DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured Conversation

TL;DR

DevNous is an LLM-based multi-agent system that automates translating unstructured team conversations into structured IT project management artifacts, improving efficiency and accuracy in governance tasks.

Contribution

This work introduces a novel LLM-based multi-agent architecture for ambient administrative agents and provides the first public benchmark dataset for this domain.

Findings

Achieved 81.3% turn accuracy on the benchmark

F1-Score of 0.845 demonstrates strong performance

Validated the architectural pattern for ambient administrative agents

Abstract

The manual translation of unstructured team dialogue into the structured artifacts required for Information Technology (IT) project governance is a critical bottleneck in modern information systems management. We introduce DevNous, a Large Language Model-based (LLM) multi-agent expert system, to automate this unstructured-to-structured translation process. DevNous integrates directly into team chat environments, identifying actionable intents from informal dialogue and managing stateful, multi-turn workflows for core administrative tasks like automated task formalization and progress summary synthesis. To quantitatively evaluate the system, we introduce a new benchmark of 160 realistic, interactive conversational turns. The dataset was manually annotated with a multi-label ground truth and is publicly available. On this benchmark, DevNous achieves an exact match turn accuracy of 81.3\% and a multiset F1-Score of 0.845, providing strong evidence for its viability. The primary contributions of this work are twofold: (1) a validated architectural pattern for developing ambient administrative agents, and (2) the introduction of the first robust empirical baseline and public benchmark dataset for this challenging problem domain.