Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Tae Hee Jo, Kyung Hoon Hyun

TL;DR

This work proposes a method that parses raw csv/JSON logs into structured behavioral workflow graphs that map the provenance and flow of creative assets and discusses 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.

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.

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

TL;DR

This work proposes a method that parses raw csv/JSON logs into structured behavioral workflow graphs that map the provenance and flow of creative assets and discusses 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.

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.
Paper Structure (9 sections, 1 figure)

This paper contains 9 sections, 1 figure.

Table of Contents

  1. Introduction
  2. The Proposed Method
  3. Semantic Filtering and Classification (De-noising)
  4. Design Sequence Reconstruction (Visualizing the workflow history)
  5. Tokenization
  6. Implications: Enhancing Process-Aware Agents
  7. From Descriptive to Predictive Analysis
  8. Scaffolding Agentic Decisions
  9. Conclusion

Figures (1)

  • Figure 1: This abstract user behavioral workflow graph visualizes the branching evolution of a creative design process session. Blue nodes indicate image nodes, green nodes indicate video nodes, and pink nodes indicate prompt nodes. The structure reveals a user exploring multiple parallel variations before converging on a single lineage.