Learn how Asana developed a smarter approach to AI context engineering. Discover our lessons on filtering, sorting, and summarizing data for better RAG system performance at scale.

AsanaEng's platform is a central hub for engineering teams and project managers, offering insights into agile project management, collaboration tools, and productivity techniques. Through articles, case studies, and best practices guides, AsanaEng offers insights into using Asana for project planning, task tracking, and team communication. Readers can learn about agile methodologies, sprint planning, and Kanban boards to streamline their workflows and achieve project success.

Asana Engineering

Asana developed an intent-augmented retrieval approach for AI systems that filters data based on user query intent before retrieval, rather than stuffing context windows with irrelevant information. Their context engineering strategy includes filtering at the field level, cross-encoder reranking, and intent-driven summarization, achieving 35% reduction in input tokens, 24% faster response times, and 30% lower costs while improving accuracy from 92-94% to 95-96%.

Stop Stuffing Prompts: How Asana Made Agents More Effective Through Context Engineering • Asana