Software teams use new method to align AI agents with team intent
Mind the Intent Gap: A Methodology for Collaborative Agent-Driven Software Engineering
Software Engineering
Summary
AI tools are now part of software teams but often miss the real goals because people never fully write down their intentions. The authors say this happens because earlier teams covered for unclear goals by talking and guessing, but AI just guesses and drifts from the original plans. They created a new way called CAIA that keeps a clear knowledge base of what the software should do and makes sure team members agree on goals before AI helps change the project. This method is already being used in industry and aims to keep AI contributions better aligned with human intent.
What this means in practice
- •For software engineering teams: Coordinate human and AI team members by aligning shared intent before making software changes using a maintained knowledge base of the product.
- •For product management teams: Ensure clearer communication of project goals and changes by using a method that captures intent explicitly before AI tools update related documentation.
A position paper. It proposes an approach and reports no results.
Authors
Nicolas Tacheny, Tom Mens, Saïd Mahmoudi
Abstract
AI agents have entered software teams, first as tools and now as team members. They produce in minutes what used to take days, yet the expected gain in delivery often fails to appear. We argue that they are entering processes designed for people, which quietly relied on people to cover three of their weaknesses. The team's intent was never fully written down, because colleagues filled the gaps. An AI agent fills them too, though by guessing, and drifts from what the team had in mind. The reasoning behind each deliverable was already lost from one step to the next, and AI agents now inflate and deflate the documents passed along. The reasoning people did alone was partly private and now moves into AI tools that keep it private by nature. We present CAIA, for Collaborative Agentic Intent Alignment, a methodology for software teams that brings agents into the way they work. A knowledge base describes the product that a project maintains. For each Change, a micro-team aligns on its intent before agents evolve the product and propose updates to the Knowledge Base. The proposed CAIA methodology emerged from an industrial need and is already in use at Ni2, with a platform built to support it. We present the methodology and outline our plans to evaluate it further.