{"version":"1.0","type":"card","id":"171c021b-0b07-4b19-81be-51166223e7c0","url":"https://stacklist.com/card/171c021b-0b07-4b19-81be-51166223e7c0","title":"Effective Context Engineering for AI Agents — Anthropic Engineering","source_url":"https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents","note":"Straight from the team that builds Claude. This post explains how to structure context so agents behave reliably — what to include, what to omit, and how to avoid common failure modes. Essential reading for anyone building multi-step AI pipelines.","image":{"url":"https://ucarecdn.com/394e6bfe-ba09-4f56-8883-a2053b4f5ac8/","alt":"Effective Context Engineering for AI Agents — Anthropic Engineering","width":2400,"height":1260},"stack":{"id":"e16dcdcb-06b9-481c-aef9-40b6d73a5c8e","title":"Master AI & LLM Context: From Basics to Production","url":"https://stacklist.com/c/technology/stack/e16dcdcb-06b9-481c-aef9-40b6d73a5c8e"},"created_at":"2026-07-02T10:08:40.045Z","updated_at":null,"aco":{"summary":"Context engineering is the emerging practice of optimizing the configuration and curation of tokens in language model context windows to achieve desired AI agent behavior, representing an evolution beyond traditional prompt engineering. It addresses the challenge of context rot and attention scarcity by strategically managing all information available to LLMs during inference, including system instructions, tools, external data, and message history.","tags":["context-engineering","prompt-engineering","llm","ai-agents","transformer-architecture","attention-mechanism"],"key_entities":[{"name":"Anthropic","type":"organization","confidence":0.95},{"name":"Large Language Models (LLM)","type":"technology","confidence":0.98},{"name":"Transformer Architecture","type":"technology","confidence":0.95},{"name":"Context Rot","type":"concept","confidence":0.92},{"name":"Prompt Engineering","type":"concept","confidence":0.96},{"name":"Attention Budget","type":"concept","confidence":0.9},{"name":"Model Context Protocol (MCP)","type":"technology","confidence":0.88}],"classification":"analysis","language":"en","confidence":0.85,"provenance":{"model":"claude-haiku-4-5","tool":"@stacklist/be@0.1.0","confidence":0.85,"timestamp":"2026-07-02T10:08:53.276Z"},"token_counts":{"approximate":5238,"cl100k":3779},"content_hash":"sha256:d90aeb407f487d382a837bd5098ebedf8ac60d068da3bc0040f4f39e9c0acd1f","acp_version":"0.2","body_available":true,"body_tokens":5238,"visibility":"public","agent_accessible":true,"status":"final"},"_links":{"self":"/api/public/card/171c021b-0b07-4b19-81be-51166223e7c0.json","html":"https://stacklist.com/card/171c021b-0b07-4b19-81be-51166223e7c0","md":"/api/public/card/171c021b-0b07-4b19-81be-51166223e7c0.md","stack_json":"/api/public/stack/e16dcdcb-06b9-481c-aef9-40b6d73a5c8e.json"}}