Anthropic Workshop: Build Agents That Run for Hours — Ash Prabaker & Andrew Wilson

Why self-evaluation is a trap and adversarial evaluator agents work better; why context compaction doesn't cure coherence drift but structured handoffs do; how to decompose work into testable sprint contracts; how to grade subjective output with rubrics an LLM can actually apply; and how to read traces as your primary debugging loop. Plus the question nobody asks: which parts of your harness should you delete when the next model drops? Speaker info: Ash Prabaker |   / ash-prabaker   Andrew Wilson |   / anddwilson   Timestamps: 0:00 Introduction and speakers 1:21 Overview of long-running agents 2:29 Challenges: Context, Planning, and Judgment 4:14 Two approaches: Model updates vs. Harness evolution 5:58 Prehistory: Sonnet 3.5, Computer Use, and MCP 6:34 The evolution of Claude Code 7:55 The Ralph loop technique 9:49 Sonnet 4.5, Agent SDK, and checkpoints 10:49 Opus 4.5 and the role of sub-agents 12:05 First long-running agent patterns 14:20 Opus 4.6, Agent Teams, and server-side compaction 17:28 State-of-the-art harness patterns 21:30 Evaluating subjective output with rubrics 23:44 Introducing the 'Planner' role 25:04 The generator-evaluator contract 31:28 Specificity in contracts and debugging traces 34:14 Adjusting harnesses as models evolve 37:56 How to build your own agent harness 39:01 Key takeaways for long-running agents 40:05 Q&A session