NormCode Canvas: Making LLM Agentic Workflows Development Sustainable via Case-Based Reasoning

TL;DR

NormCode Canvas introduces a novel case-based reasoning system for multi-step LLM workflows, enabling reliable, self-contained checkpoints and recursive learning to improve automation and debugging in AI workflows.

Contribution

The paper presents NormCode Canvas, a system that uses semi-formal planning language and recursive case learning to enhance the sustainability and reliability of LLM agent workflows.

Findings

Achieves presentation decks generation at ~40s per slide

Supports multi-step software engineering tasks with reasoning cycles

Enables self-sustaining ecosystem of plan debugging and refinement

Abstract

We present NormCode Canvas (v1.1.3), a deployed system realizing Case-Based Reasoning at two levels for multi-step LLM workflows. The foundation is NormCode, a semi-formal planning language whose compiler-verified scope rule ensures every execution checkpoint is a genuinely self-contained case -- eliminating the implicit shared state that makes retrieval unreliable and failure non-localizable in standard orchestration frameworks. Level 1 treats each checkpoint as a concrete case (suspended runtime); Fork implements retrieve-and-reuse, Value Override implements revision with automatic stale-boundary propagation. Level 2 treats each compiled plan as an abstract case; the compilation pipeline is itself a NormCode plan, enabling recursive case learning. Three structural properties follow: (C1) direct checkpoint inspection; (C2) pre-execution review via compiler-generated narrative; (C3) scope-bounded selective re-execution. Four deployed plans serve as structured evidence: PPT Generation produces presentation decks at ~40s per slide on commercial APIs; Code Assistant carries out multi-step software-engineering tasks spanning up to ten reasoning cycles; NC Compilations converts natural-language specifications into executable NormCode plans; and Canvas Assistant, when connected to an external AI code editor, automates plan debugging. Together these plans form a self-sustaining ecosystem in which plans produce, debug, and refine one another -- realizing cumulative case-based learning at system scale.