Effective harnesses for long-running agents \ Anthropic

kept by eddie nov 27, 25

Anthropic developed a two-fold harness with an initializer agent and a coding agent to enable long-running agents to make incremental progress across multiple context windows.

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, Anthropic, #ai-agents, #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, Anthropic, #ai-agents, #ai-coding, #software-engineering, #developer-tools