# ChainBuddy: An AI Agent System for Generating LLM Pipelines arXiv: https://arxiv.org/abs/2409.13588 ยท HTML: https://mlsanity.com/paper/2409.13588/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. - Builds on 26 of its 72 references that are in the map. - First posted on arXiv 20 Sep 2024. ## Placed in - LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/) ## Builds on (most cited first, 26 of 26) - [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023) - [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023) - [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020) - [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021) - [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023) - [Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences](https://mlsanity.com/paper/2404.12272/) (2024) - [PromptChainer: Chaining Large Language Model Prompts through Visual Programming](https://mlsanity.com/paper/2203.06566/) (2022) - [To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making](https://mlsanity.com/paper/2102.09692/) (2021) - [Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding](https://mlsanity.com/paper/2401.12954/) (2024) - [ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing](https://mlsanity.com/paper/2309.09128/) (2023) - [EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria](https://mlsanity.com/paper/2309.13633/) (2023) - [AutoEval Done Right: Using Synthetic Data for Model Evaluation](https://mlsanity.com/paper/2403.07008/) (2024) - [DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing](https://mlsanity.com/paper/2401.10880/) (2024) - [Better Synthetic Data by Retrieving and Transforming Existing Datasets](https://mlsanity.com/paper/2404.14361/) (2024) - [Aligning Language Models with Demonstrated Feedback](https://mlsanity.com/paper/2406.00888/) (2024) - [Teola: Towards End-to-End Optimization of LLM-based Applications](https://mlsanity.com/paper/2407.00326/) (2024) - [LLM Comparator: Visual Analytics for Side-by-Side Evaluation of Large Language Models](https://mlsanity.com/paper/2402.10524/) (2024) - [Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition](https://mlsanity.com/paper/2407.02651/) (2024) - [DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines](https://mlsanity.com/paper/2312.13382/) (2023) - [Prompt Sapper: A LLM-Empowered Production Tool for Building AI Chains](https://mlsanity.com/paper/2306.12028/) (2023) - [DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering](https://mlsanity.com/paper/1911.00061/) (2019) - [SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines](https://mlsanity.com/paper/2401.03038/) (2024) - [Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses](https://mlsanity.com/paper/2312.00763/) (2023) - [Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work](https://mlsanity.com/paper/2203.11085/) (2022) - [Imagining a Future of Designing with AI: Dynamic Grounding, Constructive Negotiation, and Sustainable Motivation](https://mlsanity.com/paper/2402.07342/) (2024) - [Co-audit: tools to help humans double-check AI-generated content](https://mlsanity.com/paper/2310.01297/) (2023) ## Built on by (most cited first, 6 of 6) - [Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI](https://mlsanity.com/paper/2505.19443/) (2025) - [Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations](https://mlsanity.com/paper/2509.11062/) (2025) - [ALLOY: Generating Reusable Agent Workflows from User Demonstration](https://mlsanity.com/paper/2510.10049/) (2025) - [XAgen: An Explainability Tool for Identifying and Correcting Failures in Multi-Agent Workflows](https://mlsanity.com/paper/2512.17896/) (2025) - [SHERPA: A Model-Driven Framework for Large Language Model Execution](https://mlsanity.com/paper/2509.00272/) (2025) - [Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocations](https://mlsanity.com/paper/2509.25492/) (2025) ## Abstract (arXiv) As large language models (LLMs) advance, their potential applications have grown significantly. However, it remains difficult to evaluate LLM behavior on user-defined tasks and craft effective pipelines to do so. Many users struggle with where to start, often referred to as the "blank page problem." ChainBuddy, an AI workflow generation assistant built into the ChainForge platform, aims to tackle this issue. From a single prompt or chat, ChainBuddy generates a starter evaluative LLM pipeline in ChainForge aligned to the user's requirements. ChainBuddy offers a straightforward and user-friendly way to plan and evaluate LLM behavior and make the process less daunting and more accessible across a wide range of possible tasks and use cases. We report a within-subjects user study comparing ChainBuddy to the baseline interface. We find that when using AI assistance, participants reported a less demanding workload, felt more confident, and produced higher quality pipelines evaluating LLM behavior. However, we also uncover a mismatch between subjective and objective ratings of performance: participants rated their successfulness similarly across conditions, while independent experts rated participant workflows significantly higher with AI assistance. Drawing connections to the Dunning-Kruger effect, we draw design implications for the future of workflow generation assistants to mitigate the risk of over-reliance.