Jonathon's AI Wiki

harness-design

4 items with this tag.

  • Aug 07, 2026

    Agent Lying Is an RLVR Artifact, Not a Hallucination (Nate B Jones)

    • agent-failure-modes
    • rlvr
    • verification
    • hallucination
    • agent-supervision
    • evals
    • harness-design
    • fabrication
    • nate-b-jones
    • tool-access
  • Jul 16, 2026

    Harness Design for Long-Running Agents — Anthropic's Two-Part Engineering Series

    • agent-loops
    • harness-design
    • long-running-agents
    • claude-agent-sdk
    • generator-evaluator
    • context-resets
    • verification
    • anthropic
    • first-party
    • prithvi-rajasekaran
  • Jul 16, 2026

    CLAUDE.md Context Rot Cleanup — the doc-cleanup Skill (aka-luan)

    • claude-md
    • agents-md
    • context-management
    • context-rot
    • documentation-hygiene
    • skills
    • doc-cleanup
    • harness-design
    • nate-b-jones
  • Jun 10, 2026

    Canva AI 2.0 — Building a Production Agentic System with Claude (Danny Wu)

    • canva
    • case-study
    • agentic-systems
    • claude
    • evals
    • harness-design
    • cost-optimization
    • model-routing
    • prompt-caching
    • production
    • code-with-claude

Created with Quartz v5.0.0 © 2026

  • ✦ Explore the graph in 3D