Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Don't Vibe Code, Do Skele-Code: Interactive No-Code Notebooks for Subject Matter Experts to Build Lower-Cost Agentic Workflows

Sriram Gopalakrishnan

Abstract

Skele-Code is a natural-language and graph-based interface for building workflows with AI agents, designed especially for less or non-technical users. It supports incremental, interactive notebook-style development, and each step is converted to code with a required set of functions and behavior to enable incremental building of workflows. Agents are invoked only for code generation and error recovery, not orchestration or task execution. This agent-supported, but code-first approach to workflows, along with the context-engineering used in Skele-Code, can help reduce token costs compared to the multi-agent system approach to executing workflows. Skele-Code produces modular, easily extensible, and shareable workflows. The generated workflows can also be used as skills by agents, or as steps in other workflows.

Don't Vibe Code, Do Skele-Code: Interactive No-Code Notebooks for Subject Matter Experts to Build Lower-Cost Agentic Workflows

Abstract

Skele-Code is a natural-language and graph-based interface for building workflows with AI agents, designed especially for less or non-technical users. It supports incremental, interactive notebook-style development, and each step is converted to code with a required set of functions and behavior to enable incremental building of workflows. Agents are invoked only for code generation and error recovery, not orchestration or task execution. This agent-supported, but code-first approach to workflows, along with the context-engineering used in Skele-Code, can help reduce token costs compared to the multi-agent system approach to executing workflows. Skele-Code produces modular, easily extensible, and shareable workflows. The generated workflows can also be used as skills by agents, or as steps in other workflows.
Paper Structure (21 sections, 3 figures)

This paper contains 21 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Skele-Code Process and User Interface
  3. The Graph & NL Interface
  4. Backend and Context Engineering
  5. Graph JSON Representation
  6. Code Generation Process
  7. Orchestration and Execution of Workflows
  8. Node code Structure
  9. Context Engineering via Markov Blanket
  10. Coding Agent Flexibility
  11. Related Work
  12. Contributions and Benefits
  13. Tradeoffs
  14. Future Work
  15. Conclusion
  16. ...and 6 more sections

Figures (3)

  • Figure 1: A prototype of the Skele-Code interface showing the graph display of the workflow (bottom) and the input/output cells (top) that display information associated with the selected node in Natural Language.
  • Figure 2: The chat mode interface that allows the user to co-develop with an agent combing chat and the interactive UI
  • Figure 3: The interface to access files output by nodes. Selecting a file downloads it from the server and displays it on a new tab.