Automating and Optimizing Prompts: ­ AI-driven Efficiency

Sunil Kumar (), Atreya ‘Chuck’ Chakraborty () and Poojan Patel ()
Additional contact information
Sunil Kumar: Roger Williams University
Atreya ‘Chuck’ Chakraborty: University of Massachusetts System
Poojan Patel: Bryant University

Chapter 9 in Prompt Engineering for Accounting and Finance, 2026, pp 295-339 from Springer

Abstract: Abstract This chapter examines prompt automation and optimization as a strategy for improving AI reliability, scalability, and efficiency in accounting and finance workflows. It explains how automated prompt engineering techniques—including auto-prompting and active prompting—shift prompt refinement from manual trial-and-error to structured, feedback-driven processes. Auto-prompting enables AI systems to generate, test, and select optimized prompt variations, improving consistency and reducing human intervention. Active prompting, inspired by active learning, focuses on identifying model weaknesses and refining prompts through targeted examples that address uncertain or error-prone cases. Through applied scenarios in expense auditing, valuation analysis, revenue recognition, and financial reporting, the chapter demonstrates how optimized prompts enhance compliance accuracy, reduce hallucinations, and improve decision support. By treating prompts as adaptive, optimizable components rather than static instructions, this chapter positions prompt optimization as a foundational mechanism for scaling trustworthy AI applications in professional finance environments.

Keywords: Auto-Prompting; Active Prompting; Prompt Optimization; AI Workflow Automation; Accounting AI Governance; Financial Data Quality Assurance; Scalable Prompt Engineering (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-032-11195-1_9

Ordering information: This item can be ordered from
http://www.springer.com/9783032111951

DOI: 10.1007/978-3-032-11195-1_9

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().