Orchid: Orchestrating Context Across Creative Workflows with Generative AI

2025-08-26

AI Summary

Current generative AI tools struggle to maintain contextual coherence across sessions and models in multi-stage creative workflows, forcing users to repeatedly restate details and contend with fragmented outputs and contextual drift—thereby undermining intent clarity and creative efficacy. To address this, we propose a context orchestration mechanism explicitly designed for iterative creative work. It is the first to systematically support explicit context referencing, inline selection, and implicit alignment, while enabling dynamic cross-turn monitoring and visual traceability. Integrating generative AI, context modeling, user-intent representation, and interaction design, our approach implements an end-to-end dynamic context management system. A 12-participant controlled study demonstrates that, compared to conventional tool combinations, our system significantly improves output innovativeness and feasibility, while enhancing users’ sense of control and intent alignment.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Context is critical for meaningful interactions between people and Generative AI (GenAI). Yet mainstream tools offer limited means to orchestrate it, particularly across workflows that span multiple interactions, sessions, and models, as often occurs in creative projects. Re specifying prior details, juggling diverse artifacts, and dealing with context drift overwhelm users, obscure intent, and curtail creativity. To address these challenges, we present Orchid, a system that gives its users affordances to specify, reference, and monitor context throughout evolving workflows. Specifically, Orchid enables users to (1) specify context related to the project, themselves, and different styles, (2) reference these via explicit mentions, inline selection, or implicit grounding, and (3) monitor context assigned to different interactions across the workflow. In a within-subjects study (n=12), participants using Orchid to execute creative tasks (compared to a baseline toolkit of web search, LLM-based chat, and digital notebooks) produced more novel and feasible outcomes, reporting greater alignment between their intent and the AI's responses, higher perceived control, and increased transparency. By prioritizing context orchestration, Orchid offers an actionable step toward next generation GenAI tools that support complex, iterative workflows - enabling creators and AI to stay aligned and augment their creative potential.

Problem

• Orchestrating context across multiple creative workflows with AI
• Addressing context drift and user overload in generative AI interactions
• Enabling specification, reference, and monitoring of contextual information

Innovation

• Orchid system for context orchestration
• Specify, reference, monitor context workflows
• Enables explicit mentions and implicit grounding