What Software Engineering Looks Like to AI Agents? -- An Empirical Study of AI-Only Technical Discourse on MoltBook

TL;DR

This study analyzes autonomous AI agent discourse on MoltBook, revealing a coherent, security-focused technical discussion that differs from human developer conversations by emphasizing trust, tooling, and automation over environment-specific details.

Contribution

It provides the first detailed empirical analysis of AI-only technical discourse, highlighting its themes, structure, and differences from human developer discussions.

Findings

Discourse is highly concentrated with 12 recurring themes, mainly Security and Trust.

AI discourse contains fewer concrete cues like code snippets and environment details.

It is coherent but selectively emphasizes security, tooling, and automation over local project details.

Abstract

AI agents are increasingly framed as software-engineering teammates, yet most studies examine them inside human-centered workflows. Little is known about the discourse autonomous AI agents produce when they interact mainly with one another. This paper examines what autonomous agents discuss on MoltBook, how that discourse is organized, and how it differs from human developer discourse. We combine human open coding of a 500-post sample, a concentration-plus-check topic-analysis pipeline over 4,707 English-filtered MoltBook technology posts, and a matched comparison with 5,211 human-generated GitHub Discussions posts. MoltBook technology discourse spans 12 recurring themes, led by Security and Trust (27.4%). At the community level, activity is highly concentrated: the largest submolt accounts for 63.5% of posts (Gini = 0.88), yet a stability-aware BERTopic pipeline still identifies 32 non-outlier sub-topics. Relative to the GitHub Discussions baseline, MoltBook discourse contains fewer concrete, context-rich cues such as code-formatted artifacts, environment details, runtime failures, and reproduction steps. Social mimicry appears only in limited form, while idealization is reflected mainly through lower hedging. Overall, AI-only technical discourse is coherent but selective. It repeatedly returns to security and trust, memory and context management, tooling and APIs, debugging and error handling, workflow automation, and infrastructure/ops, while omitting much of the project-local and runtime detail common in human developer discourse. This may reflect fewer environment-specific failures, reproduction steps, and other grounding cues in MoltBook.