Skip to content
Tagged articles

hillclimbing

2 articles · Page 1 of 1
Architect
Architect
Oct 3, 2026 · Artificial Intelligence

What Counts as a Real Agent Improvement? Lessons from Claude.dev's Four Engineering Articles

Using a subscription billing error as a case study, this article analyzes how to systematically improve AI agents through permission separation, task-specific skill management, reproducible error tracking, rigorous evaluation design, controlled hillclimbing optimization, and deployment validation — drawing on four Claude.dev engineering articles.

AI agentsClaude CodeSkills
0 likes · 22 min read
What Counts as a Real Agent Improvement? Lessons from Claude.dev's Four Engineering Articles
PaperAgent
PaperAgent
Oct 2, 2026 · Artificial Intelligence

Anthropic's Claude Agent Engineering: Multi-Agent Workflows, Skills & Eval

Anthropic publishes its internal Claude agent engineering practices on claude.dev, covering dynamic multi-agent workflows, hundreds of reusable skills, context engineering principles that cut system prompts by 80%, and evaluation-driven hillclimbing that boosted accuracy to 90.5% at one-fifth the cost.

AI agentsAnthropicClaude Code
0 likes · 13 min read
Anthropic's Claude Agent Engineering: Multi-Agent Workflows, Skills & Eval