, Claude Code, Anthropic, #ai-coding, #software-engineering, #productivity, #developer-tools
Claude Codes #3 - by Zvi Mowshowitz
Claude Code and Claude Cowork dominate AI coding tools, with Anthropic's safety approach enabling permissive agents, but users warned against over-optimizing setups.
also on Claude Cowork, Claude Code, Anthropic, #user-experience, #ai-coding, #productivity, #developer-tools
Running an AI-native engineering org
An Anthropic engineering leader describes how agentic coding shifted bottlenecks from writing code to verification, and outlines new norms for planning, review, context gathering, and team roles.
also on Claude Cowork, Claude Code, Anthropic, #ai-coding, #software-engineering, #productivity, #developer-tools