Optimizing Research Processes and the GenAI-Assisted Workflow

Optimizing Research Processes and the GenAI-Assisted Workflow

📅 Monday 18/05 10:30-12:00h

📍 Main Hall

🔎 Needs Analysis

PhD candidates seek ways to streamline academic writing while maintaining critical thinking. This workshop offers a methodological solution using a “Task-Aligned GenAI Framework.” Beyond a generic tutorial, I present a structured approach where AI tools are matched to specific cognitive tasks to enhance quality, breaking the research process into three stages: Literature Review, processing, and synthesizing.

Assigning dedicated tools to each stage reduces cognitive load and ensures accuracy. This allows researchers to focus on generating insights without getting lost in technical complexities or AI hallucinations. It aligns with TEL principles by demonstrating how technology supports, rather than replaces, human inquiry. PhD students will gain experience in this framework, ensuring they leverage these tools to amplify their academic voice and produce high-quality research.

📒 Session Description

This “live lab” workshop transforms the literature review process using a “Task-Aligned GenAI Framework.” Participants work directly on their personal research topics, moving from raw articles to synthesized text through a structured four-step workflow:

1. Systematic Retrieval: Using semantic search protocols to map literature and isolate high-impact empirical studies.
2. “Knowledge Brain”: Uploading texts into a source-grounded AI environment for “Active Analysis”- interrogating documents to uncover hidden patterns and themes.
3. Matrix Extraction: Creating a Synthesis Matrix, a rigorous comparison table isolating methodology, findings, and limitations across papers.
4. “Matrix-to-Text”: Bridging reading and writing by converting structured matrix rows into cohesive academic paragraphs using generative writing assistants.

We conclude with a critical discussion on the “Human-in-the-Loop” principle, ensuring critical oversight and preserving the unique academic voice of the researcher.

💡 Learning Objectives

1. Apply advanced search protocols to locate high-impact empirical papers (Q1) and filter out irrelevant sources.
2. Utilize a source-grounded AI platform to build a personal “Theoretical Knowledge Brain” based on your own repository. This enables active reading, generates structured abstracts, identifies thematic patterns, and streamlines qualitative data analysis.
3. Create a detailed extraction table that isolates methodology, findings, comparisons, theoretical contributions, and other critical research components directly from the original text.
4. Execute the “Matrix-to-Text” Workflow: Practice converting a row of structured data into a cohesive academic paragraph using generative writing assistants.