ai-docs

evals

28件のページ

Automating eval design and hillclimbing with Claude
Working at the frontier: How Balyasny Asset Management evaluates and governs Claude Fable 5
How Cresta turned CX expertise into an agent builder on the Claude Agent SDK
How we made claude.ai faster
Using Claude Code: Spending your effort
Define success criteria and build evaluations
Prompt engineering overview
Reduce hallucinations
Choosing the right model
How Anthropic runs large-scale code migrations with Claude Code
Clio: A system for privacy-preserving insights into real-world AI use
Increase web search accuracy and efficiency with dynamic filtering
New in Claude Managed Agents: dreaming, outcomes, and multiagent orchestration
Designing AI-resistant technical evaluations
Skill authoring best practices
How we built Claude Code auto mode: a safer way to skip permissions
Claude Cookbooks
The "think" tool: Enabling Claude to stop and think in complex tool use situations
Introducing Contextual Retrieval
Demystifying evals for AI agents
Effective harnesses for long-running agents
Eval awareness in Claude Opus 4.6's BrowseComp performance
Harness design for long-running application development
Increase output consistency
Quantifying infrastructure noise in agentic coding evals
How we built our multi-agent research system
Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet
Writing effective tools for agents — with agents

作成 Quartz v5.0.0

GitHub
Discord Community