Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems

TL;DR

This paper proposes a systems-level data model for preserving durable, structured intermediate artifacts in AI systems to enhance inspectability, revisability, and maintainability of AI-generated work.

Contribution

It formalizes a data model for intermediate artifacts, distinguishing them from other AI outputs, and emphasizes their role in improving system transparency and revision capabilities.

Findings

Defines a formal data model for intermediate artifacts.

Distinguishes artifacts from chat transcripts and final answers.

Highlights the importance of artifact lineage and state resolution.

Abstract

Many AI systems are organized around loops in which models reason, call tools, observe results, and continue until a task is complete. These systems often produce final artifacts such as memos, plans, recommendations, and analyses, while the intermediate work that shaped those outputs remains ephemeral. For multi-step, revisable AI work, final artifacts are often lossy projections over upstream state. We argue that such systems should preserve durable, inspectable intermediate artifacts: typed, structured, addressable, versioned, dependency-aware, authoritative, and consumable by downstream computation. These artifacts are not the model's private chain-of-thought. They are maintained work products such as evidence maps, claim structures, criteria, assumptions, plans, transformation rules, synthesis procedures, unresolved tensions, and partial products that later humans and agents can inspect, revise, supersede, and improve. The contribution is a systems-level data model. We distinguish intermediate artifacts from chat transcripts, memory, hidden chain-of-thought, narration, thinking, and final answers; formalize additive and superseding update semantics with explicit current-state resolution; describe how artifact lineage supports durable intermediate state across revisions; and argue that evaluation must target maintained-state quality, not only final-output quality. The claim is not that artifacts make models smarter. It is that durable intermediate artifacts make AI-generated work more inspectable, revisable, and maintainable over time.