Auditing and Controlling AI Agent Actions in Spreadsheets

2026-04-21

AI Summary

Current AI agents operating in spreadsheet environments often lack transparency when performing complex tasks, making it difficult for users to scrutinize assumptions, detect errors, or intervene in a timely manner. To address this limitation, this work proposes Pista, the first system to enable real-time visibility and control over AI agent decision-making within spreadsheets. Pista decomposes agent actions into interpretable steps and provides an interactive intervention interface, transforming the execution process into an auditable and controllable sequence of operations. This design empowers users to actively participate during task execution rather than being limited to post-hoc review. A user study (N=24) demonstrates that, compared to conventional post-execution review approaches, Pista significantly improves users’ task comprehension, error detection rates, and sense of co-ownership over the agent’s output.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Teamwork

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Advances in AI agent capabilities have outpaced users' ability to meaningfully oversee their execution. AI agents can perform sophisticated, multi-step knowledge work autonomously from start to finish, yet this process remains effectively inaccessible during execution, often buried within large volumes of intermediate reasoning and outputs: by the time users receive the output, all underlying decisions have already been made without their involvement. This lack of transparency leaves users unable to examine the agent's assumptions, identify errors before they propagate, or redirect execution when it deviates from their intent. The stakes are particularly high in spreadsheet environments, where process and artifact are inseparable. Each decision the agent makes is recorded directly in cells that belong to and reflect on the user. We introduce Pista, a spreadsheet AI agent that decomposes execution into auditable, controllable actions, providing users with visibility into the agent's decision-making process and the capacity to intervene at each step. A formative study (N = 8) and a within-subjects summative evaluation (N = 16) comparing Pista to a baseline agent demonstrated that active participation in execution influenced not only task outcomes but also users' comprehension of the task, their perception of the agent, and their sense of role within the workflow. Users identified their own intent reflected in the agent's actions, detected errors that post-hoc review would have failed to surface, and reported a sense of co-ownership over the resulting output. These findings indicate that meaningful human oversight of AI agents in knowledge work requires not improved post-hoc review mechanisms, but active participation in decisions as they are made.

Problem

• AI agent oversight
• transparency
• spreadsheet automation
• human-AI collaboration
• action auditability

Innovation

• auditable AI
• controllable actions
• human-AI collaboration
• spreadsheet agents
• real-time intervention