Build a Research Agent with Claude Managed Agents (Part 2 of 4) — Anthropic
Source
youtube.com
Author
AI Engineer
Date
Context
Anthropic's Managed Agents can use explicit acceptance criteria to drive revisions. In the research-agent workshop, a task includes a required deliverable, a grading rubric and an iteration limit. After the AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → produces its work, a grader checks it and returns feedback that can trigger another attempt.
The outcomes documentation explains that the grader uses a separate context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → and assesses individual criteria. This makes the rubric consequential: concrete requirements give the agent specific defects to repair, and the iteration limit bounds how long that revision loop can continue.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
video1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Run Code — Kevin Orellana, AWS
videoHow Inference Keeps Up with Our Insatiable Need for Tokens — Cerebras & Gimlet Labs
videoAuth for Agents: Let AI Sign Up for Your Product with auth.md — Michael Grinich, WorkOS
videoDecoupling the Brain from the Hands: Claude Managed Agents (Part 1 of 4) — Anthropic
