Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AINeedsPlanner: A Workbook to Support Effective Collaboration Between AI Experts and Clients

Dae Hyun Kim, Hyungyu Shin, Shakhnozakhon Yadgarova, Jinho Son, Hariharan Subramonyam, Juho Kim

TL;DR

The paper tackles the challenge of effectively planning AI applications by bridging knowledge gaps between clients and AI experts. It introduces AINeedsPlanner, a boundary-object workbook informed by formative interviews and a main study, to structure the information flow across three planning phases and to support both client preparation and expert discussion. The authors identify a comprehensive 71-node information-need taxonomy and four dimensions that modulate these needs, and validate the workbook through two real-world case studies, demonstrating improved preparedness, communication completeness, and planning efficiency. The work advances practical guidance for client–AI expert collaborations and lays a foundation for adaptive, domain-aware planning tools that can scale with the evolving AI landscape.

Abstract

Clients often partner with AI experts to develop AI applications tailored to their needs. In these partnerships, careful planning and clear communication are critical, as inaccurate or incomplete specifications can result in misaligned model characteristics, expensive reworks, and potential friction between collaborators. Unfortunately, given the complexity of requirements ranging from functionality, data, and governance, effective guidelines for collaborative specification of requirements in client-AI expert collaborations are missing. In this work, we introduce AINeedsPlanner, a workbook that AI experts and clients can use to facilitate effective interchange and clear specifications. The workbook is based on (1) an interview of 10 completed AI application project teams, which identifies and characterizes steps in AI application planning and (2) a study with 12 AI experts, which defines a taxonomy of AI experts' information needs and dimensions that affect the information needs. Finally, we demonstrate the workbook's utility with two case studies in real-world settings.

AINeedsPlanner: A Workbook to Support Effective Collaboration Between AI Experts and Clients

TL;DR

The paper tackles the challenge of effectively planning AI applications by bridging knowledge gaps between clients and AI experts. It introduces AINeedsPlanner, a boundary-object workbook informed by formative interviews and a main study, to structure the information flow across three planning phases and to support both client preparation and expert discussion. The authors identify a comprehensive 71-node information-need taxonomy and four dimensions that modulate these needs, and validate the workbook through two real-world case studies, demonstrating improved preparedness, communication completeness, and planning efficiency. The work advances practical guidance for client–AI expert collaborations and lays a foundation for adaptive, domain-aware planning tools that can scale with the evolving AI landscape.

Abstract

Clients often partner with AI experts to develop AI applications tailored to their needs. In these partnerships, careful planning and clear communication are critical, as inaccurate or incomplete specifications can result in misaligned model characteristics, expensive reworks, and potential friction between collaborators. Unfortunately, given the complexity of requirements ranging from functionality, data, and governance, effective guidelines for collaborative specification of requirements in client-AI expert collaborations are missing. In this work, we introduce AINeedsPlanner, a workbook that AI experts and clients can use to facilitate effective interchange and clear specifications. The workbook is based on (1) an interview of 10 completed AI application project teams, which identifies and characterizes steps in AI application planning and (2) a study with 12 AI experts, which defines a taxonomy of AI experts' information needs and dimensions that affect the information needs. Finally, we demonstrate the workbook's utility with two case studies in real-world settings.
Paper Structure (37 sections, 5 figures, 3 tables)

This paper contains 37 sections, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Supporting AI Specification
  4. Workflows for Building AI Applications
  5. Collaboration for Building AI Applications
  6. Formative Interview: Understanding the Planning Process between AI Experts & Clients
  7. Participants
  8. Procedure
  9. Assessing RQ1: The Process of Planning
  10. Phase 1. Collaboration Preparation Phase
  11. Phase 2. Main Discussion Phase
  12. Phase 3. Execution Preparations
  13. Assessing RQ2: Documentation Form in Facilitating the Planning Process
  14. Main Study: Understanding & Taxonomizing the Information Needs of AI Experts from Clients
  15. Participants
  16. ...and 22 more sections

Figures (5)

  • Figure 1: An overview of the structure of the paper. We use the formative interview and the main study results to inform the AINeedsPlanner workbook, on which we performed two case studies.
  • Figure 2: The three phases of the AI application planning process in client-AI expert collaboration and the comprising steps of each of the phases.
  • Figure 3: A taxonomy of the information needs of an AI expert from their client as they sketch out their technical approach.
  • Figure 4: An outline of the workbook contents and a sample of the workbook content style.
  • Figure 5: A Venn diagram showing the commonalities and differences between the information covered by AINeedsPlanner and the information covered by Subramonyam et al. subramonyam2022solving.