CocoFlow¶
Product or Programme · All products and programmes
Evidence · 3 claims (2 for, 1 mixed) · 2 studies (1 causal, 1 design),q2· 1 of 2 report an effect size · 3 claims rest on one study
Description¶
CocoFlow is an AI agent builder platform developed by COCOROBO Limited that enables teachers to create subject-specific pedagogical agents through prompt engineering, uploaded knowledge bases, and visual workflow design.
Components¶
- CocoFlow AI agent builder platform used by teachers to construct pedagogical agents: CocoFlow is an AI agent builder platform developed by the EdTech company COCOROBO Limited, used as the core tool in both workshop cycles. Its "editing interface supports teachers in constructing pedagogical agents through prompt engineering, knowledge base creation via file upload, and workflow design via a visual drag-and-drop canvas." Teachers were expected to independently create at least one deployable AI agent aligned with their instructional subject and learning objectives. Platform behavioral logs over eight weeks provided the engagement data for Cycle 1's clustering analysis. (Haiyang Xin et al. (2026))
- CocoFlow no-code AI agent creation platform: CocoFlow is a web-based platform enabling students to create conversational AI agents without programming. "Students drag pre-built components from a module library to a visual canvas, constructing dialogue workflows that define how agents respond to user inputs." Key components include intent recognition modules, entity extraction modules, and conditional logic nodes, with a real-time chat simulator for immediate testing and debugging. A pre-trained NLU engine handles intent recognition and entity extraction so students focus on system-level design. (Yimeng Sun et al. (2026))
Claims¶
- 87% of K-12 teachers ceased meaningful AI agent creation within three weeks of completing a two-day professional development workshop [~M]
- Five-day no-code AI agent creation improves students' CT self-perception, with large gains in abstract and algorithmic thinking and a medium gain in pattern recognition and generalization [+M]
- Iterative testing engagement during AI agent creation predicts CT self-efficacy gains after controlling for initial self-efficacy [+M]
Related Products and Programmes¶
Key Sources¶
- Haiyang Xin, Qiannan Niu, Shuang Li, Yimeng Sun, Ching Sing Chai, Lingyun Huang, Gaowei Chen. (2026). An Activity-Theoretical Approach to Teacher Professional Development in Pedagogical AI Agent Design. https://arxiv.org/abs/2605.12934
- Sun, Y., Xin, H., Li, S., Niu, Q., Chai, C. S., Huang, L., & Chen, G. (2025). Modeling AI-TPACK in Practice: Insights from Teachers' Multi-Agent Workflow Design. https://cocorobo.cc. doi:10.48550/arxiv.2605.13906
- Yimeng Sun, Haiyang Xin, Qiannan Niu, Shuang Li, Lingyun Huang, Gaowei Chen. (2026). Computational Thinking Development in AI Agent Creation: A Mixed-Methods Study. https://cocorobo.cc
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
cocoflow |
title |
CocoFlow |
description |
CocoFlow is an AI agent builder platform developed by COCOROBO Limited that enables teachers to create subject-specific pedagogical agents through prompt engineering, uploaded knowledge bases, and visual workflow design. |
status |
review |
product_kind |
software |
generated |
by process:settle-candidates on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.