From Logs to Agents: Reconstructing High-Level Creative Workflows from Low-Level Raw System Traces

TL;DR

This paper introduces a method to convert low-level system logs from AI creativity tools into high-level behavioral workflows, facilitating better understanding and assistance by future intelligent agents.

Contribution

It presents a novel approach to parse raw logs into structured workflow graphs, enabling analysis of user behavior and supporting process-aware AI systems.

Findings

Structured workflows enable sequence mining and probabilistic modeling.

High-level behavioral tokens improve interpretability of creative system logs.

Workflow abstraction is essential for developing intelligent, assistive agents.

Abstract

Current AI-based Creativity Support Tools (CSTs) generate massive amounts of low-level log data (e.g., clicks, parameter tweaks, metadata updates) that are hard to interpret as "creative intent". We argue that to enable future agentic systems to understand and assist users, we must first translate these noisy system traces into meaningful high-level user behavioral traces. We propose a method that parses raw csv/JSON logs into structured behavioral workflow graphs that map the provenance and flow of creative assets. By abstracting low-level system events into high-level behavioral tokens (e.g., MODIFY_Prompt, GENERATE_Image), this method enables downstream analyses like sequence mining and probabilistic modeling. We discuss how this structured workflow history is a prerequisite for "Process-Aware Agents" - systems capable of suggesting next design moves or explaining rationales based on a deeper understanding of the user's workflow patterns and history.