NormCode Canvas: Making LLM Agentic Workflows Development Sustainable via Case-Based Reasoning
This addresses the challenge of making LLM agentic workflows sustainable for developers, though it appears incremental as it builds on existing orchestration frameworks with specific improvements.
The paper tackles the problem of unreliable retrieval and non-localizable failures in multi-step LLM workflows by introducing NormCode Canvas, a system using Case-Based Reasoning at two levels, which enables plans to produce, debug, and refine each other, with results including generating presentation decks at about 40 seconds per slide on commercial APIs.
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.